Timezone: »

A Primer on PAC-Bayesian Learning
Benjamin Guedj · John Shawe-Taylor

Mon Jun 10 09:15 AM -- 11:30 AM (PDT) @ Grand Ballroom
Event URL: https://bguedj.github.io/icml2019/index.html »

Over the past few years, the PAC-Bayesian approach has been applied to numerous settings, including classification, high-dimensional sparse regression, image denoising and reconstruction of large random matrices, recommendation systems and collaborative filtering, binary ranking, online ranking, transfer learning, multiview learning, signal processing, to name but a few. The "PAC-Bayes" query on arXiv illustrates how PAC-Bayes is quickly re-emerging as a principled theory to efficiently address modern machine learning topics, such as leaning with heavy-tailed and dependent data, or deep neural networks generalisation abilities. This tutorial aims at providing the ICML audience with a comprehensive overview of PAC-Bayes, starting from statistical learning theory (complexity terms analysis, generalisation and oracle bounds) and covering algorithmic (actual implementation of PAC-Bayesian algorithms) developments, up to the most recent PAC-Bayesian analyses of deep neural networks generalisation abilities. We intend to address the largest audience, with an elementary background in probability theory and statistical learning, although all key concepts will be covered from scratch.

Author Information

Benjamin Guedj (Inria and University College London)
Benjamin Guedj

Benjamin Guedj is a tenured research scientist at Inria (France) and a senior research scientist at University College London (UK). His main research areas are statistical learning theory, PAC-Bayes, machine learning and computational statistics. He obtained a PhD in mathematics from Sorbonne Université (formerly Université Pierre et Marie Curie, France) in 2013.

John Shawe-Taylor (University College London)
John Shawe-Taylor

John Shawe-Taylor has contributed to a number of fields ranging from graph theory through cryptography to statistical learning theory and its applications. However, his main contributions have been in the development of the analysis and subsequent algorithmic definition of principled machine learning algorithms founded in statistical learning theory. This work has helped to drive a fundamental rebirth in the field of machine learning with the introduction of kernel methods and support vector machines, driving the mapping of these approaches onto novel domains including work in computer vision, document classification, and applications in biology and medicine focused on brain scan, immunity and proteome analysis. He has published over 300 papers and two books that have attracted over 62000 citations.