
Statistically NearOptimal Hypothesis Selection
Hypothesis Selection is a fundamental distribution learning problem wher...
read it

A Theory of Universal Learning
How quickly can a given class of concepts be learned from examples? It i...
read it

What Do Neural Networks Learn When Trained With Random Labels?
We study deep neural networks (DNNs) trained on natural image data with ...
read it

Proper Learning, Helly Number, and an Optimal SVM Bound
The classical PAC sample complexity bounds are stated for any Empirical ...
read it

Predicting Neural Network Accuracy from Weights
We study the prediction of the accuracy of a neural network given only i...
read it

Iterated Jackknives and TwoSided Variance Inequalities
We consider the variance of a function of n independent random variables...
read it

Measuring Compositional Generalization: A Comprehensive Method on Realistic Data
Stateoftheart machine learning methods exhibit limited compositional ...
read it

Fast classification rates without standard margin assumptions
We consider the classical problem of learning rates for classes with fin...
read it

Sharper bounds for uniformly stable algorithms
The generalization bounds for stable algorithms is a classical question ...
read it

Google Research Football: A Novel Reinforcement Learning Environment
Recent progress in the field of reinforcement learning has been accelera...
read it

When can unlabeled data improve the learning rate?
In semisupervised classification, one is given access both to labeled a...
read it

Practical and Consistent Estimation of fDivergences
The estimation of an fdivergence between two probability distributions ...
read it

Evaluating Generative Models Using Divergence Frontiers
Despite the tremendous progress in the estimation of generative models, ...
read it

The Optimal Approximation Factor in Density Estimation
Consider the following problem: given two arbitrary densities q_1,q_2 an...
read it

Passing Tests without Memorizing: Two Models for Fooling Discriminators
We introduce two mathematical frameworks for foolability in the context ...
read it

Assessing Generative Models via Precision and Recall
Recent advances in generative modeling have led to an increased interest...
read it

Gradient Descent Quantizes ReLU Network Features
Deep neural networks are often trained in the overparametrized regime (...
read it

Are GANs Created Equal? A LargeScale Study
Generative adversarial networks (GAN) are a powerful subclass of generat...
read it

Wasserstein AutoEncoders
We propose the Wasserstein AutoEncoder (WAE)a new algorithm for buil...
read it

Approximation and Convergence Properties of Generative Adversarial Learning
Generative adversarial networks (GAN) approximate a target data distribu...
read it

Better Text Understanding Through ImageToText Transfer
Generic text embeddings are successfully used in a variety of tasks. How...
read it

From optimal transport to generative modeling: the VEGAN cookbook
We study unsupervised generative modeling in terms of the optimal transp...
read it

AdaGAN: Boosting Generative Models
Generative Adversarial Networks (GAN) (Goodfellow et al., 2014) are an e...
read it
Olivier Bousquet
is this you? claim profile