The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics.

ICML is one of the fastest growing artificial intelligence conferences in the world. This year, ICML will host over 8,000 participants with a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.

Nine papers by the chair’s academic team have been accepted at this 2019 edition of ICML, by Stephan Clémençon, Olivier Fercoq, Robert M. Gower, Pierre Laforgue, Eugene Ndiaye, Gaël Richard et Umut Simsekli.

Almost surely constrained convex optimization
Olivier Fercoq (Télécom ParisTech) · Ahmet Alacaoglu (EPFL) · Ion Necoara (University Bucharest) · Volkan Cevher (EPFL)

A conditional gradient-based augmented Lagrangian framework
Alp Yurtsever (EPFL) · Olivier Fercoq (Télécom ParisTech) · Volkan Cevher (EPFL)

A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks
Umut Simsekli (Télécom ParisTech) · Levent Sagun (CEA) · Mert Gurbuzbalaban (Rutgers University)

Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex Optimization
Thanh Huy Nguyen (Télécom ParisTech) · Umut Simsekli (Télécom ParisTech) · Gaël Richard (Télécom ParisTech)

On Medians of (Randomized) Pairwise Means
Stephan Clémençon (Télécom ParisTech) · Pierre Laforgue (Télécom ParisTech) · Patrice Bertail (Université Paris Nanterre)

Optimal mini-batch size for stochastic variance reduced methods
Nidham Gazagnadou (Télécom ParisTech) · Robert Gower (Télécom ParisTech) · Joseph Salmon (Université de Montpellier)

Safe Grid Search with Optimal Complexity
Eugene Ndiaye (Télécom ParisTech) · Tam Le (RIKEN AIP) · Olivier Fercoq (Télécom ParisTech) · Joseph Salmon (Université de Montpellier) · Ichiro Takeuchi (Nagoya Institute of Technology / RIKEN)

Sliced-Wasserstein Flows: Nonparametric Generative Modeling via Optimal Transport and Diffusions
Antoine Liutkus (Inria) · Umut Simsekli (Télécom ParisTech) · Szymon Majewski (IMPAN) · Alain Durmus (ENS) · Fabian-Robert Stöter (Inria)

SGD with Arbitrary Sampling: General Analysis and Improved Rates
Xun Qian (KAUST) · Peter Richtarik (KAUST) · Robert M. Gower (Télécom ParisTech) · Alibek Sailanbayev (King Abdullah University of Science and Technology) · Nicolas Loizou (The University of Edinburgh) · Egor Shulgin (Moscow Institute of Physics and Technology)