1.5k citations · 3.2k across the 15 of their papers we have counts for
16 papers
Discovery of Unstable Singularities
Yongji Wang, Mehdi Bennani, James Martens +19
Whether singularities can form in fluids remains a foundational unanswered question in mathematics. This phenomenon occurs when solutions to governing equations, such as the 3D Eul…
Out of the Ordinary: Spectrally Adapting Regression for Covariate Shift
Benjamin Eyre, Elliot Creager, David Madras +2
Designing deep neural network classifiers that perform robustly on distributions differing from the available training data is an active area of machine learning research. However,…
Why does Throwing Away Data Improve Worst-Group Error?
Kamalika Chaudhuri, Kartik Ahuja, Martin Arjovsky +1
When facing data with imbalanced classes or groups, practitioners follow an intriguing strategy to achieve best results. They throw away examples until the classes or groups are ba…
Simple data balancing achieves competitive worst-group-accuracy
Badr Youbi Idrissi, Martin Arjovsky, Mohammad Pezeshki +1
We study the problem of learning classifiers that perform well across (known or unknown) groups of data. After observing that common worst-group-accuracy datasets suffer from subst…
Out of Distribution Generalization in Machine Learning
Martin Arjovsky
Machine learning has achieved tremendous success in a variety of domains in recent years. However, a lot of these success stories have been in places where the training and the tes…
Linear unit-tests for invariance discovery
Benjamin Aubin, Agnieszka Słowik, Martin Arjovsky +2
There is an increasing interest in algorithms to learn invariant correlations across training environments. A big share of the current proposals find theoretical support in the cau…
Low Distortion Block-Resampling with Spatially Stochastic Networks
Sarah Jane Hong, Martin Arjovsky, Darryl Barnhart +1
We formalize and attack the problem of generating new images from old ones that are as diverse as possible, only allowing them to change without restrictions in certain parts of th…
Never Give Up: Learning Directed Exploration Strategies
Adrià Puigdomènech Badia, Pablo Sprechmann, Alex Vitvitskyi +8
We propose a reinforcement learning agent to solve hard exploration games by learning a range of directed exploratory policies. We construct an episodic memory-based intrinsic rewa…
Symplectic Recurrent Neural Networks
Zhengdao Chen, Jianyu Zhang, Martin Arjovsky +1
We propose Symplectic Recurrent Neural Networks (SRNNs) as learning algorithms that capture the dynamics of physical systems from observed trajectories. An SRNN models the Hamilton…
Invariant Risk Minimization
Martin Arjovsky, Léon Bottou, Ishaan Gulrajani +1
We introduce Invariant Risk Minimization (IRM), a learning paradigm to estimate invariant correlations across multiple training distributions. To achieve this goal, IRM learns a da…
Geometrical Insights for Implicit Generative Modeling
Leon Bottou, Martin Arjovsky, David Lopez-Paz +1
Learning algorithms for implicit generative models can optimize a variety of criteria that measure how the data distribution differs from the implicit model distribution, including…
Improved Training of Wasserstein GANs
Ishaan Gulrajani, Faruk Ahmed, Martin Arjovsky +2
Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stab…
Towards Principled Methods for Training Generative Adversarial Networks
Martin Arjovsky, Léon Bottou
The goal of this paper is not to introduce a single algorithm or method, but to make theoretical steps towards fully understanding the training dynamics of generative adversarial n…
Adversarially Learned Inference
Vincent Dumoulin, Ishmael Belghazi, Ben Poole +4
We introduce the adversarially learned inference (ALI) model, which jointly learns a generation network and an inference network using an adversarial process. The generation networ…
Unitary Evolution Recurrent Neural Networks
Martin Arjovsky, Amar Shah, Yoshua Bengio
Recurrent neural networks (RNNs) are notoriously difficult to train. When the eigenvalues of the hidden to hidden weight matrix deviate from absolute value 1, optimization becomes…
Saddle-free Hessian-free Optimization
Martin Arjovsky
Nonconvex optimization problems such as the ones in training deep neural networks suffer from a phenomenon called saddle point proliferation. This means that there are a vast numbe…