Chair of Dynamics of Learning Algorithms

Laboratory

The Dynamics of Learning Algorithms (DOLA) Chair at EPFL focuses on understanding the mechanisms behind key algorithms in machine learning and signal processing. They investigate what algorithms learn, how they learn, when they succeed or fail, and how to enhance them. Research areas include optimization, statistical and functional approximation, with a current emphasis on gradient methods for neural networks, sparse deconvolution, and divergences between probability measures.

Chair of Dynamics of Learning Algorithms

Graph Chatbot

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Statistical Inference for Inverse Problems: From Sparsity-Based Methods to Neural Networks

Random matrix methods for high-dimensional machine learning models

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Statistical Inference for Inverse Problems: From Sparsity-Based Methods to Neural Networks

Random matrix methods for high-dimensional machine learning models