Zoom:  https://oist.zoom.us/j/91565544179?pwd=khgQtrethEsl0YQoC3yI9sD8bdqbFd.1
ミーティング ID: 915 6554 4179
パスコード: 715110

Speaker: Dr. Lenka Zdeborová, Associate Professor,  EPFL (École Polytechnique Fédérale de Lausanne)

Title: Statistical Physics Perspective on Understanding Learning with Neural Networks

Abstract: For over four decades, statistical physics has studied exactly solvable models of artificial neural networks. In this talk, we will explore how such models offer insights into deep learning and large language models. Specifically, we will examine a research strategy that trades distributional assumptions about data for precise control over learning behavior in high-dimensional settings. We will discuss several types of phase transitions that emerge in this limit, particularly as a function of data quantity. In particular, we will highlight how discontinuous phase transitions are linked to algorithmic hardness, impacting the behavior of gradient-based learning algorithms. Finally, we will present recent progress in learning from sequences and advances in understanding generalization in modern architectures, including the role of dot-product attention layers in transformers.

Bio: Lenka Zdeborová is a Professor of Physics and Computer Science at École Polytechnique Fédérale de Lausanne, where she leads the Statistical Physics of Computation Laboratory. She received a PhD in physics from the University of Paris-Sud and 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, in 2021 the Gibbs lectureship of AMS and the Neuron Fund award, in 2025 she received an ERC Advanced Grant. Lenka's expertise is in the application of concepts from statistical physics, such as advanced mean field methods, the replica method, and related message-passing algorithms, to problems in machine learning, signal processing, inference, and optimization. She enjoys erasing the boundaries between theoretical physics, mathematics and computer science.