CIS – “Get to know your neighbors” Seminar Series
Insights on gradient-based algorithms in high-dimensional non-convex learning
Monday November 9, 2020 – 3:15 – 4:15pm (UTC+01:00)
Gradient descent algorithms and their noisy variants, such as the Langevin dynamics or multi-pass SGD, are the working horse of machine learning. Yet their behaviour and performance remain perplexing, in particular in the high-dimensional non-convex setting.
In this talk, I will highlight the importance of the associated theoretical questions. I will then present several high-dimensional and non-convex statistical learning problems in which the performance of gradient-based algorithms can be analysed down to a constant. The common point of these settings is that the data come from a probabilistic generative model leading to problems for which, in the high-dimensional limit, statistical physics provides exact closed solutions for the performance of the gradient-based algorithms. The covered settings include the spiked mixed matrix-tensor model and the phase retrieval.
Lenka Zdeborová is a Professor of Physics and of Computer Science in École Polytechnique Fédérale de Lausanne. She received a PhD in physics from University Paris-Sud and from Charles University in Prague in 2008. She spent two years in the Los Alamos National Laboratory as the Director’s Postdoctoral Fellow.
Between 2010 and 2020 she was a researcher at CNRS working in the Institute of Theoretical Physics in CEA Saclay, France. In 2014, she was awarded the CNRS bronze medal, in 2016 Philippe Meyer prize in theoretical physics and an ERC Starting Grant, in 2018 the Irène Joliot-Curie prize.
She is an editorial board member for Journal of Physics A, Physical Review E, Physical Review X, SIMODS, Machine Learning: Science and Technology, and Information and Inference. Lenka’s expertise is in applications of methods developed in statistical physics, such as advanced mean field methods, replica method and related message-passing algorithms, to problems in machine learning, signal processing, inference and optimization.