Early next week we will have François Laviolette from Université Laval giving a talk on Monday March 26 at 3pm in room Claire-McNicoll (CM) Z240.

Want to meet with Prof. Lavoilette? Fill out this Doodle

Learn how to improve the lower bound on your knowledge!

Michael

TITLE PAC-Bayesian Analysis and Its Applications

KEYWORDS ML Theory, Statistics, DL Theoretic Bounds

ABSTRACT
PAC-Bayesian analysis is a basic and very general tool for
data-dependent analysis of the generalization performance of learning
algorithms. By now, it has been applied in diverse areas, such as
supervised learning, unsupervised learning, and reinforcement
learning, leading to state-of-the-art algorithms and generalization
bounds. PAC-Bayesian analysis, in a sense, takes the best out of
Bayesian methods and the more frequentist approach related to PAC
learning and puts it together: (1) it provides an easy way to exploit
prior knowledge (like Bayesian methods); (2) it provides strict and
explicit generalization guarantees (like VC theory); and (3) it is
data-dependent and provides an easy and strict way of exploiting
benign conditions (like Rademacher complexities). In addition,
PAC-Bayesian bounds directly lead to efficient learning algorithms.

We will start with a general introduction to PAC-Bayesian analysis,
which should be accessible to people with prior knowledge of machine
learning. Then, we will survey multiple forms of PAC-Bayesian bounds
and their numerous applications in different fields (including deep
learning). Some of these applications will be explained in more
details, while others will be surveyed at a high level.

BIO
Professor François Laviolette is the founding director of the Big Data
Research Centre (BDRC) of Université Laval, which regroups more than
47 researchers from five faculties working on different fundamental
and applied aspects of data science. He has been a full professor in
the Department of Computer Science and Software Engineering of
Université Laval since 2002. Prof. Laviolette's main research involves
Machine Learning and Big Data Analytics. He is a world-class leader in
PAC-Bayesian theory, a branch of learning theory that gives rise to a
better understanding of existing machine learning algorithms, and also
makes it possible to design new ones. Professor Laviolette has also
developed a strong expertise in bio-informatics. In that area, he
worked on interpretable machine learning algorithms that were able to
uncover valuable knowledge for new medical applications.
Professor Laviolette is the lead researcher of the GRAAL laboratory of
Laval University, whose mission is to conduct research on Machine
Learning fundamentals and to develop innovative artificial
intelligence applications. Over the past six years, Prof. Laviolette
has supervised and co-supervised more than 36 graduate students
members of the GRAAL.