Search Results for author:
Found 292 papers, 113 papers with code
Dataflow graphs as complete causal graphs
Component-based development is one of the core principles behind modern software engineering practices.
Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap
We then use hyperspherical uniformity (which characterizes the degree of uniformity on the unit hypersphere) as a unified framework to quantify these two objectives.
Hindsight States: Blending Sim and Real Task Elements for Efficient Reinforcement Learning
Reinforcement learning has shown great potential in solving complex tasks when large amounts of data can be generated with little effort.
Posterior Annealing: Fast Calibrated Uncertainty for Regression
Bayesian deep learning approaches that allow uncertainty estimation for regression problems often converge slowly and yield poorly calibrated uncertainty estimates that can not be effectively used for quantification.
On the Interventional Kullback-Leibler Divergence
Modern machine learning approaches excel in static settings where a large amount of i. i. d.
Robustness Implies Fairness in Causal Algorithmic Recourse
Algorithmic recourse aims to disclose the inner workings of the black-box decision process in situations where decisions have significant consequences, by providing recommendations to empower beneficiaries to achieve a more favorable outcome.
The passive symmetries of machine learning
Our goal is to understand the implications of passive symmetries for machine learning: Which passive symmetries play a role (e. g., permutation symmetry in graph neural networks)?
Moûsai: Text-to-Music Generation with Long-Context Latent Diffusion
In our work, we investigate the potential of diffusion models for text-conditional music generation.
normflows: A PyTorch Package for Normalizing Flows
It allows to build normalizing flow models from a suite of base distributions, flow layers, and neural networks.
Multi armed bandits and quantum channel oracles
Multi armed bandits are one of the theoretical pillars of reinforcement learning.
Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning
Recent years have seen a surge of interest in learning high-level causal representations from low-level image pairs under interventions.
Understanding Stereotypes in Language Models: Towards Robust Measurement and Zero-Shot Debiasing
Generated texts from large pretrained language models have been shown to exhibit a variety of harmful, human-like biases about various demographics.
Evaluating vaccine allocation strategies using simulation-assisted causal modelling
Early on during a pandemic, vaccine availability is limited, requiring prioritisation of different population groups.
On the Relationship Between Explanation and Prediction: A Causal View
Explainability has become a central requirement for the development, deployment, and adoption of machine learning (ML) models and we are yet to understand what explanation methods can and cannot do.
Adapting to noise distribution shifts in flow-based gravitational-wave inference
Deep learning techniques for gravitational-wave parameter estimation have emerged as a fast alternative to standard samplers $\unicode{x2013}$ producing results of comparable accuracy.
FED-CD: Federated Causal Discovery from Interventional and Observational Data
We perform a comprehensive experimental evaluation on synthetic data that demonstrates that FED-CD enables effective aggregation of decentralized data for causal discovery without direct sample sharing, even when the contributing distributed data sets cover disjoint sets of interventions.
A General Purpose Neural Architecture for Geospatial Systems
Geospatial Information Systems are used by researchers and Humanitarian Assistance and Disaster Response (HADR) practitioners to support a wide variety of important applications.
Iterative Teaching by Data Hallucination
We consider the problem of iterative machine teaching, where a teacher sequentially provides examples based on the status of a learner under a discrete input space (i. e., a pool of finite samples), which greatly limits the teacher's capability.
Spectral Representation Learning for Conditional Moment Models
For nonparametric conditional moment models, efficient estimation often relies on preimposed conditions on various measures of ill-posedness of the hypothesis space, which are hard to validate when flexible models are used.
A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models
By grounding the behavioral analysis in a causal graph describing an intuitive reasoning process, we study the behavior of language models in terms of robustness and sensitivity to direct interventions in the input space.
Neural Attentive Circuits
Recent work has seen the development of general purpose neural architectures that can be trained to perform tasks across diverse data modalities.
On the Identifiability and Estimation of Causal Location-Scale Noise Models
We study the class of location-scale or heteroscedastic noise models (LSNMs), in which the effect $Y$ can be written as a function of the cause $X$ and a noise source $N$ independent of $X$, which may be scaled by a positive function $g$ over the cause, i. e., $Y = f(X) + g(X)N$.
Neural Importance Sampling for Rapid and Reliable Gravitational-Wave Inference
This shows a median sample efficiency of $\approx 10\%$ (two orders-of-magnitude better than standard samplers) as well as a ten-fold reduction in the statistical uncertainty in the log evidence.
When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment
Using a state-of-the-art large language model (LLM) as a basis, we propose a novel moral chain of thought (MORALCOT) prompting strategy that combines the strengths of LLMs with theories of moral reasoning developed in cognitive science to predict human moral judgments.
DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability
In representation learning, a common approach is to seek representations which disentangle the underlying factors of variation.
Bridging the Gap to Real-World Object-Centric Learning
Humans naturally decompose their environment into entities at the appropriate level of abstraction to act in the world.
Function Classes for Identifiable Nonlinear Independent Component Analysis
Several families of spurious solutions fitting perfectly the data, but that do not correspond to the ground truth factors can be constructed in generic settings.
Flow Annealed Importance Sampling Bootstrap
Normalizing flows are tractable density models that can approximate complicated target distributions, e. g. Boltzmann distributions of physical systems.
Homomorphism Autoencoder -- Learning Group Structured Representations from Observed Transitions
How can we acquire world models that veridically represent the outside world both in terms of what is there and in terms of how our actions affect it?
Discrete Key-Value Bottleneck
Deep neural networks perform well on classification tasks where data streams are i. i. d.
Probable Domain Generalization via Quantile Risk Minimization
By minimizing the $\alpha$-quantile of predictor's risk distribution over domains, QRM seeks predictors that perform well with probability $\alpha$.
Structural Causal 3D Reconstruction
This paper considers the problem of unsupervised 3D object reconstruction from in-the-wild single-view images.
Assaying Out-Of-Distribution Generalization in Transfer Learning
Since out-of-distribution generalization is a generally ill-posed problem, various proxy targets (e. g., calibration, adversarial robustness, algorithmic corruptions, invariance across shifts) were studied across different research programs resulting in different recommendations.
Adversarial Robustness
Out-of-Distribution Generalization
+1
Probing the Robustness of Independent Mechanism Analysis for Representation Learning
One aim of representation learning is to recover the original latent code that generated the data, a task which requires additional information or inductive biases.
Functional Generalized Empirical Likelihood Estimation for Conditional Moment Restrictions
Important problems in causal inference, economics, and, more generally, robust machine learning can be expressed as conditional moment restrictions, but estimation becomes challenging as it requires solving a continuum of unconditional moment restrictions.
Variational Causal Dynamics: Discovering Modular World Models from Interventions
In doing so, VCD significantly extends the capabilities of the current state-of-the-art in latent world models while also comparing favourably in terms of prediction accuracy.
AutoML Two-Sample Test
Two-sample tests are important in statistics and machine learning, both as tools for scientific discovery as well as to detect distribution shifts.
Sampling without Replacement Leads to Faster Rates in Finite-Sum Minimax Optimization
We obtain tight convergence rates for RR and SO and demonstrate that these strategies lead to faster convergence than uniform sampling.
Embrace the Gap: VAEs Perform Independent Mechanism Analysis
Leveraging self-consistency, we show that the ELBO converges to a regularized log-likelihood.
BaCaDI: Bayesian Causal Discovery with Unknown Interventions
Inferring causal structures from experimentation is a central task in many domains.
Amortized Inference for Causal Structure Learning
Rather than searching over structures, we train a variational inference model to directly predict the causal structure from observational or interventional data.
Original or Translated? A Causal Analysis of the Impact of Translationese on Machine Translation Performance
We show that these two factors have a large causal effect on the MT performance, in addition to the test-model direction mismatch highlighted by existing work on the impact of translationese.
Half-sibling regression meets exoplanet imaging: PSF modeling and subtraction using a flexible, domain knowledge-driven, causal framework
Our HSR-based method provides an alternative, flexible and promising approach to the challenge of modeling and subtracting the stellar PSF and systematic noise in exoplanet imaging data.
From Statistical to Causal Learning
We describe basic ideas underlying research to build and understand artificially intelligent systems: from symbolic approaches via statistical learning to interventional models relying on concepts of causality.
Causal de Finetti: On the Identification of Invariant Causal Structure in Exchangeable Data
It is known that under i.\, i.\, d assumption, even with infinite data, there is a limit to how fine-grained a causal structure we can identify.
Phenomenology of Double Descent in Finite-Width Neural Networks
`Double descent' delineates the generalization behaviour of models depending on the regime they belong to: under- or over-parameterized.
Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers
Algorithmic fairness is frequently motivated in terms of a trade-off in which overall performance is decreased so as to improve performance on disadvantaged groups where the algorithm would otherwise be less accurate.
Score matching enables causal discovery of nonlinear additive noise models
This paper demonstrates how to recover causal graphs from the score of the data distribution in non-linear additive (Gaussian) noise models.
Interventions, Where and How? Experimental Design for Causal Models at Scale
Existing methods in experimental design for causal discovery from limited data either rely on linear assumptions for the SCM or select only the intervention target.
Logical Fallacy Detection
In this paper, we propose the task of logical fallacy detection, and provide a new dataset (Logic) of logical fallacies generally found in text, together with an additional challenge set for detecting logical fallacies in climate change claims (LogicClimate).
On Pitfalls of Identifiability in Unsupervised Learning. A Note on: "Desiderata for Representation Learning: A Causal Perspective"
Model identifiability is a desirable property in the context of unsupervised representation learning.
Causal Inference Through the Structural Causal Marginal Problem
We introduce an approach to counterfactual inference based on merging information from multiple datasets.
Compositional Multi-Object Reinforcement Learning with Linear Relation Networks
Although reinforcement learning has seen remarkable progress over the last years, solving robust dexterous object-manipulation tasks in multi-object settings remains a challenge.
Physical Derivatives: Computing policy gradients by physical forward-propagation
Model-free and model-based reinforcement learning are two ends of a spectrum.
On the Adversarial Robustness of Causal Algorithmic Recourse
Algorithmic recourse seeks to provide actionable recommendations for individuals to overcome unfavorable classification outcomes from automated decision-making systems.
Learning soft interventions in complex equilibrium systems
Complex systems often contain feedback loops that can be described as cyclic causal models.
Towards Principled Disentanglement for Domain Generalization
To tackle this challenge, we first formalize the OOD generalization problem as constrained optimization, called Disentanglement-constrained Domain Generalization (DDG).
Group equivariant neural posterior estimation
We here describe an alternative method to incorporate equivariances under joint transformations of parameters and data.
GalilAI: Out-of-Task Distribution Detection using Causal Active Experimentation for Safe Transfer RL
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.
Out of Distribution (OOD) Detection
Reinforcement Learning (RL)
Cause-effect inference through spectral independence in linear dynamical systems: theoretical foundations
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.
Resampling Base Distributions of Normalizing Flows
Normalizing flows are a popular class of models for approximating probability distributions.
Ranked #42 on
Image Generation
on CIFAR-10
(bits/dimension metric)
Iterative Teaching by Label Synthesis
In this paper, we consider the problem of iterative machine teaching, where a teacher provides examples sequentially based on the current iterative learner.
Distributional Robustness Regularized Scenario Optimization with Application to Model Predictive Control
We provide a functional view of distributional robustness motivated by robust statistics and functional analysis.
Unsupervised Object Learning via Common Fate
Learning generative object models from unlabelled videos is a long standing problem and required for causal scene modeling.
Action-Sufficient State Representation Learning for Control with Structural Constraints
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.
Dynamic Inference with Neural Interpreters
Modern neural network architectures can leverage large amounts of data to generalize well within the training distribution.
You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction
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.
Boxhead: A Dataset for Learning Hierarchical Representations
Disentanglement is hypothesized to be beneficial towards a number of downstream tasks.
Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP
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.
Spatial Context Awareness for Unsupervised Change Detection in Optical Satellite Images
It uses this model to analyze differences in the pixel and its spatial context-based predictions in subsequent time periods for change detection.
Invariant Causal Representation Learning for Out-of-Distribution Generalization
Extensive experiments on both synthetic and real-world datasets show that our approach outperforms a variety of baseline methods.
On the interventional consistency of autoencoders
Autoencoders have played a crucial role in the field of representation learning since its inception, proving to be a flexible learning scheme able to accommodate various notions of optimality of the representation.
Direct Advantage Estimation
The predominant approach in reinforcement learning is to assign credit to actions based on the expected return.
Learning Neural Causal Models with Active Interventions
Discovering causal structures from data is a challenging inference problem of fundamental importance in all areas of science.
Visual Representation Learning Does Not Generalize Strongly Within the Same Domain
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.
The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agents
By training 240 representations and over 10, 000 reinforcement learning (RL) 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.
Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration
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.
Backward-Compatible Prediction Updates: A Probabilistic Approach
; and (ii) if the new predictions differ from the current ones, should we update?
Generalization and Robustness Implications in Object-Centric Learning
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.
Exploring the Latent Space of Autoencoders with Interventional Assays
Autoencoders exhibit impressive abilities to embed the data manifold into a low-dimensional latent space, making them a staple of representation learning methods.
Shallow Representation is Deep: Learning Uncertainty-aware and Worst-case Random Feature Dynamics
Random features is a powerful universal function approximator that inherits the theoretical rigor of kernel methods and can scale up to modern learning tasks.
Real-time gravitational-wave science with neural posterior estimation
We demonstrate unprecedented accuracy for rapid gravitational-wave parameter estimation with deep learning.
Algorithmic Recourse in Partially and Fully Confounded Settings Through Bounding Counterfactual Effects
Algorithmic recourse aims to provide actionable recommendations to individuals to obtain a more favourable outcome from an automated decision-making system.
Towards Total Recall in Industrial Anomaly Detection
Being able to spot defective parts is a critical component in large-scale industrial manufacturing.
Ranked #2 on
Anomaly Detection
on MVTec AD
Representation Learning for Out-of-distribution Generalization in Reinforcement Learning
Learning data representations that are useful for various downstream tasks is a cornerstone of artificial intelligence.
Out-of-Distribution Generalization
reinforcement-learning
+2
CausalAdv: Adversarial Robustness through the Lens of Causality
The adversarial vulnerability of deep neural networks has attracted significant attention in machine learning.
Independent mechanism analysis, a new concept?
Specifically, our approach is motivated by thinking of each source as independently influencing the mixing process.
Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style
A common practice is to perform data augmentation via hand-crafted transformations intended to leave the semantics of the data invariant.
Ranked #1 on
Image Classification
on Causal3DIdent
Causal Influence Detection for Improving Efficiency in Reinforcement Learning
Many reinforcement learning (RL) environments consist of independent entities that interact sparsely.
Instrument Space Selection for Kernel Maximum Moment Restriction
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.
The Inductive Bias of Quantum Kernels
Quantum computers offer the possibility to efficiently compute inner products of exponentially large density operators that are classically hard to compute.
Diffusion-Based Representation Learning
In contrast, the introduced diffusion-based representation learning relies on a new formulation of the denoising score matching objective and thus encodes the information needed for denoising.
DiBS: Differentiable Bayesian Structure Learning
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.
Fast and Slow Learning of Recurrent Independent Mechanisms
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.
Regret Bounds for Gaussian-Process Optimization in Large Domains
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.
Pyfectious: An individual-level simulator to discover optimal containment polices for epidemic diseases
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.
A prior-based approximate latent Riemannian metric
In this work we propose a surrogate conformal Riemannian metric in the latent space of a generative model that is simple, efficient and robust.
Learning with Hyperspherical Uniformity
Due to the over-parameterization nature, neural networks are a powerful tool for nonlinear function approximation.
Nonlinear Invariant Risk Minimization: A Causal Approach
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.
Finding Stable Matchings in PhD Markets with Consistent Preferences and Cooperative Partners
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
Towards Causal Representation Learning
The two fields of machine learning and graphical causality arose and developed separately.
Adversarially Robust Kernel Smoothing
We propose a scalable robust learning algorithm combining kernel smoothing and robust optimization.
Conditional Distributional Treatment Effect with Kernel Conditional Mean Embeddings and U-Statistic Regression
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.
Bayesian Quadrature on Riemannian Data Manifolds
Riemannian manifolds provide a principled way to model nonlinear geometric structure inherent in data.
A Witness Two-Sample Test
That is, the test set is used to simultaneously estimate the expectations and define the basis points, while the training set only serves to select the kernel and is discarded.
Spatially Structured Recurrent Modules
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.
Learning to interpret trajectories
By learning to predict trajectories of dynamical systems, model-based methods can make extensive use of all observations from past experience.
Learned residual Gerchberg-Saxton network for computer generated holography
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.
Meta Attention Networks: Meta-Learning Attention to Modulate Information Between Recurrent Independent Mechanisms
Decomposing knowledge into interchangeable pieces promises a generalization advantage when there are changes in distribution.
Dependency Structure Discovery from Interventions
Promising results have driven a recent surge of interest in continuous optimization methods for Bayesian network structure learning from observational data.
Invariant Causal Representation Learning
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).
Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation
We propose counterfactual RL algorithms to learn both population-level and individual-level policies.
Assaying Large-scale Testing Models to Interpret COVID-19 Case Numbers
Large-scale testing is considered key to assess the state of the current COVID-19 pandemic.
Applications Populations and Evolution
Causal analysis of Covid-19 Spread in Germany
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.
COVI-AgentSim: an Agent-based Model for Evaluating Methods of Digital Contact Tracing
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.
A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation
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.
On the Transfer of Disentangled Representations in Realistic Settings
Learning meaningful representations that disentangle the underlying structure of the data generating process is considered to be of key importance in machine learning.
Predicting Infectiousness for Proactive Contact Tracing
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).
Instrumental Variable Regression via Kernel Maximum Moment Loss
We investigate a simple objective for nonlinear instrumental variable (IV) regression based on a kernelized conditional moment restriction (CMR) known as a maximum moment restriction (MMR).
Function Contrastive Learning of Transferable Meta-Representations
This \emph{meta-representation}, which is computed from a few observed examples of the underlying function, is learned jointly with the predictive model.
On the Fairness of Causal Algorithmic Recourse
Algorithmic fairness is typically studied from the perspective of predictions.
Physically constrained causal noise models for high-contrast imaging of exoplanets
The detection of exoplanets in high-contrast imaging (HCI) data hinges on post-processing methods to remove spurious light from the host star.
A survey of algorithmic recourse: definitions, formulations, solutions, and prospects
Machine learning is increasingly used to inform decision-making in sensitive situations where decisions have consequential effects on individuals' lives.
CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning
To facilitate research addressing this problem, we propose CausalWorld, a benchmark for causal structure and transfer learning in a robotic manipulation environment.
Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning
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.
Function Contrastive Learning of Transferable Representations
Few-shot-learning seeks to find models that are capable of fast-adaptation to novel tasks which are not encountered during training.
Learning explanations that are hard to vary
In this paper, we investigate the principle that `good explanations are hard to vary' in the context of deep learning.
Real-time Prediction of COVID-19 related Mortality using Electronic Health Records
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.
Learning Dynamical Systems using Local Stability Priors
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.
TriFinger: An Open-Source Robot for Learning Dexterity
Dexterous object manipulation remains an open problem in robotics, despite the rapid progress in machine learning during the past decade.
Geometrically Enriched Latent Spaces
A common assumption in generative models is that the generator immerses the latent space into a Euclidean ambient space.
A Commentary on the Unsupervised Learning of Disentangled Representations
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.
S2RMs: Spatially Structured Recurrent Modules
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.
Causal Feature Selection via Orthogonal Search
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.
Relative gradient optimization of the Jacobian term in unsupervised deep learning
Learning expressive probabilistic models correctly describing the data is a ubiquitous problem in machine learning.
Metrizing Weak Convergence with Maximum Mean Discrepancies
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.)
On Disentangled Representations Learned From Correlated Data
The focus of disentanglement approaches has been on identifying independent factors of variation in data.
Structure by Architecture: Disentangled Representations without Regularization
We study the problem of self-supervised structured representation learning using autoencoders for generative modeling.
Kernel Distributionally Robust Optimization
We prove a theorem that generalizes the classical duality in the mathematical problem of moments.
Algorithmic recourse under imperfect causal knowledge: a probabilistic approach
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.
Learning to Play Table Tennis From Scratch using Muscular Robots
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.
Neural Lyapunov Redesign
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.
Learning Kernel Tests Without Data Splitting
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.
A machine learning route between band mapping and band structure
Electronic band structure (BS) and crystal structure are the two complementary identifiers of solid state materials.
Data Analysis, Statistics and Probability Materials Science Computational Physics
Necessary and sufficient conditions for causal feature selection in time series with latent common causes
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.
Simpson's paradox in Covid-19 case fatality rates: a mediation analysis of age-related causal effects
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
Crackovid: Optimizing Group Testing
We study the problem usually referred to as group testing in the context of COVID-19.
Disentangling Factors of Variations Using Few Labels
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.
Towards causal generative scene models via competition of experts
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.
Quantifying the Effects of Contact Tracing, Testing, and Containment Measures in the Presence of Infection Hotspots
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.
A theory of independent mechanisms for extrapolation in generative models
Generative models can be trained to emulate complex empirical data, but are they useful to make predictions in the context of previously unobserved environments?
Worst-Case Risk Quantification under Distributional Ambiguity using Kernel Mean Embedding in Moment Problem
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.
SLEIPNIR: Deterministic and Provably Accurate Feature Expansion for Gaussian Process Regression with Derivatives
Gaussian processes are an important regression tool with excellent analytic properties which allow for direct integration of derivative observations.
MYND: Unsupervised Evaluation of Novel BCI Control Strategies on Consumer Hardware
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
Testing Goodness of Fit of Conditional Density Models with Kernels
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 $r_x$.
Algorithmic Recourse: from Counterfactual Explanations to Interventions
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.
Weakly-Supervised Disentanglement Without Compromises
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.
A Kernel Mean Embedding Approach to Reducing Conservativeness in Stochastic Programming and Control
We apply kernel mean embedding methods to sample-based stochastic optimization and control.
Selecting causal brain features with a single conditional independence test per feature
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.
Perceiving the arrow of time in autoregressive motion
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.
A New Distribution-Free Concept for Representing, Comparing, and Propagating Uncertainty in Dynamical Systems with Kernel Probabilistic Programming
This work presents the concept of kernel mean embedding and kernel probabilistic programming in the context of stochastic systems.
Causality for Machine Learning
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.
Kernel-Guided Training of Implicit Generative Models with Stability Guarantees
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.
Kernel Stein Tests for Multiple Model Comparison
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).
Optimal experimental design via Bayesian optimization: active causal structure learning for Gaussian process networks
We study the problem of causal discovery through targeted interventions.
Learning Neural Causal Models from Unknown Interventions
Promising results have driven a recent surge of interest in continuous optimization methods for Bayesian network structure learning from observational data.
Learning by shaking: Computing policy gradients by physical forward-propagation
Model-free and model-based reinforcement learning are two ends of a spectrum.
Model-based Reinforcement Learning
Reinforcement Learning (RL)
Recurrent Independent Mechanisms
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.
Multidimensional Contrast Limited Adaptive Histogram Equalization
Contrast enhancement is an important preprocessing technique for improving the performance of downstream tasks in image processing and computer vision.
On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Dataset
Learning meaningful and compact representations with disentangled semantic aspects is considered to be of key importance in representation learning.