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 • ICLR 2022 • Sidak Pal Singh, Aurelien Lucchi, Thomas Hofmann, Bernhard Schölkopf

`Double descent' delineates the generalization behaviour of models depending on the regime they belong to: under- or over-parameterized.

2 code implementations • ICLR 2022 • Gregor Bachmann, Thomas Hofmann, Aurélien Lucchi

Despite the tremendous empirical success of deep learning models to solve various learning tasks, our theoretical understanding of their generalization ability is very limited.

1 code implementation • 26 Jan 2022 • Dimitri von Rütte, Luca Biggio, Yannic Kilcher, Thomas Hofmann

Generating music with deep neural networks has been an area of active research in recent years.

no code implementations • 2 Jan 2022 • Enea Monzio Compagnoni, Luca Biggio, Antonio Orvieto, Thomas Hofmann, Josef Teichmann

Time series analysis is a widespread task in Natural Sciences, Social Sciences, and Engineering.

no code implementations • 1 Sep 2021 • Leonard Adolphs, Benjamin Boerschinger, Christian Buck, Michelle Chen Huebscher, Massimiliano Ciaramita, Lasse Espeholt, Thomas Hofmann, Yannic Kilcher, Sascha Rothe, Pier Giuseppe Sessa, Lierni Sestorain Saralegui

This paper presents first successful steps in designing agents that learn meta-strategies for iterative query refinement.

1 code implementation • 4 Aug 2021 • Leonard Adolphs, Shehzaad Dhuliawala, Thomas Hofmann

We apply this approach of querying by example to the LAMA probe and obtain substantial improvements of up to 37. 8% for BERT-large on the T-REx data when providing only 10 demonstrations--even outperforming a baseline that queries the model with up to 40 paraphrases of the question.

no code implementations • NeurIPS 2021 • Sidak Pal Singh, Gregor Bachmann, Thomas Hofmann

Moreover, we demonstrate that our bounds remain faithful as an estimate of the numerical Hessian rank, for a larger class of models such as rectified and hyperbolic tangent networks.

no code implementations • NeurIPS 2021 • Lorenzo Noci, Gregor Bachmann, Kevin Roth, Sebastian Nowozin, Thomas Hofmann

Recent works on Bayesian neural networks (BNNs) have highlighted the need to better understand the implications of using Gaussian priors in combination with the compositional structure of the network architecture.

no code implementations • NeurIPS 2021 • Lorenzo Noci, Kevin Roth, Gregor Bachmann, Sebastian Nowozin, Thomas Hofmann

The dataset curation hypothesis of Aitchison (2020): we show empirically that the CPE does not arise in a real curated data set but can be produced in a controlled experiment with varying curation strength.

no code implementations • 7 Jun 2021 • Antonio Orvieto, Jonas Kohler, Dario Pavllo, Thomas Hofmann, Aurelien Lucchi

This paper revisits the so-called vanishing gradient phenomenon, which commonly occurs in deep randomly initialized neural networks.

no code implementations • 7 May 2021 • Gregor Bachmann, Seyed-Mohsen Moosavi-Dezfooli, Thomas Hofmann

By considering a specific dataset, it was observed that a neural network completely misclassifies a projection of the training data (adversarial set), rendering any existing generalization bound based on uniform convergence vacuous.

1 code implementation • ICCV 2021 • Dario Pavllo, Jonas Kohler, Thomas Hofmann, Aurelien Lucchi

Recent advances in differentiable rendering have sparked an interest in learning generative models of textured 3D meshes from image collections.

no code implementations • 23 Mar 2021 • Paulina Grnarova, Yannic Kilcher, Kfir Y. Levy, Aurelien Lucchi, Thomas Hofmann

Among known problems experienced by practitioners is the lack of convergence guarantees or convergence to a non-optimum cycle.

no code implementations • 21 Mar 2021 • Pelin Dogan-Schönberger, Julian Mäder, Thomas Hofmann

Swiss German is a dialect continuum whose natively acquired dialects significantly differ from the formal variety of the language.

no code implementations • 23 Feb 2021 • Peiyuan Zhang, Antonio Orvieto, Hadi Daneshmand, Thomas Hofmann, Roy Smith

Viewing optimization methods as numerical integrators for ordinary differential equations (ODEs) provides a thought-provoking modern framework for studying accelerated first-order optimizers.

no code implementations • NeurIPS 2020 • Hadi Daneshmand, Jonas Kohler, Francis Bach, Thomas Hofmann, Aurelien Lucchi

Randomly initialized neural networks are known to become harder to train with increasing depth, unless architectural enhancements like residual connections and batch normalization are used.

1 code implementation • NeurIPS 2020 • Dario Pavllo, Graham Spinks, Thomas Hofmann, Marie-Francine Moens, Aurelien Lucchi

A key contribution of our work is the encoding of the mesh and texture as 2D representations, which are semantically aligned and can be easily modeled by a 2D convolutional GAN.

no code implementations • 5 Mar 2020 • Florian Schmidt, Thomas Hofmann

Measuring the quality of a generated sequence against a set of references is a central problem in many learning frameworks, be it to compute a score, to assign a reward, or to perform discrimination.

no code implementations • 3 Mar 2020 • Hadi Daneshmand, Jonas Kohler, Francis Bach, Thomas Hofmann, Aurelien Lucchi

Randomly initialized neural networks are known to become harder to train with increasing depth, unless architectural enhancements like residual connections and batch normalization are used.

1 code implementation • ECCV 2020 • Dario Pavllo, Aurelien Lucchi, Thomas Hofmann

We propose a weakly-supervised approach for conditional image generation of complex scenes where a user has fine control over objects appearing in the scene.

no code implementations • 31 Oct 2019 • Peiyuan Zhang, Hadi Daneshmand, Thomas Hofmann

We study the mixing properties for stochastic accelerated gradient descent (SAGD) on least-squares regression.

no code implementations • 25 Sep 2019 • Kevin Roth, Yannic Kilcher, Thomas Hofmann

We establish a theoretical link between adversarial training and operator norm regularization for deep neural networks.

no code implementations • 4 Sep 2019 • Leonard Adolphs, Thomas Hofmann

We, however, consider the task of designing an agent that not just succeeds in a single game, but performs well across a whole family of games, sharing the same theme.

1 code implementation • IJCNLP 2019 • Florian Schmidt, Stephan Mandt, Thomas Hofmann

Autoregressive state transitions, where predictions are conditioned on past predictions, are the predominant choice for both deterministic and stochastic sequential models.

1 code implementation • 15 Aug 2019 • Nathanaël Perraudin, Ankit Srivastava, Aurelien Lucchi, Tomasz Kacprzak, Thomas Hofmann, Alexandre Réfrégier

Our results show that the proposed model produces samples of high visual quality, although the statistical analysis reveals that capturing rare features in the data poses significant problems for the generative models.

no code implementations • 7 Jun 2019 • Janis Fluri, Tomasz Kacprzak, Aurelien Lucchi, Alexandre Refregier, Adam Amara, Thomas Hofmann, Aurel Schneider

We present the cosmological results with a CNN from the KiDS-450 tomographic weak lensing dataset, constraining the total matter density $\Omega_m$, the fluctuation amplitude $\sigma_8$, and the intrinsic alignment amplitude $A_{\rm{IA}}$.

Cosmology and Nongalactic Astrophysics

no code implementations • NeurIPS 2020 • Kevin Roth, Yannic Kilcher, Thomas Hofmann

We establish a theoretical link between adversarial training and operator norm regularization for deep neural networks.

no code implementations • ICLR 2019 • Yannic Kilcher, Gary Bécigneul, Thomas Hofmann

We develop our method for fully-connected as well as convolutional layers.

no code implementations • ICLR 2019 • Paulina Grnarova, Kfir. Y. Levy, Aurelien Lucchi, Nathanael Perraudin, Thomas Hofmann, Andreas Krause

Generative Adversarial Networks (GANs) have shown great results in accurately modeling complex distributions, but their training is known to be difficult due to instabilities caused by a challenging minimax optimization problem.

1 code implementation • 13 Feb 2019 • Kevin Roth, Yannic Kilcher, Thomas Hofmann

We investigate conditions under which test statistics exist that can reliably detect examples, which have been adversarially manipulated in a white-box attack.

1 code implementation • NeurIPS 2019 • Paulina Grnarova, Kfir. Y. Levy, Aurelien Lucchi, Nathanael Perraudin, Ian Goodfellow, Thomas Hofmann, Andreas Krause

Evaluations are essential for: (i) relative assessment of different models and (ii) monitoring the progress of a single model throughout training.

no code implementations • WS 2018 • Valentin Trifonov, Octavian-Eugen Ganea, Anna Potapenko, Thomas Hofmann

Previous research on word embeddings has shown that sparse representations, which can be either learned on top of existing dense embeddings or obtained through model constraints during training time, have the benefit of increased interpretability properties: to some degree, each dimension can be understood by a human and associated with a recognizable feature in the data.

1 code implementation • CONLL 2018 • Nikolaos Kolitsas, Octavian-Eugen Ganea, Thomas Hofmann

Entity Linking (EL) is an essential task for semantic text understanding and information extraction.

Ranked #1 on Entity Linking on OKE-2016

no code implementations • 23 Jul 2018 • Janis Fluri, Tomasz Kacprzak, Aurelien Lucchi, Alexandre Refregier, Adam Amara, Thomas Hofmann

We find that, for a shape noise level corresponding to 8. 53 galaxies/arcmin$^2$ and the smoothing scale of $\sigma_s = 2. 34$ arcmin, the network is able to generate 45% tighter constraints.

Cosmology and Nongalactic Astrophysics

no code implementations • ICML 2018 • Celestine Dünner, Aurelien Lucchi, Matilde Gargiani, An Bian, Thomas Hofmann, Martin Jaggi

Due to the rapid growth of data and computational resources, distributed optimization has become an active research area in recent years.

no code implementations • NeurIPS 2018 • Florian Schmidt, Thomas Hofmann

Autoregressive feedback is considered a necessity for successful unconditional text generation using stochastic sequence models.

no code implementations • 27 May 2018 • Jonas Kohler, Hadi Daneshmand, Aurelien Lucchi, Ming Zhou, Klaus Neymeyr, Thomas Hofmann

Normalization techniques such as Batch Normalization have been applied successfully for training deep neural networks.

1 code implementation • 25 May 2018 • Lierni Sestorain, Massimiliano Ciaramita, Christian Buck, Thomas Hofmann

Our method can obtain improvements also on the setting where a small amount of parallel data for the zero-shot language pair is available.

3 code implementations • NeurIPS 2018 • Octavian-Eugen Ganea, Gary Bécigneul, Thomas Hofmann

However, the representational power of hyperbolic geometry is not yet on par with Euclidean geometry, mostly because of the absence of corresponding hyperbolic neural network layers.

no code implementations • 22 May 2018 • Kevin Roth, Aurelien Lucchi, Sebastian Nowozin, Thomas Hofmann

We propose a novel data-dependent structured gradient regularizer to increase the robustness of neural networks vis-a-vis adversarial perturbations.

1 code implementation • 15 May 2018 • Leonard Adolphs, Hadi Daneshmand, Aurelien Lucchi, Thomas Hofmann

Gradient-based optimization methods are the most popular choice for finding local optima for classical minimization and saddle point problems.

2 code implementations • ICML 2018 • Octavian-Eugen Ganea, Gary Bécigneul, Thomas Hofmann

Learning graph representations via low-dimensional embeddings that preserve relevant network properties is an important class of problems in machine learning.

Ranked #1 on Link Prediction on WordNet

no code implementations • ICML 2018 • Hadi Daneshmand, Jonas Kohler, Aurelien Lucchi, Thomas Hofmann

We analyze the variance of stochastic gradients along negative curvature directions in certain non-convex machine learning models and show that stochastic gradients exhibit a strong component along these directions.

no code implementations • 27 Jan 2018 • Andres C. Rodriguez, Tomasz Kacprzak, Aurelien Lucchi, Adam Amara, Raphael Sgier, Janis Fluri, Thomas Hofmann, Alexandre Réfrégier

Computational models of the underlying physical processes, such as classical N-body simulations, are extremely resource intensive, as they track the action of gravity in an expanding universe using billions of particles as tracers of the cosmic matter distribution.

no code implementations • 15 Nov 2017 • Yannic Kilcher, Thomas Hofmann

Black-Box attacks on machine learning models occur when an attacker, despite having no access to the inner workings of a model, can successfully craft an attack by means of model theft.

no code implementations • ICLR 2018 • Yannic Kilcher, Aurelien Lucchi, Thomas Hofmann

In implicit models, one often interpolates between sampled points in latent space.

no code implementations • ICLR 2018 • Yannic Kilcher, Aurelien Lucchi, Thomas Hofmann

We consider the problem of training generative models with deep neural networks as generators, i. e. to map latent codes to data points.

no code implementations • ICLR 2018 • Yannic Kilcher, Gary Becigneul, Thomas Hofmann

It is commonly agreed that the use of relevant invariances as a good statistical bias is important in machine-learning.

no code implementations • 28 Jul 2017 • Yannic Kilcher, Aurélien Lucchi, Thomas Hofmann

We consider the problem of training generative models with deep neural networks as generators, i. e. to map latent codes to data points.

1 code implementation • 21 Jul 2017 • Pascal Kaiser, Jan Dirk Wegner, Aurelien Lucchi, Martin Jaggi, Thomas Hofmann, Konrad Schindler

We adapt a state-of-the-art CNN architecture for semantic segmentation of buildings and roads in aerial images, and compare its performance when using different training data sets, ranging from manually labeled, pixel-accurate ground truth of the same city to automatic training data derived from OpenStreetMap data from distant locations.

no code implementations • 17 Jul 2017 • Jorit Schmelzle, Aurelien Lucchi, Tomasz Kacprzak, Adam Amara, Raphael Sgier, Alexandre Réfrégier, Thomas Hofmann

We find that our implementation of DCNN outperforms the skewness and kurtosis statistics, especially for high noise levels.

no code implementations • 13 Jun 2017 • Hadi Daneshmand, Hamed Hassani, Thomas Hofmann

Gradient descent and coordinate descent are well understood in terms of their asymptotic behavior, but less so in a transient regime often used for approximations in machine learning.

no code implementations • ICLR 2018 • Paulina Grnarova, Kfir. Y. Levy, Aurelien Lucchi, Thomas Hofmann, Andreas Krause

We consider the problem of training generative models with a Generative Adversarial Network (GAN).

1 code implementation • NeurIPS 2017 • Kevin Roth, Aurelien Lucchi, Sebastian Nowozin, Thomas Hofmann

Deep generative models based on Generative Adversarial Networks (GANs) have demonstrated impressive sample quality but in order to work they require a careful choice of architecture, parameter initialization, and selection of hyper-parameters.

3 code implementations • EMNLP 2017 • Octavian-Eugen Ganea, Thomas Hofmann

We propose a novel deep learning model for joint document-level entity disambiguation, which leverages learned neural representations.

Ranked #2 on Entity Disambiguation on WNED-CWEB

1 code implementation • 7 Mar 2017 • Jan Deriu, Aurelien Lucchi, Valeria De Luca, Aliaksei Severyn, Simon Müller, Mark Cieliebak, Thomas Hofmann, Martin Jaggi

This paper presents a novel approach for multi-lingual sentiment classification in short texts.

1 code implementation • 16 Nov 2016 • Wenhu Chen, Aurelien Lucchi, Thomas Hofmann

We here propose a novel way of using such textual data by artificially generating missing visual information.

2 code implementations • TACL 2017 • Jason Lee, Kyunghyun Cho, Thomas Hofmann

We observe that on CS-EN, FI-EN and RU-EN, the quality of the multilingual character-level translation even surpasses the models specifically trained on that language pair alone, both in terms of BLEU score and human judgment.

no code implementations • 20 May 2016 • Hadi Daneshmand, Aurelien Lucchi, Thomas Hofmann

Solutions on this path are tracked such that the minimizer of the previous objective is guaranteed to be within the quadratic convergence region of the next objective to be optimized.

no code implementations • 9 Mar 2016 • Hadi Daneshmand, Aurelien Lucchi, Thomas Hofmann

For many machine learning problems, data is abundant and it may be prohibitive to make multiple passes through the full training set.

1 code implementation • 8 Sep 2015 • Octavian-Eugen Ganea, Marina Ganea, Aurelien Lucchi, Carsten Eickhoff, Thomas Hofmann

We demonstrate the accuracy of our approach on a wide range of benchmark datasets, showing that it matches, and in many cases outperforms, existing state-of-the-art methods.

no code implementations • NeurIPS 2015 • Thomas Hofmann, Aurelien Lucchi, Simon Lacoste-Julien, Brian McWilliams

As a side-product we provide a unified convergence analysis for a family of variance reduction algorithms, which we call memorization algorithms.

no code implementations • 28 Mar 2015 • Aurelien Lucchi, Brian McWilliams, Thomas Hofmann

Quasi-Newton methods are widely used in practise for convex loss minimization problems.

no code implementations • NeurIPS 2014 • Martin Jaggi, Virginia Smith, Martin Takáč, Jonathan Terhorst, Sanjay Krishnan, Thomas Hofmann, Michael. I. Jordan

Communication remains the most significant bottleneck in the performance of distributed optimization algorithms for large-scale machine learning.

3 code implementations • 23 Jan 2013 • Thomas Hofmann

Probabilistic Latent Semantic Analysis is a novel statistical technique for the analysis of two-mode and co-occurrence data, which has applications in information retrieval and filtering, natural language processing, machine learning from text, and in related areas.

Cannot find the paper you are looking for? You can
Submit a new open access paper.

Contact us on:
hello@paperswithcode.com
.
Papers With Code is a free resource with all data licensed under CC-BY-SA.