Sylvain Gelly

Karol Kurach

Jürgen Schmidhuber

Neural Networks, 2020

A Sober Look at the Unsupervised Learning of Disentangled Representations and their Evaluation.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2020

What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study.

[BibT_eX]

[DOI]

CoRR, 2020

Predicting Neural Network Accuracy from Weights.

[BibT_eX]

[DOI]

CoRR, 2020

On Last-Layer Algorithms for Classification: Decoupling Representation from Uncertainty Estimation.

[BibT_eX]

[DOI]

CoRR, 2020

What Do Neural Networks Learn When Trained With Random Labels?

[BibT_eX]

[DOI]

Hartmut Maennel

Ibrahim M. Alabdulmohsin

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

On Mutual Information Maximization for Representation Learning.

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

Big Transfer (BiT): General Visual Representation Learning.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2020, 2020

Self-Supervised Learning of Video-Induced Visual Invariances.

[BibT_eX]

[DOI]

Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

Precision-Recall Curves Using Information Divergence Frontiers.

[BibT_eX]

[DOI]

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

A Commentary on the Unsupervised Learning of Disentangled Representations.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

Google Research Football: A Novel Reinforcement Learning Environment.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019

Large Scale Learning of General Visual Representations for Transfer.

[BibT_eX]

[DOI]

CoRR, 2019

Semantic Bottleneck Scene Generation.

[BibT_eX]

[DOI]

CoRR, 2019

The Visual Task Adaptation Benchmark.

[BibT_eX]

[DOI]

CoRR, 2019

MULEX: Disentangling Exploitation from Exploration in Deep RL.

[BibT_eX]

[DOI]

CoRR, 2019

Evaluating Generative Models Using Divergence Frontiers.

[BibT_eX]

[DOI]

CoRR, 2019

Adaptive Temporal-Difference Learning for Policy Evaluation with Per-State Uncertainty Estimates.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

High-Fidelity Image Generation With Fewer Labels.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

A Large-Scale Study on Regularization and Normalization in GANs.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

Parameter-Efficient Transfer Learning for NLP.

[BibT_eX]

[DOI]

Neil Houlsby

Andrei Giurgiu

Stanislaw Jastrzebski

Bruna Morrone

Quentin de Laroussilhe

Andrea Gesmundo

Mona Attariyan

Proceedings of the 36th International Conference on Machine Learning, 2019

Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

FVD: A new Metric for Video Generation.

[BibT_eX]

[DOI]

Thomas Unterthiner

Proceedings of the Deep Generative Models for Highly Structured Data, 2019

Episodic Curiosity through Reachability.

[BibT_eX]

[DOI]

Proceedings of the 7th International Conference on Learning Representations, 2019

On Self Modulation for Generative Adversarial Networks.

[BibT_eX]

[DOI]

Proceedings of the 7th International Conference on Learning Representations, 2019

When can unlabeled data improve the learning rate?

[BibT_eX]

[DOI]

Proceedings of the Conference on Learning Theory, 2019

2018

Towards Accurate Generative Models of Video: A New Metric & Challenges.

[BibT_eX]

[DOI]

Thomas Unterthiner

CoRR, 2018

Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations.

[BibT_eX]

[DOI]

CoRR, 2018

A Case for Object Compositionality in Deep Generative Models of Images.

[BibT_eX]

[DOI]

Karol Kurach

CoRR, 2018

The GAN Landscape: Losses, Architectures, Regularization, and Normalization.

[BibT_eX]

[DOI]

CoRR, 2018

Temporal Difference Learning with Neural Networks - Study of the Leakage Propagation Problem.

[BibT_eX]

[DOI]

CoRR, 2018

On Accurate Evaluation of GANs for Language Generation.

[BibT_eX]

[DOI]

Stanislau Semeniuta

Aliaksei Severyn

CoRR, 2018

MemGEN: Memory is All You Need.

[BibT_eX]

[DOI]

CoRR, 2018

Gradient Descent Quantizes ReLU Network Features.

[BibT_eX]

[DOI]

Hartmut Maennel

Olivier Bousquet

CoRR, 2018

Assessing Generative Models via Precision and Recall.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Are GANs Created Equal? A Large-Scale Study.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Wasserstein Auto-Encoders.

[BibT_eX]

[DOI]

Proceedings of the 6th International Conference on Learning Representations, 2018

Clustering Meets Implicit Generative Models.

[BibT_eX]

[DOI]

Proceedings of the 6th International Conference on Learning Representations, 2018

2017

Better Text Understanding Through Image-To-Text Transfer.

[BibT_eX]

[DOI]

CoRR, 2017

Critical Hyper-Parameters: No Random, No Cry.

[BibT_eX]

[DOI]

CoRR, 2017

Toward Optimal Run Racing: Application to Deep Learning Calibration.

[BibT_eX]

[DOI]

CoRR, 2017

AdaGAN: Boosting Generative Models.

[BibT_eX]

[DOI]

Ilya O. Tolstikhin

Carl-Johann Simon-Gabriel

Olivier Bousquet

Bernhard Schölkopf

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

2012

The grand challenge of computer Go: Monte Carlo tree search and extensions.

[BibT_eX]

[DOI]

Commun. ACM, 2012

2011

Monte-Carlo tree search and rapid action value estimation in computer Go.

[BibT_eX]

[DOI]

David Silver

Artif. Intell., 2011

2009

Combiner connaissances expertes, hors-ligne, transientes et en ligne pour l'exploration Monte-Carlo. Apprentissage et MC.

[BibT_eX]

[DOI]

Rev. d'Intelligence Artif., 2009

A Statistical Learning Perspective of Genetic Programming.

[BibT_eX]

[DOI]

Proceedings of the Genetic Programming, 12th European Conference, 2009

2008

The Parallelization of Monte-Carlo Planning - Parallelization of MC-Planning.

[BibT_eX]

Proceedings of the ICINCO 2008, 2008

Achieving Master Level Play in 9 x 9 Computer Go.

[BibT_eX]

[DOI]

David Silver

Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence, 2008

2007

Comparison-Based Algorithms Are Robust and Randomized Algorithms Are Anytime.

[BibT_eX]

[DOI]

Sylvie Ruette

Evol. Comput., 2007

Combining online and offline knowledge in UCT.

[BibT_eX]

[DOI]

David Silver

Proceedings of the Machine Learning, 2007

Active learning in regression, with application to stochastic dynamic programming.

[BibT_eX]

Proceedings of the ICINCO 2007, 2007

Nonlinear programming in approximate dynamic programming - bang-bang solutions, stock-management and unsmooth penalties.

[BibT_eX]

Proceedings of the ICINCO 2007, 2007

DCMA: yet another derandomization in covariance-matrix-adaptation.

[BibT_eX]

[DOI]

Proceedings of the Genetic and Evolutionary Computation Conference, 2007

Modifications of UCT and sequence-like simulations for Monte-Carlo Go.

[BibT_eX]

[DOI]

Yizao Wang

Proceedings of the 2007 IEEE Symposium on Computational Intelligence and Games, 2007

2006

Universal Consistency and Bloat in GP Some theoretical considerations about Genetic Programming from a Statistical Learning Theory viewpoint.

[BibT_eX]

[DOI]

Rev. d'Intelligence Artif., 2006

Bayesian Networks: a Non-Frequentist Approach for Parametrization, and a more Accurate Structural Complexity Measure Bayesian Networks Learning.

[BibT_eX]

[DOI]

Rev. d'Intelligence Artif., 2006

On the Ultimate Convergence Rates for Isotropic Algorithms and the Best Choices Among Various Forms of Isotropy.

[BibT_eX]

[DOI]

Proceedings of the Parallel Problem Solving from Nature, 2006

General Lower Bounds for Evolutionary Algorithms.

[BibT_eX]

[DOI]

Proceedings of the Parallel Problem Solving from Nature, 2006

Learning for stochastic dynamic programming.

[BibT_eX]

[DOI]

Proceedings of the 14th European Symposium on Artificial Neural Networks, 2006

Resource-Aware Parameterizations of EDA.

[BibT_eX]

[DOI]

Christian Gagné

Proceedings of the IEEE International Conference on Evolutionary Computation, 2006

2005

Artificial Agents and Speculative Bubbles

[BibT_eX]

[DOI]

CoRR, 2005

From Factorial and Hierarchical HMM to Bayesian Network: A Representation Change Algorithm.

[BibT_eX]

[DOI]

Nicolas Bredèche

Michèle Sebag

Proceedings of the Abstraction, 2005

A statistical learning theory approach of bloat.

[BibT_eX]

[DOI]

Proceedings of the Genetic and Evolutionary Computation Conference, 2005

Inférence dans les HMM hiérarchiques et factorisés : changement de représentation vers le formalisme des Réseaux Bayésiens.

[BibT_eX]

[DOI]

Michèle Sebag

Nicolas Bredèche

Proceedings of the Extraction des connaissances : Etat et perspectives (Ateliers de la conférence EGC'2005), 2005

Apprentissage statistique et programmation génétique: la croissance du code est-elle inévitable?

[BibT_eX]

Proceedings of the Actes de CAP 05, Conférence francophone sur l'apprentissage automatique, 2005

Statistical asymptotic and non-asymptotic consistency of bayesian networks: convergence to the right structure and consistent probability estimates.

[BibT_eX]

Proceedings of the Actes de CAP 05, Conférence francophone sur l'apprentissage automatique, 2005

Taylor-based pseudo-metrics for random process fitting in dynamic programming: expected loss minimization and risk management.

[BibT_eX]

Proceedings of the Actes de CAP 05, Conférence francophone sur l'apprentissage automatique, 2005

HMM hiérarchiques et factorisés: mécanisme d'inférence et apprentissage à partir de peu de données.

[BibT_eX]