• Publications
  • Influence
Improved Training of Wasserstein GANs
TLDR
This work proposes an alternative to clipping weights: penalize the norm of gradient of the critic with respect to its input, which performs better than standard WGAN and enables stable training of a wide variety of GAN architectures with almost no hyperparameter tuning.
Wasserstein Generative Adversarial Networks
TLDR
This work introduces a new algorithm named WGAN, an alternative to traditional GAN training that can improve the stability of learning, get rid of problems like mode collapse, and provide meaningful learning curves useful for debugging and hyperparameter searches.
Adversarially Learned Inference
TLDR
The adversarially learned inference (ALI) model is introduced, which jointly learns a generation network and an inference network using an adversarial process and the usefulness of the learned representations is confirmed by obtaining a performance competitive with state-of-the-art on the semi-supervised SVHN and CIFAR10 tasks.
Towards Principled Methods for Training Generative Adversarial Networks
TLDR
The goal of this paper is to make theoretical steps towards fully understanding the training dynamics of generative adversarial networks, and performs targeted experiments to substantiate the theoretical analysis and verify assumptions, illustrate claims, and quantify the phenomena.
Invariant Risk Minimization
TLDR
This work introduces Invariant Risk Minimization, a learning paradigm to estimate invariant correlations across multiple training distributions and shows how the invariances learned by IRM relate to the causal structures governing the data and enable out-of-distribution generalization.
Unitary Evolution Recurrent Neural Networks
TLDR
This work constructs an expressive unitary weight matrix by composing several structured matrices that act as building blocks with parameters to be learned, and demonstrates the potential of this architecture by achieving state of the art results in several hard tasks involving very long-term dependencies.
Never Give Up: Learning Directed Exploration Strategies
TLDR
This work constructs an episodic memory-based intrinsic reward using k-nearest neighbors over the agent's recent experience to train the directed exploratory policies, thereby encouraging the agent to repeatedly revisit all states in its environment.
Symplectic Recurrent Neural Networks
TLDR
It is shown that SRNNs succeed reliably on complex and noisy Hamiltonian systems, and how to augment the SRNN integration scheme in order to handle stiff dynamical systems such as bouncing billiards.
Out of Distribution Generalization in Machine Learning
TLDR
A central topic in the thesis is the strong link between discovering the causal structure of the data, finding features that are reliable (when using them to predict) regardless of their context, and out of distribution generalization.
Geometrical Insights for Implicit Generative Modeling
TLDR
This work can establish surprising approximate global convergence guarantees for the $1$-Wasserstein distance, even when the parametric generator has a nonconvex parametrization.
...
1
2
...