Alexandre Bouchard-Côté

Professor, University of British Columbia

Talk Title

Breaking the Communication Barrier

Abstract

The global communication barrier is a natural performance limit arising in several annealing methods. A natural question is: can this barrier be broken?

I will talk about several approaches to tackle this problem, including a perspective on variational inference based on (a weird kind of) statistical estimation instead of optimization. This perspective allows us to scale to large problems while avoiding the headaches of tuning stochastic optimization methods.

My group is working on making these advanced Monte Carlo methods easy to use: we have developed Blang, a Bayesian modelling language to perform inference over arbitrary data types using non-reversible, highly parallel algorithms, and Pigeons, a package allowing the user to leverage clusters of 1000s of nodes to speed-up difficult Monte Carlo problems without requiring knowledge of distributed algorithms.

References:

- Parallel Tempering With a Variational Reference. (2022)
    Nikola Surjanovic, Saifuddin Syed, Alexandre Bouchard-Côté, Trevor Campbell
    NeurIPS 2022
    https://arxiv.org/abs/2206.00080

- Non-Reversible Parallel Tempering: a Scalable Highly Parallel MCMC Scheme. (2021)
    Saifuddin Syed, Alexandre Bouchard-Côté, George Deligiannidis, Arnaud Doucet.
    Journal of Royal Statistical Society, Series B
    https://rss.onlinelibrary.wiley.com/doi/10.1111/rssb.12464


Software:

- Pigeons: Fast, Distributed Bayesian Inference for Everyone
    Miguel Biron-Lattes, Alexandre Bouchard-Côté, Trevor Campbell, Nikola Surjanovic, Saifuddin Syed, Paul Tiede
    JuliaCon 2023 (accepted)
    https://julia-tempering.github.io/Pigeons.jl/dev/

- Blang: Probabilitistic Programming for Combinatorial Spaces
    Alexandre Bouchard-Côté, Kevin Chern, Davor Cubranic, Sahand Hosseini,
    Justin Hume, Matteo Lepur, Zihui Ouyang, Giorgio Sgarbi
    Journal of Statistical Software (Accepted)
    https://arxiv.org/abs/1912.10396
    https://www.stat.ubc.ca/~bouchard/blang/

Bio

Alexandre Bouchard is a professor of statistics at the University of British Columbia. He received his PhD in computer science from the University of California, Berkeley. His research focuses on computational Bayesian methods and applications in cancer genomics and phylogenetics. https://www.stat.ubc.ca/~bouchard/index.html

Headshot of Alexandre Bouchard