Ilya O Tolstikhin — accepted AI-conference papers

2020

What Do Neural Networks Learn When Trained With Random Labels?

Hartmut Maennel, Ibrahim M Alabdulmohsin, Ilya O Tolstikhin, Robert Baldock, Olivier Bousquet, Sylvain Gelly +1

NeurIPS 2020spotlight

We study deep neural networks (DNNs) trained on natural image data with entirely random labels. Despite its popularity in the literature, where it is often used to study memorization, generalization, and other phenomena, little is known about what DNNs learn in this setting. In this paper, we show a…

Cited by 91 Source ↗PDF ↗Scholar ↗

2019

Practical and Consistent Estimation of f-Divergences

Paul Rubenstein, Olivier Bousquet, Josip Djolonga, Carlos Riquelme, Ilya O Tolstikhin

NeurIPS 2019poster

The estimation of an f-divergence between two probability distributions based on samples is a fundamental problem in statistics and machine learning. Most works study this problem under very weak assumptions, in which case it is provably hard. We consider the case of stronger structural assumptions…

Cited by 53 Source ↗PDF ↗code ↗Scholar ↗

2017

AdaGAN: Boosting Generative Models

Ilya O Tolstikhin, Sylvain Gelly, Olivier Bousquet, Carl-Johann SIMON-GABRIEL, Bernhard Schölkopf

NeurIPS 2017poster

Generative Adversarial Networks (GAN) are an effective method for training generative models of complex data such as natural images. However, they are notoriously hard to train and can suffer from the problem of missing modes where the model is not able to produce examples in certain regions of the…

Cited by 291 Source ↗PDF ↗code ↗Scholar ↗

2016

Consistent Kernel Mean Estimation for Functions of Random Variables

Carl-Johann Simon-Gabriel, Adam Scibior, Ilya O Tolstikhin, Bernhard Schölkopf

NeurIPS 2016poster

We provide a theoretical foundation for non-parametric estimation of functions of random variables using kernel mean embeddings. We show that for any continuous function f, consistent estimators of the mean embedding of a random variable X lead to consistent estimators of the mean embedding of f(X).…

Cited by 12 Source ↗PDF ↗Scholar ↗

2016

Minimax Estimation of Maximum Mean Discrepancy with Radial Kernels

Ilya O Tolstikhin, Bharath K. Sriperumbudur, Bernhard Schölkopf

NeurIPS 2016poster

Maximum Mean Discrepancy (MMD) is a distance on the space of probability measures which has found numerous applications in machine learning and nonparametric testing. This distance is based on the notion of embedding probabilities in a reproducing kernel Hilbert space. In this paper, we present the…

Cited by 166 Source ↗PDF ↗Scholar ↗