You need to log in to edit.

You can create a new account if you don't have one.

Or, discuss a change on Slack.

You can create a new account if you don't have one.

Or, discuss a change on Slack.

no code implementations • 10 Dec 2021 • Michel Besserve, Bernhard Schölkopf

Complex systems often contain feedback loops that can be described as cyclic causal models.

1 code implementation • 27 Nov 2021 • HANLIN ZHANG, Yi-Fan Zhang, Weiyang Liu, Adrian Weller, Bernhard Schölkopf, Eric P. Xing

To tackle this challenge, we first formalize the OOD generalization problem as constrained optimization, called Disentanglement-constrained Domain Generalization (DDG).

no code implementations • 25 Nov 2021 • Maximilian Dax, Stephen R. Green, Jonathan Gair, Michael Deistler, Bernhard Schölkopf, Jakob H. Macke

We here describe an alternative method to incorporate equivariances under joint transformations of parameters and data.

no code implementations • 29 Oct 2021 • Michel Besserve, Naji Shajarisales, Dominik Janzing, Bernhard Schölkopf

A new perspective has been provided based on the principle of Independence of Causal Mechanisms (ICM), leading to the Spectral Independence Criterion (SIC), postulating that the power spectral density (PSD) of the cause time series is uncorrelated with the squared modulus of the frequency response of the filter generating the effect.

1 code implementation • 29 Oct 2021 • Vincent Stimper, Bernhard Schölkopf, José Miguel Hernández-Lobato

Normalizing flows are a popular class of models for approximating probability distributions.

Ranked #34 on Image Generation on CIFAR-10 (bits/dimension metric)

no code implementations • 29 Oct 2021 • Sumedh A Sontakke, Stephen Iota, Zizhao Hu, Arash Mehrjou, Laurent Itti, Bernhard Schölkopf

Extending the successes in supervised learning methods to the reinforcement learning (RL) setting, however, is difficult due to the data generating process - RL agents actively query their environment for data, and the data are a function of the policy followed by the agent.

no code implementations • NeurIPS 2021 • Weiyang Liu, Zhen Liu, Hanchen Wang, Liam Paull, Bernhard Schölkopf, Adrian Weller

In this paper, we consider the problem of iterative machine teaching, where a teacher provides examples sequentially based on the current iterative learner.

no code implementations • 26 Oct 2021 • Yassine Nemmour, Bernhard Schölkopf, Jia-Jie Zhu

We provide a functional view of distributional robustness motivated by robust statistics and functional analysis.

no code implementations • 13 Oct 2021 • Matthias Tangemann, Steffen Schneider, Julius von Kügelgen, Francesco Locatello, Peter Gehler, Thomas Brox, Matthias Kümmerer, Matthias Bethge, Bernhard Schölkopf

Learning generative object models from unlabelled videos is a long standing problem and required for causal scene modeling.

no code implementations • NeurIPS 2021 • Nasim Rahaman, Muhammad Waleed Gondal, Shruti Joshi, Peter Gehler, Yoshua Bengio, Francesco Locatello, Bernhard Schölkopf

Modern neural network architectures can leverage large amounts of data to generalize well within the training distribution.

no code implementations • 12 Oct 2021 • Biwei Huang, Chaochao Lu, Liu Leqi, José Miguel Hernández-Lobato, Clark Glymour, Bernhard Schölkopf, Kun Zhang

Perceived signals in real-world scenarios are usually high-dimensional and noisy, and finding and using their representation that contains essential and sufficient information required by downstream decision-making tasks will help improve computational efficiency and generalization ability in the tasks.

no code implementations • 11 Oct 2021 • Osama Makansi, Julius von Kügelgen, Francesco Locatello, Peter Gehler, Dominik Janzing, Thomas Brox, Bernhard Schölkopf

Applying this procedure to state-of-the-art trajectory prediction methods on standard benchmark datasets shows that they are, in fact, unable to reason about interactions.

no code implementations • NeurIPS Workshop SVRHM 2021 • Yukun Chen, Andrea Dittadi, Frederik Träuble, Stefan Bauer, Bernhard Schölkopf

Disentanglement is hypothesized to be beneficial towards a number of downstream tasks.

1 code implementation • EMNLP 2021 • Zhijing Jin, Julius von Kügelgen, Jingwei Ni, Tejas Vaidhya, Ayush Kaushal, Mrinmaya Sachan, Bernhard Schölkopf

The principle of independent causal mechanisms (ICM) states that generative processes of real world data consist of independent modules which do not influence or inform each other.

no code implementations • 5 Oct 2021 • Lukas Kondmann, Aysim Toker, Sudipan Saha, Bernhard Schölkopf, Laura Leal-Taixé, Xiao Xiang Zhu

It uses this model to analyze differences in the pixel and its spatial context-based predictions in subsequent time periods for change detection.

no code implementations • 13 Sep 2021 • Hsiao-Ru Pan, Nico Gürtler, Alexander Neitz, Bernhard Schölkopf

The predominant approach is to assign credit based on the expected return.

1 code implementation • 6 Sep 2021 • Nino Scherrer, Olexa Bilaniuk, Yashas Annadani, Anirudh Goyal, Patrick Schwab, Bernhard Schölkopf, Michael C. Mozer, Yoshua Bengio, Stefan Bauer, Nan Rosemary Ke

Discovering causal structures from data is a challenging inference problem of fundamental importance in all areas of science.

1 code implementation • 17 Jul 2021 • Lukas Schott, Julius von Kügelgen, Frederik Träuble, Peter Gehler, Chris Russell, Matthias Bethge, Bernhard Schölkopf, Francesco Locatello, Wieland Brendel

An important component for generalization in machine learning is to uncover underlying latent factors of variation as well as the mechanism through which each factor acts in the world.

no code implementations • 12 Jul 2021 • Andrea Dittadi, Frederik Träuble, Manuel Wüthrich, Felix Widmaier, Peter Gehler, Ole Winther, Francesco Locatello, Olivier Bachem, Bernhard Schölkopf, Stefan Bauer

By training 240 representations and over 10, 000 reinforcement learning policies on a simulated robotic setup, we evaluate to what extent different properties of pretrained VAE-based representations affect the OOD generalization of downstream agents.

1 code implementation • 12 Jul 2021 • Cian Eastwood, Ian Mason, Christopher K. I. Williams, Bernhard Schölkopf

Existing methods for SFDA leverage entropy-minimization techniques which: (i) apply only to classification; (ii) destroy model calibration; and (iii) rely on the source model achieving a good level of feature-space class-separation in the target domain.

no code implementations • NeurIPS 2021 • Frederik Träuble, Julius von Kügelgen, Matthäus Kleindessner, Francesco Locatello, Bernhard Schölkopf, Peter Gehler

; and (ii) if the new predictions differ from the current ones, should we update?

no code implementations • 1 Jul 2021 • Andrea Dittadi, Samuele Papa, Michele De Vita, Bernhard Schölkopf, Ole Winther, Francesco Locatello

The idea behind object-centric representation learning is that natural scenes can better be modeled as compositions of objects and their relations as opposed to distributed representations.

no code implementations • 30 Jun 2021 • Felix Leeb, Stefan Bauer, Bernhard Schölkopf

The encoders and decoders of autoencoders effectively project the input onto learned manifolds in the latent space and data space respectively.

no code implementations • 24 Jun 2021 • Diego Agudelo-España, Yassine Nemmour, Bernhard Schölkopf, Jia-Jie Zhu

Random features is a powerful universal function approximator that inherits the theoretical rigor of kernel methods and can scale up to modern learning tasks.

no code implementations • 23 Jun 2021 • Maximilian Dax, Stephen R. Green, Jonathan Gair, Jakob H. Macke, Alessandra Buonanno, Bernhard Schölkopf

We demonstrate unprecedented accuracy for rapid gravitational-wave parameter estimation with deep learning.

no code implementations • 22 Jun 2021 • Julius von Kügelgen, Nikita Agarwal, Jakob Zeitler, Afsaneh Mastouri, Bernhard Schölkopf

Algorithmic recourse aims to provide actionable recommendations to individuals to obtain a more favourable outcome from an automated decision-making system.

7 code implementations • 15 Jun 2021 • Karsten Roth, Latha Pemula, Joaquin Zepeda, Bernhard Schölkopf, Thomas Brox, Peter Gehler

Being able to spot defective parts is a critical component in large-scale industrial manufacturing.

Ranked #2 on Anomaly Detection on MVTec AD (using extra training data)

no code implementations • ICML Workshop URL 2021 • Frederik Träuble, Andrea Dittadi, Manuel Wuthrich, Felix Widmaier, Peter Vincent Gehler, Ole Winther, Francesco Locatello, Olivier Bachem, Bernhard Schölkopf, Stefan Bauer

Learning data representations that are useful for various downstream tasks is a cornerstone of artificial intelligence.

no code implementations • 11 Jun 2021 • Yonggang Zhang, Mingming Gong, Tongliang Liu, Gang Niu, Xinmei Tian, Bo Han, Bernhard Schölkopf, Kun Zhang

The spurious correlation implies that the adversarial distribution is constructed via making the statistical conditional association between style information and labels drastically different from that in natural distribution.

1 code implementation • NeurIPS 2021 • Luigi Gresele, Julius von Kügelgen, Vincent Stimper, Bernhard Schölkopf, Michel Besserve

Specifically, our approach is motivated by thinking of each source as independently influencing the mixing process.

1 code implementation • NeurIPS 2021 • Julius von Kügelgen, Yash Sharma, Luigi Gresele, Wieland Brendel, Bernhard Schölkopf, Michel Besserve, Francesco Locatello

A common practice is to perform data augmentation via hand-crafted transformations intended to leave the semantics of the data invariant.

1 code implementation • 7 Jun 2021 • Rui Zhang, Krikamol Muandet, Bernhard Schölkopf, Masaaki Imaizumi

Kernel maximum moment restriction (KMMR) recently emerges as a popular framework for instrumental variable (IV) based conditional moment restriction (CMR) models with important applications in conditional moment (CM) testing and parameter estimation for IV regression and proximal causal learning.

1 code implementation • NeurIPS 2021 • Jonas M. Kübler, Simon Buchholz, Bernhard Schölkopf

Quantum computers offer the possibility to efficiently compute inner products of exponentially large density operators that are classically hard to compute.

1 code implementation • NeurIPS 2021 • Maximilian Seitzer, Bernhard Schölkopf, Georg Martius

Many reinforcement learning (RL) environments consist of independent entities that interact sparsely.

no code implementations • 29 May 2021 • Korbinian Abstreiter, Stefan Bauer, Bernhard Schölkopf, Arash Mehrjou

In contrast, the introduced diffusion based representation learning relies on a new formulation of the denoising score-matching objective and thus encodes information needed for denoising.

1 code implementation • NeurIPS 2021 • Lars Lorch, Jonas Rothfuss, Bernhard Schölkopf, Andreas Krause

In this work, we propose a general, fully differentiable framework for Bayesian structure learning (DiBS) that operates in the continuous space of a latent probabilistic graph representation.

no code implementations • 18 May 2021 • Kanika Madan, Nan Rosemary Ke, Anirudh Goyal, Bernhard Schölkopf, Yoshua Bengio

To study these ideas, we propose a particular training framework in which we assume that the pieces of knowledge an agent needs and its reward function are stationary and can be re-used across tasks.

1 code implementation • NeurIPS 2021 • Manuel Wüthrich, Bernhard Schölkopf, Andreas Krause

These regret bounds illuminate the relationship between the number of evaluations, the domain size (i. e. cardinality of finite domains / Lipschitz constant of the covariance function in continuous domains), and the optimality of the retrieved function value.

1 code implementation • 24 Mar 2021 • Arash Mehrjou, Ashkan Soleymani, Amin Abyaneh, Samir Bhatt, Bernhard Schölkopf, Stefan Bauer

Simulating the spread of infectious diseases in human communities is critical for predicting the trajectory of an epidemic and verifying various policies to control the devastating impacts of the outbreak.

no code implementations • 9 Mar 2021 • Georgios Arvanitidis, Bogdan Georgiev, Bernhard Schölkopf

In this work we propose a surrogate conformal Riemannian metric in the latent space of a generative model that is simple, efficient and robust.

1 code implementation • 2 Mar 2021 • Weiyang Liu, Rongmei Lin, Zhen Liu, Li Xiong, Bernhard Schölkopf, Adrian Weller

Due to the over-parameterization nature, neural networks are a powerful tool for nonlinear function approximation.

no code implementations • 24 Feb 2021 • Chaochao Lu, Yuhuai Wu, Jośe Miguel Hernández-Lobato, Bernhard Schölkopf

Finally, in the discussion, we further explore the aforementioned assumption and propose a more general hypothesis, called the Agnostic Hypothesis: there exist a set of hidden causal factors affecting both inputs and outcomes.

no code implementations • 23 Feb 2021 • Maximilian Mordig, Riccardo Della Vecchia, Nicolò Cesa-Bianchi, Bernhard Schölkopf

Our setting is motivated by a PhD market of students, advisors, and co-advisors, and can be generalized to supply chain networks viewed as $n$-sided markets.

Computer Science and Game Theory Theoretical Economics Combinatorics

no code implementations • 22 Feb 2021 • Bernhard Schölkopf, Francesco Locatello, Stefan Bauer, Nan Rosemary Ke, Nal Kalchbrenner, Anirudh Goyal, Yoshua Bengio

The two fields of machine learning and graphical causality arose and developed separately.

no code implementations • 16 Feb 2021 • Junhyung Park, Uri Shalit, Bernhard Schölkopf, Krikamol Muandet

We propose to analyse the conditional distributional treatment effect (CoDiTE), which, in contrast to the more common conditional average treatment effect (CATE), is designed to encode a treatment's distributional aspects beyond the mean.

1 code implementation • 16 Feb 2021 • Jia-Jie Zhu, Christina Kouridi, Yassine Nemmour, Bernhard Schölkopf

We propose the adversarially robust kernel smoothing (ARKS) algorithm, combining kernel smoothing, robust optimization, and adversarial training for robust learning.

1 code implementation • 12 Feb 2021 • Christian Fröhlich, Alexandra Gessner, Philipp Hennig, Bernhard Schölkopf, Georgios Arvanitidis

Riemannian manifolds provide a principled way to model nonlinear geometric structure inherent in data.

no code implementations • 10 Feb 2021 • Jonas M. Kübler, Wittawat Jitkrittum, Bernhard Schölkopf, Krikamol Muandet

Its statistic is given by the difference in expectations of the witness function, a real-valued function defined as a weighted sum of kernel evaluations on a set of basis points.

no code implementations • 1 Jan 2021 • Nan Rosemary Ke, Olexa Bilaniuk, Anirudh Goyal, Stefan Bauer, Bernhard Schölkopf, Michael Curtis Mozer, Hugo Larochelle, Christopher Pal, Yoshua Bengio

Promising results have driven a recent surge of interest in continuous optimization methods for Bayesian network structure learning from observational data.

no code implementations • ICLR 2021 • Kanika Madan, Nan Rosemary Ke, Anirudh Goyal, Bernhard Schölkopf, Yoshua Bengio

Decomposing knowledge into interchangeable pieces promises a generalization advantage when there are changes in distribution.

no code implementations • ICLR 2021 • Nasim Rahaman, Anirudh Goyal, Muhammad Waleed Gondal, Manuel Wuthrich, Stefan Bauer, Yash Sharma, Yoshua Bengio, Bernhard Schölkopf

Capturing the structure of a data-generating process by means of appropriate inductive biases can help in learning models that generalise well and are robust to changes in the input distribution.

no code implementations • 1 Jan 2021 • Chaochao Lu, Yuhuai Wu, José Miguel Hernández-Lobato, Bernhard Schölkopf

As an alternative, we propose Invariant Causal Representation Learning (ICRL), a learning paradigm that enables out-of-distribution generalization in the nonlinear setting (i. e., nonlinear representations and nonlinear classifiers).

no code implementations • ICLR 2021 • Alexander Neitz, Giambattista Parascandolo, Bernhard Schölkopf

By learning to predict trajectories of dynamical systems, model-based methods can make extensive use of all observations from past experience.

no code implementations • 1 Jan 2021 • Lennart Schlieder, Heiner Kremer, Valentin Volchkov, Kai Melde, Peer Fischer, Bernhard Schölkopf

Instead of an iterative optimization algorithm that converges to a (sub-)optimal solution, the inverse problem can be solved by training a neural network to directly estimate the inverse operator.

no code implementations • 16 Dec 2020 • Chaochao Lu, Biwei Huang, Ke Wang, José Miguel Hernández-Lobato, Kun Zhang, Bernhard Schölkopf

We propose counterfactual RL algorithms to learn both population-level and individual-level policies.

no code implementations • 3 Dec 2020 • Michel Besserve, Simon Buchholz, Bernhard Schölkopf

Large-scale testing is considered key to assess the state of the current COVID-19 pandemic.

Applications Populations and Evolution

no code implementations • NeurIPS 2020 • Atalanti Mastakouri, Bernhard Schölkopf

In this work, we study the causal relations among German regions in terms of the spread of Covid-19 since the beginning of the pandemic, taking into account the restriction policies that were applied by the different federal states.

no code implementations • 30 Oct 2020 • Prateek Gupta, Tegan Maharaj, Martin Weiss, Nasim Rahaman, Hannah Alsdurf, Abhinav Sharma, Nanor Minoyan, Soren Harnois-Leblanc, Victor Schmidt, Pierre-Luc St. Charles, Tristan Deleu, Andrew Williams, Akshay Patel, Meng Qu, Olexa Bilaniuk, Gaétan Marceau Caron, Pierre Luc Carrier, Satya Ortiz-Gagné, Marc-Andre Rousseau, David Buckeridge, Joumana Ghosn, Yang Zhang, Bernhard Schölkopf, Jian Tang, Irina Rish, Christopher Pal, Joanna Merckx, Eilif B. Muller, Yoshua Bengio

The rapid global spread of COVID-19 has led to an unprecedented demand for effective methods to mitigate the spread of the disease, and various digital contact tracing (DCT) methods have emerged as a component of the solution.

no code implementations • ICLR 2021 • Andrea Dittadi, Frederik Träuble, Francesco Locatello, Manuel Wüthrich, Vaibhav Agrawal, Ole Winther, Stefan Bauer, Bernhard Schölkopf

Learning meaningful representations that disentangle the underlying structure of the data generating process is considered to be of key importance in machine learning.

no code implementations • 27 Oct 2020 • Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar Rätsch, Sylvain Gelly, Bernhard Schölkopf, Olivier Bachem

The idea behind the \emph{unsupervised} learning of \emph{disentangled} representations is that real-world data is generated by a few explanatory factors of variation which can be recovered by unsupervised learning algorithms.

1 code implementation • ICLR 2021 • Yoshua Bengio, Prateek Gupta, Tegan Maharaj, Nasim Rahaman, Martin Weiss, Tristan Deleu, Eilif Muller, Meng Qu, Victor Schmidt, Pierre-Luc St-Charles, Hannah Alsdurf, Olexa Bilanuik, David Buckeridge, Gáetan Marceau Caron, Pierre-Luc Carrier, Joumana Ghosn, Satya Ortiz-Gagne, Chris Pal, Irina Rish, Bernhard Schölkopf, Abhinav Sharma, Jian Tang, Andrew Williams

Predictions are used to provide personalized recommendations to the individual via an app, as well as to send anonymized messages to the individual's contacts, who use this information to better predict their own infectiousness, an approach we call proactive contact tracing (PCT).

1 code implementation • 15 Oct 2020 • Rui Zhang, Masaaki Imaizumi, Bernhard Schölkopf, Krikamol Muandet

We propose a simple framework for nonlinear instrumental variable (IV) regression based on a kernelized conditional moment restriction (CMR) known as a maximum moment restriction (MMR).

no code implementations • 14 Oct 2020 • Muhammad Waleed Gondal, Shruti Joshi, Nasim Rahaman, Stefan Bauer, Manuel Wüthrich, Bernhard Schölkopf

This \emph{meta-representation}, which is computed from a few observed examples of the underlying function, is learned jointly with the predictive model.

no code implementations • 13 Oct 2020 • Julius von Kügelgen, Amir-Hossein Karimi, Umang Bhatt, Isabel Valera, Adrian Weller, Bernhard Schölkopf

Algorithmic fairness is typically studied from the perspective of predictions.

no code implementations • 12 Oct 2020 • Timothy D. Gebhard, Markus J. Bonse, Sascha P. Quanz, Bernhard Schölkopf

The detection of exoplanets in high-contrast imaging (HCI) data hinges on post-processing methods to remove spurious light from the host star.

no code implementations • ICLR 2021 • Ossama Ahmed, Frederik Träuble, Anirudh Goyal, Alexander Neitz, Yoshua Bengio, Bernhard Schölkopf, Manuel Wüthrich, Stefan Bauer

To facilitate research addressing this problem, we propose CausalWorld, a benchmark for causal structure and transfer learning in a robotic manipulation environment.

no code implementations • 8 Oct 2020 • Amir-Hossein Karimi, Gilles Barthe, Bernhard Schölkopf, Isabel Valera

Machine learning is increasingly used to inform decision-making in sensitive situations where decisions have consequential effects on individuals' lives.

1 code implementation • 7 Oct 2020 • Sumedh A. Sontakke, Arash Mehrjou, Laurent Itti, Bernhard Schölkopf

Inspired by this, we attempt to equip reinforcement learning agents with the ability to perform experiments that facilitate a categorization of the rolled-out trajectories, and to subsequently infer the causal factors of the environment in a hierarchical manner.

no code implementations • 28 Sep 2020 • Muhammad Waleed Gondal, Shruti Joshi, Nasim Rahaman, Stefan Bauer, Manuel Wuthrich, Bernhard Schölkopf

Few-shot-learning seeks to find models that are capable of fast-adaptation to novel tasks which are not encountered during training.

3 code implementations • ICLR 2021 • Giambattista Parascandolo, Alexander Neitz, Antonio Orvieto, Luigi Gresele, Bernhard Schölkopf

In this paper, we investigate the principle that `good explanations are hard to vary' in the context of deep learning.

no code implementations • 31 Aug 2020 • Patrick Schwab, Arash Mehrjou, Sonali Parbhoo, Leo Anthony Celi, Jürgen Hetzel, Markus Hofer, Bernhard Schölkopf, Stefan Bauer

Coronavirus Disease 2019 (COVID-19) is an emerging respiratory disease caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) with rapid human-to-human transmission and a high case fatality rate particularly in older patients.

no code implementations • 23 Aug 2020 • Arash Mehrjou, Andrea Iannelli, Bernhard Schölkopf

A coupled computational approach to simultaneously learn a vector field and the region of attraction of an equilibrium point from generated trajectories of the system is proposed.

2 code implementations • 8 Aug 2020 • Manuel Wüthrich, Felix Widmaier, Felix Grimminger, Joel Akpo, Shruti Joshi, Vaibhav Agrawal, Bilal Hammoud, Majid Khadiv, Miroslav Bogdanovic, Vincent Berenz, Julian Viereck, Maximilien Naveau, Ludovic Righetti, Bernhard Schölkopf, Stefan Bauer

Dexterous object manipulation remains an open problem in robotics, despite the rapid progress in machine learning during the past decade.

no code implementations • 2 Aug 2020 • Georgios Arvanitidis, Søren Hauberg, Bernhard Schölkopf

A common assumption in generative models is that the generator immerses the latent space into a Euclidean ambient space.

no code implementations • 28 Jul 2020 • Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar Rätsch, Sylvain Gelly, Bernhard Schölkopf, Olivier Bachem

The goal of the unsupervised learning of disentangled representations is to separate the independent explanatory factors of variation in the data without access to supervision.

no code implementations • 13 Jul 2020 • Nasim Rahaman, Anirudh Goyal, Muhammad Waleed Gondal, Manuel Wuthrich, Stefan Bauer, Yash Sharma, Yoshua Bengio, Bernhard Schölkopf

Capturing the structure of a data-generating process by means of appropriate inductive biases can help in learning models that generalize well and are robust to changes in the input distribution.

no code implementations • 6 Jul 2020 • Anant Raj, Stefan Bauer, Ashkan Soleymani, Michel Besserve, Bernhard Schölkopf

The problem of inferring the direct causal parents of a response variable among a large set of explanatory variables is of high practical importance in many disciplines.

1 code implementation • NeurIPS 2020 • Luigi Gresele, Giancarlo Fissore, Adrián Javaloy, Bernhard Schölkopf, Aapo Hyvärinen

Learning expressive probabilistic models correctly describing the data is a ubiquitous problem in machine learning.

no code implementations • 16 Jun 2020 • Carl-Johann Simon-Gabriel, Alessandro Barp, Bernhard Schölkopf, Lester Mackey

More precisely, we prove that, on a locally compact, non-compact, Hausdorff space, the MMD of a bounded continuous Borel measurable kernel k, whose reproducing kernel Hilbert space (RKHS) functions vanish at infinity, metrizes the weak convergence of probability measures if and only if k is continuous and integrally strictly positive definite (i. s. p. d.)

no code implementations • 14 Jun 2020 • Felix Leeb, Guilia Lanzillotta, Yashas Annadani, Michel Besserve, Stefan Bauer, Bernhard Schölkopf

We study the problem of self-supervised structured representation learning using autoencoders for generative modeling.

1 code implementation • 14 Jun 2020 • Frederik Träuble, Elliot Creager, Niki Kilbertus, Francesco Locatello, Andrea Dittadi, Anirudh Goyal, Bernhard Schölkopf, Stefan Bauer

The focus of disentanglement approaches has been on identifying independent factors of variation in data.

2 code implementations • 12 Jun 2020 • Jia-Jie Zhu, Wittawat Jitkrittum, Moritz Diehl, Bernhard Schölkopf

We prove a theorem that generalizes the classical duality in the mathematical problem of moments.

1 code implementation • NeurIPS 2020 • Amir-Hossein Karimi, Julius von Kügelgen, Bernhard Schölkopf, Isabel Valera

Recent work has discussed the limitations of counterfactual explanations to recommend actions for algorithmic recourse, and argued for the need of taking causal relationships between features into consideration.

no code implementations • 10 Jun 2020 • Dieter Büchler, Simon Guist, Roberto Calandra, Vincent Berenz, Bernhard Schölkopf, Jan Peters

This work is the first to (a) fail-safe learn of a safety-critical dynamic task using anthropomorphic robot arms, (b) learn a precision-demanding problem with a PAM-driven system despite the control challenges and (c) train robots to play table tennis without real balls.

1 code implementation • 6 Jun 2020 • Arash Mehrjou, Mohammad Ghavamzadeh, Bernhard Schölkopf

We provide theoretical results on the class of systems that can be treated with the proposed algorithm and empirically evaluate the effectiveness of our method using an exemplary dynamical system.

1 code implementation • NeurIPS 2020 • Jonas M. Kübler, Wittawat Jitkrittum, Bernhard Schölkopf, Krikamol Muandet

Modern large-scale kernel-based tests such as maximum mean discrepancy (MMD) and kernelized Stein discrepancy (KSD) optimize kernel hyperparameters on a held-out sample via data splitting to obtain the most powerful test statistics.

1 code implementation • 20 May 2020 • Rui Patrick Xian, Vincent Stimper, Marios Zacharias, Shuo Dong, Maciej Dendzik, Samuel Beaulieu, Bernhard Schölkopf, Martin Wolf, Laurenz Rettig, Christian Carbogno, Stefan Bauer, Ralph Ernstorfer

A common task in photoemission band mapping is to recover the underlying quasiparticle dispersion, which we call band structure reconstruction.

Data Analysis, Statistics and Probability Materials Science Computational Physics

no code implementations • 18 May 2020 • Atalanti A. Mastakouri, Bernhard Schölkopf, Dominik Janzing

We study the identification of direct and indirect causes on time series and provide conditions in the presence of latent variables, which we prove to be necessary and sufficient under some graph constraints.

1 code implementation • 14 May 2020 • Julius von Kügelgen, Luigi Gresele, Bernhard Schölkopf

We point out limitations and extensions for future work, and, finally, discuss the role of causal reasoning in the broader context of using AI to combat the Covid-19 pandemic.

Applications Methodology

no code implementations • 13 May 2020 • Louis Abraham, Gary Bécigneul, Bernhard Schölkopf

We study the problem usually referred to as group testing in the context of COVID-19.

no code implementations • ICLR Workshop LLD 2019 • Francesco Locatello, Michael Tschannen, Stefan Bauer, Gunnar Rätsch, Bernhard Schölkopf, Olivier Bachem

Recently, Locatello et al. (2019) demonstrated that unsupervised disentanglement learning without inductive biases is theoretically impossible and that existing inductive biases and unsupervised methods do not allow to consistently learn disentangled representations.

no code implementations • 27 Apr 2020 • Julius von Kügelgen, Ivan Ustyuzhaninov, Peter Gehler, Matthias Bethge, Bernhard Schölkopf

Learning how to model complex scenes in a modular way with recombinable components is a pre-requisite for higher-order reasoning and acting in the physical world.

2 code implementations • 15 Apr 2020 • Lars Lorch, Heiner Kremer, William Trouleau, Stratis Tsirtsis, Aron Szanto, Bernhard Schölkopf, Manuel Gomez-Rodriguez

Multiple lines of evidence strongly suggest that infection hotspots, where a single individual infects many others, play a key role in the transmission dynamics of COVID-19.

no code implementations • 1 Apr 2020 • Michel Besserve, Rémy Sun, Dominik Janzing, Bernhard Schölkopf

Generative models can be trained to emulate complex empirical data, but are they useful to make predictions in the context of previously unobserved environments?

no code implementations • 31 Mar 2020 • Jia-Jie Zhu, Wittawat Jitkrittum, Moritz Diehl, Bernhard Schölkopf

In order to anticipate rare and impactful events, we propose to quantify the worst-case risk under distributional ambiguity using a recent development in kernel methods -- the kernel mean embedding.

1 code implementation • 5 Mar 2020 • Emmanouil Angelis, Philippe Wenk, Bernhard Schölkopf, Stefan Bauer, Andreas Krause

Gaussian processes are an important regression tool with excellent analytic properties which allow for direct integration of derivative observations.

1 code implementation • 26 Feb 2020 • Matthias R. Hohmann, Lisa Konieczny, Michelle Hackl, Brian Wirth, Talha Zaman, Raffi Enficiaud, Moritz Grosse-Wentrup, Bernhard Schölkopf

We introduce MYND: A framework that couples consumer-grade recording hardware with an easy-to-use application for the unsupervised evaluation of BCI control strategies.

Human-Computer Interaction Neurons and Cognition 68U35 H.5.2

1 code implementation • 24 Feb 2020 • Wittawat Jitkrittum, Heishiro Kanagawa, Bernhard Schölkopf

We propose two nonparametric statistical tests of goodness of fit for conditional distributions: given a conditional probability density function $p(y|x)$ and a joint sample, decide whether the sample is drawn from $p(y|x)r_x(x)$ for some density $r_x$.

1 code implementation • 14 Feb 2020 • Amir-Hossein Karimi, Bernhard Schölkopf, Isabel Valera

As machine learning is increasingly used to inform consequential decision-making (e. g., pre-trial bail and loan approval), it becomes important to explain how the system arrived at its decision, and also suggest actions to achieve a favorable decision.

2 code implementations • ICML 2020 • Francesco Locatello, Ben Poole, Gunnar Rätsch, Bernhard Schölkopf, Olivier Bachem, Michael Tschannen

Third, we perform a large-scale empirical study and show that such pairs of observations are sufficient to reliably learn disentangled representations on several benchmark data sets.

1 code implementation • L4DC 2020 • Jia-Jie Zhu, Moritz Diehl, Bernhard Schölkopf

We apply kernel mean embedding methods to sample-based stochastic optimization and control.

no code implementations • NeurIPS 2019 • Atalanti Mastakouri, Bernhard Schölkopf, Dominik Janzing

We propose a constraint-based causal feature selection method for identifying causes of a given target variable, selecting from a set of candidate variables, while there can also be hidden variables acting as common causes with the target.

no code implementations • NeurIPS 2019 • Kristof Meding, Dominik Janzing, Bernhard Schölkopf, Felix A. Wichmann

We employ a so-called frozen noise paradigm enabling us to compare human performance with four different algorithms on a trial-by-trial basis: A causal inference algorithm exploiting the dependence structure of additive noise terms, a neurally inspired network, a Bayesian ideal observer model as well as a simple heuristic.

1 code implementation • 25 Nov 2019 • Jia-Jie Zhu, Krikamol Muandet, Moritz Diehl, Bernhard Schölkopf

This work presents the concept of kernel mean embedding and kernel probabilistic programming in the context of stochastic systems.

no code implementations • 24 Nov 2019 • Bernhard Schölkopf

Graphical causal inference as pioneered by Judea Pearl arose from research on artificial intelligence (AI), and for a long time had little connection to the field of machine learning.

no code implementations • 29 Oct 2019 • Arash Mehrjou, Wittawat Jitkrittum, Krikamol Muandet, Bernhard Schölkopf

Modern implicit generative models such as generative adversarial networks (GANs) are generally known to suffer from issues such as instability, uninterpretability, and difficulty in assessing their performance.

3 code implementations • NeurIPS 2019 • Jen Ning Lim, Makoto Yamada, Bernhard Schölkopf, Wittawat Jitkrittum

The first test, building on the post selection inference framework, provably controls the number of best models that are wrongly declared worse (false positive rate).

no code implementations • 9 Oct 2019 • Julius von Kügelgen, Paul K. Rubenstein, Bernhard Schölkopf, Adrian Weller

We study the problem of causal discovery through targeted interventions.

2 code implementations • 2 Oct 2019 • Nan Rosemary Ke, Olexa Bilaniuk, Anirudh Goyal, Stefan Bauer, Hugo Larochelle, Bernhard Schölkopf, Michael C. Mozer, Chris Pal, Yoshua Bengio

Promising results have driven a recent surge of interest in continuous optimization methods for Bayesian network structure learning from observational data.

no code implementations • 25 Sep 2019 • Arash Mehrjou, Ashkan Soleymani, Stefan Bauer, Bernhard Schölkopf

Model-free and model-based reinforcement learning are two ends of a spectrum.

4 code implementations • ICLR 2021 • Anirudh Goyal, Alex Lamb, Jordan Hoffmann, Shagun Sodhani, Sergey Levine, Yoshua Bengio, Bernhard Schölkopf

Learning modular structures which reflect the dynamics of the environment can lead to better generalization and robustness to changes which only affect a few of the underlying causes.

1 code implementation • 26 Jun 2019 • Vincent Stimper, Stefan Bauer, Ralph Ernstorfer, Bernhard Schölkopf, R. Patrick Xian

Contrast enhancement is an important preprocessing technique for improving the performance of downstream tasks in image processing and computer vision.

2 code implementations • NeurIPS 2019 • Muhammad Waleed Gondal, Manuel Wüthrich, Đorđe Miladinović, Francesco Locatello, Martin Breidt, Valentin Volchkov, Joel Akpo, Olivier Bachem, Bernhard Schölkopf, Stefan Bauer

Learning meaningful and compact representations with disentangled semantic aspects is considered to be of key importance in representation learning.

no code implementations • 7 Jun 2019 • Đorđe Miladinović, Muhammad Waleed Gondal, Bernhard Schölkopf, Joachim M. Buhmann, Stefan Bauer

Sequential data often originates from diverse domains across which statistical regularities and domain specifics exist.

no code implementations • NeurIPS 2019 • Francesco Locatello, Gabriele Abbati, Tom Rainforth, Stefan Bauer, Bernhard Schölkopf, Olivier Bachem

Recently there has been a significant interest in learning disentangled representations, as they promise increased interpretability, generalization to unseen scenarios and faster learning on downstream tasks.

no code implementations • 31 May 2019 • Jonas M. Kübler, Krikamol Muandet, Bernhard Schölkopf

The kernel mean embedding of probability distributions is commonly used in machine learning as an injective mapping from distributions to functions in an infinite dimensional Hilbert space.

1 code implementation • 28 May 2019 • Julius von Kügelgen, Alexander Mey, Marco Loog, Bernhard Schölkopf

While the success of semi-supervised learning (SSL) is still not fully understood, Sch\"olkopf et al. (2012) have established a link to the principle of independent causal mechanisms.

1 code implementation • 22 May 2019 • Stratis Tsirtsis, Behzad Tabibian, Moein Khajehnejad, Adish Singla, Bernhard Schölkopf, Manuel Gomez-Rodriguez

Using this characterization, we first show that, in general, we cannot expect to find optimal decision policies in polynomial time and there are cases in which deterministic policies are suboptimal.

no code implementations • 16 May 2019 • Luigi Gresele, Paul K. Rubenstein, Arash Mehrjou, Francesco Locatello, Bernhard Schölkopf

In contrast to known identifiability results for nonlinear ICA, we prove that independent latent sources with arbitrary mixing can be recovered as long as multiple, sufficiently different noisy views are available.

1 code implementation • 14 May 2019 • Wittawat Jitkrittum, Patsorn Sangkloy, Muhammad Waleed Gondal, Amit Raj, James Hays, Bernhard Schölkopf

We propose a novel procedure which adds "content-addressability" to any given unconditional implicit model e. g., a generative adversarial network (GAN).

no code implementations • 13 May 2019 • Behzad Tabibian, Vicenç Gómez, Abir De, Bernhard Schölkopf, Manuel Gomez Rodriguez

Can we design ranking models that understand the consequences of their proposed rankings and, more importantly, are able to avoid the undesirable ones?

no code implementations • 3 May 2019 • Francesco Locatello, Michael Tschannen, Stefan Bauer, Gunnar Rätsch, Bernhard Schölkopf, Olivier Bachem

Recently, Locatello et al. (2019) demonstrated that unsupervised disentanglement learning without inductive biases is theoretically impossible and that existing inductive biases and unsupervised methods do not allow to consistently learn disentangled representations.

no code implementations • ICLR 2019 • Carl-Johann Simon-Gabriel, Yann Ollivier, Léon Bottou, Bernhard Schölkopf, David Lopez-Paz

Over the past four years, neural networks have been proven vulnerable to adversarial images: targeted but imperceptible image perturbations lead to drastically different predictions.

2 code implementations • 18 Apr 2019 • Timothy D. Gebhard, Niki Kilbertus, Ian Harry, Bernhard Schölkopf

In the last few years, machine learning techniques, in particular convolutional neural networks, have been investigated as a method to replace or complement traditional matched filtering techniques that are used to detect the gravitational-wave signature of merging black holes.

3 code implementations • ICLR 2020 • Partha Ghosh, Mehdi S. M. Sajjadi, Antonio Vergari, Michael Black, Bernhard Schölkopf

Variational Autoencoders (VAEs) provide a theoretically-backed and popular framework for deep generative models.

no code implementations • ICLR Workshop DeepGenStruct 2019 • Ðorđe Miladinović, Waleed Gondal, Bernhard Schölkopf, Joachim M. Buhmann, Stefan Bauer

To learn robust cross-environment descriptions of sequences we introduce disentangled state space models (DSSM).

no code implementations • ICLR Workshop LLD 2019 • Mostafa Dehghani, Arash Mehrjou, Stephan Gouws, Jaap Kamps, Bernhard Schölkopf

Training labels are expensive to obtain and may be of varying quality, as some may be from trusted expert labelers while others might be from heuristics or other sources of weak supervision such as crowd-sourcing.

no code implementations • 6 Mar 2019 • Anant Raj, Luigi Gresele, Michel Besserve, Bernhard Schölkopf, Stefan Bauer

The problem of inferring the direct causal parents of a response variable among a large set of explanatory variables is of high practical importance in many disciplines.

no code implementations • 5 Mar 2019 • Biwei Huang, Kun Zhang, Jiji Zhang, Joseph Ramsey, Ruben Sanchez-Romero, Clark Glymour, Bernhard Schölkopf

In this paper, we develop a framework for causal discovery from such data, called Constraint-based causal Discovery from heterogeneous/NOnstationary Data (CD-NOD), to find causal skeleton and directions and estimate the properties of mechanism changes.

1 code implementation • 22 Feb 2019 • Gabriele Abbati, Philippe Wenk, Michael A. Osborne, Andreas Krause, Bernhard Schölkopf, Stefan Bauer

Stochastic differential equations are an important modeling class in many disciplines.

2 code implementations • 17 Feb 2019 • Philippe Wenk, Gabriele Abbati, Michael A. Osborne, Bernhard Schölkopf, Andreas Krause, Stefan Bauer

Parameter inference in ordinary differential equations is an important problem in many applied sciences and in engineering, especially in a data-scarce setting.

1 code implementation • 12 Feb 2019 • Diego Agudelo-España, Sebastian Gomez-Gonzalez, Stefan Bauer, Bernhard Schölkopf, Jan Peters

Online detection of instantaneous changes in the generative process of a data sequence generally focuses on retrospective inference of such change points without considering their future occurrences.

1 code implementation • 8 Feb 2019 • Niki Kilbertus, Manuel Gomez-Rodriguez, Bernhard Schölkopf, Krikamol Muandet, Isabel Valera

In this paper, we show that in this selective labels setting, learning a predictor directly only from available labeled data is suboptimal in terms of both fairness and utility.

2 code implementations • 30 Jan 2019 • Mateo Rojas-Carulla, Ilya Tolstikhin, Guillermo Luque, Nicholas Youngblut, Ruth Ley, Bernhard Schölkopf

We introduce GeNet, a method for shotgun metagenomic classification from raw DNA sequences that exploits the known hierarchical structure between labels for training.

no code implementations • 26 Jan 2019 • Arash Mehrjou, Wittawat Jitkrittum, Krikamol Muandet, Bernhard Schölkopf

Modern implicit generative models such as generative adversarial networks (GANs) are generally known to suffer from issues such as instability, uninterpretability, and difficulty in assessing their performance.

1 code implementation • 26 Dec 2018 • Chaochao Lu, Bernhard Schölkopf, José Miguel Hernández-Lobato

Using this benchmark, we demonstrate that the proposed algorithms are superior to traditional RL methods in confounded environments with observational data.

no code implementations • ICLR 2020 • Michel Besserve, Arash Mehrjou, Rémy Sun, Bernhard Schölkopf

Deep generative models can emulate the perceptual properties of complex image datasets, providing a latent representation of the data.

no code implementations • 3 Dec 2018 • Niki Kilbertus, Giambattista Parascandolo, Bernhard Schölkopf

Anti-causal models are used to drive this search, but a causal model is required for validation.

6 code implementations • ICML 2019 • Francesco Locatello, Stefan Bauer, Mario Lucic, Gunnar Rätsch, Sylvain Gelly, Bernhard Schölkopf, Olivier Bachem

The key idea behind the unsupervised learning of disentangled representations is that real-world data is generated by a few explanatory factors of variation which can be recovered by unsupervised learning algorithms.

no code implementations • 14 Nov 2018 • Arash Mehrjou, Bernhard Schölkopf

Filtering is a general name for inferring the states of a dynamical system given observations.

no code implementations • 31 Oct 2018 • Raphael Suter, Đorđe Miladinović, Bernhard Schölkopf, Stefan Bauer

The ability to learn disentangled representations that split underlying sources of variation in high dimensional, unstructured data is important for data efficient and robust use of neural networks.

3 code implementations • NeurIPS 2018 • Wittawat Jitkrittum, Heishiro Kanagawa, Patsorn Sangkloy, James Hays, Bernhard Schölkopf, Arthur Gretton

Given two candidate models, and a set of target observations, we address the problem of measuring the relative goodness of fit of the two models.

1 code implementation • 31 Aug 2018 • Sebastian Gomez-Gonzalez, Gerhard Neumann, Bernhard Schölkopf, Jan Peters

However, to be able to capture variability and correlations between different joints, a probabilistic movement primitive requires the estimation of a larger number of parameters compared to their deterministic counterparts, that focus on modeling only the mean behavior.

2 code implementations • NeurIPS 2018 • Alexander Neitz, Giambattista Parascandolo, Stefan Bauer, Bernhard Schölkopf

We introduce a method which enables a recurrent dynamics model to be temporally abstract.

1 code implementation • 31 Jul 2018 • Muhammad Waleed Gondal, Bernhard Schölkopf, Michael Hirsch

Moreover, we show that a texture representation of those deep features better capture the perceptual quality of an image than the original deep features.

no code implementations • 20 Jul 2018 • Eduardo Pérez-Pellitero, Mehdi S. M. Sajjadi, Michael Hirsch, Bernhard Schölkopf

Together with a video discriminator, we also propose additional loss functions to further reinforce temporal consistency in the generated sequences.

3 code implementations • 4 Jun 2018 • Niklas Pfister, Sebastian Weichwald, Peter Bühlmann, Bernhard Schölkopf

We introduce coroICA, confounding-robust independent component analysis, a novel ICA algorithm which decomposes linearly mixed multivariate observations into independent components that are corrupted (and rendered dependent) by hidden group-wise stationary confounding.

no code implementations • 27 May 2018 • Arash Mehrjou, Friedrich Solowjow, Sebastian Trimpe, Bernhard Schölkopf

Apart from its application for encoding a sequence of observations, we propose to use the compression achieved by this encoding as a criterion for model selection.

1 code implementation • 21 May 2018 • Saeed Saremi, Arash Mehrjou, Bernhard Schölkopf, Aapo Hyvärinen

We present the utility of DEEN in learning the energy, the score function, and in single-step denoising experiments for synthetic and high-dimensional data.

1 code implementation • 4 May 2018 • Matthias Bauer, Valentin Volchkov, Michael Hirsch, Bernhard Schölkopf

The modulation transfer function (MTF) is widely used to characterise the performance of optical systems.

no code implementations • 30 Apr 2018 • Francesco Locatello, Damien Vincent, Ilya Tolstikhin, Gunnar Rätsch, Sylvain Gelly, Bernhard Schölkopf

A common assumption in causal modeling posits that the data is generated by a set of independent mechanisms, and algorithms should aim to recover this structure.

no code implementations • ICML 2018 • Francesco Locatello, Anant Raj, Sai Praneeth Karimireddy, Gunnar Rätsch, Bernhard Schölkopf, Sebastian U. Stich, Martin Jaggi

Exploiting the connection between the two algorithms, we present a unified analysis of both, providing affine invariant sublinear $\mathcal{O}(1/t)$ rates on smooth objectives and linear convergence on strongly convex objectives.

no code implementations • 16 Mar 2018 • Philipp Geiger, Michel Besserve, Justus Winkelmann, Claudius Proissl, Bernhard Schölkopf

We study data-driven assistants that provide congestion forecasts to users of shared facilities (roads, cafeterias, etc.

1 code implementation • 5 Mar 2018 • Rohit Babbar, Bernhard Schölkopf

The goal in extreme multi-label classification is to learn a classifier which can assign a small subset of relevant labels to an instance from an extremely large set of target labels.

Extreme Multi-Label Classification
General Classification
**+1**

no code implementations • 19 Feb 2018 • Patrick Blöbaum, Dominik Janzing, Takashi Washio, Shohei Shimizu, Bernhard Schölkopf

We address the problem of inferring the causal direction between two variables by comparing the least-squares errors of the predictions in both possible directions.

no code implementations • ICML 2018 • Mehdi S. M. Sajjadi, Giambattista Parascandolo, Arash Mehrjou, Bernhard Schölkopf

A possible explanation for training instabilities is the inherent imbalance between the networks: While the discriminator is trained directly on both real and fake samples, the generator only has control over the fake samples it produces since the real data distribution is fixed by the choice of a given dataset.

1 code implementation • ICLR 2019 • Carl-Johann Simon-Gabriel, Yann Ollivier, Léon Bottou, Bernhard Schölkopf, David Lopez-Paz

Over the past few years, neural networks were proven vulnerable to adversarial images: targeted but imperceptible image perturbations lead to drastically different predictions.

1 code implementation • ICML 2018 • Giambattista Parascandolo, Niki Kilbertus, Mateo Rojas-Carulla, Bernhard Schölkopf

The approach is unsupervised and based on a set of experts that compete for data generated by the mechanisms, driving specialization.

no code implementations • ICLR 2018 • Mostafa Dehghani, Arash Mehrjou, Stephan Gouws, Jaap Kamps, Bernhard Schölkopf

To this end, we propose "fidelity-weighted learning" (FWL), a semi-supervised student-teacher approach for training deep neural networks using weakly-labeled data.

1 code implementation • ICML 2018 • Matej Balog, Ilya Tolstikhin, Bernhard Schölkopf

First, releasing (an estimate of) the kernel mean embedding of the data generating random variable instead of the database itself still allows third-parties to construct consistent estimators of a wide class of population statistics.

1 code implementation • ICCV 2017 • Patrick Wieschollek, Michael Hirsch, Bernhard Schölkopf, Hendrik P. A. Lensch

As handheld video cameras are now commonplace and available in every smartphone, images and videos can be recorded almost everywhere at anytime.

no code implementations • 4 Jul 2017 • Paul K. Rubenstein, Sebastian Weichwald, Stephan Bongers, Joris M. Mooij, Dominik Janzing, Moritz Grosse-Wentrup, Bernhard Schölkopf

Complex systems can be modelled at various levels of detail.

no code implementations • NeurIPS 2017 • Niki Kilbertus, Mateo Rojas-Carulla, Giambattista Parascandolo, Moritz Hardt, Dominik Janzing, Bernhard Schölkopf

Going beyond observational criteria, we frame the problem of discrimination based on protected attributes in the language of causal reasoning.

no code implementations • NeurIPS 2017 • Shixiang Gu, Timothy Lillicrap, Zoubin Ghahramani, Richard E. Turner, Bernhard Schölkopf, Sergey Levine

Off-policy model-free deep reinforcement learning methods using previously collected data can improve sample efficiency over on-policy policy gradient techniques.

no code implementations • ICLR 2018 • Matthias Bauer, Mateo Rojas-Carulla, Jakub Bartłomiej Świątkowski, Bernhard Schölkopf, Richard E. Turner

The goal is to generalise from an initial large-scale classification task to a separate task comprising new classes and small numbers of examples.

no code implementations • 21 May 2017 • Arash Mehrjou, Bernhard Schölkopf, Saeed Saremi

We introduce a novel framework for adversarial training where the target distribution is annealed between the uniform distribution and the data distribution.

no code implementations • 5 May 2017 • Michel Besserve, Naji Shajarisales, Bernhard Schölkopf, Dominik Janzing

The postulate of independence of cause and mechanism (ICM) has recently led to several new causal discovery algorithms.

no code implementations • ICCV 2017 • Tae Hyun Kim, Kyoung Mu Lee, Bernhard Schölkopf, Michael Hirsch

We show the superiority of the proposed method in an extensive experimental evaluation.

no code implementations • 27 Mar 2017 • Lei Xiao, Felix Heide, Wolfgang Heidrich, Bernhard Schölkopf, Michael Hirsch

Recently, several discriminative learning approaches have been proposed for effective image restoration, achieving convincing trade-off between image quality and computational efficiency.

1 code implementation • NeurIPS 2017 • Ilya Tolstikhin, Sylvain Gelly, Olivier Bousquet, Carl-Johann Simon-Gabriel, Bernhard Schölkopf

Generative Adversarial Networks (GAN) (Goodfellow et al., 2014) are an effective method for training generative models of complex data such as natural images.

3 code implementations • ICCV 2017 • Mehdi S. M. Sajjadi, Bernhard Schölkopf, Michael Hirsch

Single image super-resolution is the task of inferring a high-resolution image from a single low-resolution input.

no code implementations • 6 Dec 2016 • Anant Raj, Abhishek Kumar, Youssef Mroueh, P. Thomas Fletcher, Bernhard Schölkopf

We consider transformations that form a \emph{group} and propose an approach based on kernel methods to derive local group invariant representations.

no code implementations • NeurIPS 2016 • Ilya O. Tolstikhin, Bharath K. Sriperumbudur, Bernhard Schölkopf

Maximum Mean Discrepancy (MMD) is a distance on the space of probability measures which has found numerous applications in machine learning and nonparametric testing.

no code implementations • 24 Oct 2016 • Behzad Tabibian, Isabel Valera, Mehrdad Farajtabar, Le Song, Bernhard Schölkopf, Manuel Gomez-Rodriguez

Then, we propose a temporal point process modeling framework that links these temporal traces to robust, unbiased and interpretable notions of information reliability and source trustworthiness.

no code implementations • NeurIPS 2016 • Carl-Johann Simon-Gabriel, Adam Ścibior, Ilya Tolstikhin, Bernhard Schölkopf

We provide a theoretical foundation for non-parametric estimation of functions of random variables using kernel mean embeddings.

no code implementations • 23 Sep 2016 • Anant Raj, Jakob Olbrich, Bernd Gärtner, Bernhard Schölkopf, Martin Jaggi

We propose a new framework for deriving screening rules for convex optimization problems.

no code implementations • 6 Sep 2016 • Mehdi S. M. Sajjadi, Rolf Köhler, Bernhard Schölkopf, Michael Hirsch

Light field photography captures rich structural information that may facilitate a number of traditional image processing and computer vision tasks.

no code implementations • 15 Jul 2016 • Patrick Wieschollek, Bernhard Schölkopf, Hendrik P. A. Lensch, Michael Hirsch

We present a neural network model approach for multi-frame blind deconvolution.

no code implementations • 14 Jun 2016 • Philipp Geiger, Katja Hofmann, Bernhard Schölkopf

The amount of digitally available but heterogeneous information about the world is remarkable, and new technologies such as self-driving cars, smart homes, or the internet of things may further increase it.

no code implementations • 31 May 2016 • Krikamol Muandet, Kenji Fukumizu, Bharath Sriperumbudur, Bernhard Schölkopf

Next, we discuss the Hilbert space embedding for conditional distributions, give theoretical insights, and review some applications.