The Statistical Learning Theory working group will meet on Wednesdays. We will have readings, presentations and discussions on topics including (but, not limited to) statistical learning theory, nonparametric estimation and inference, deep learning, functional data analysis, topological data analysis and algebraic statistics. The focus of the group is to read and discuss important papers in one particular topic of interest for a semester or two.
Time  Wednesday 2:15  3:45 PM 

Location  Zoom 
Topics
This semester we will focus on stochastic optimization. The papers we will focus on are categorized below.

Sampling and Gradient Flow:
 Francis Bach’s tutorial on gradient flows
 The Variational Formulation of the FokkerPlanck Equation
 Convergence of Langevin MCMC in KLdivergence
 Sampling as optimization in the space of measures: The Langevin dynamics as a composite optimization problem
 Sampling Can Be Faster Than Optimization
 Stein Variational Gradient Descent as Gradient Flow
 SVGD as a kernelized Wasserstein gradient flow of the chisquared divergence
 Maximum Mean Discrepancy Gradient Flow
 A NonAsymptotic Analysis for Stein Variational Gradient Descent
 Stochastic ParticleOptimization Sampling and the NonAsymptotic Convergence Theory

Langevin Monte Carlo:
 Theoretical guarantees for approximate sampling from smooth and logconcave densities
 Nonasymptotic convergence analysis for the Unadjusted Langevin Algorithm
 Highdimensional Bayesian inference via the Unadjusted Langevin Algorithm
 Analysis of Langevin Monte Carlo via convex optimization
 Userfriendly guarantees for the Langevin Monte Carlo with inaccurate gradient

Optimization:
Here is an overview of gradient flows by Filippo Santambrogio, introductory lectures on convex optimization by Yurii Nesterov and the more exhaustive lectures on convex optimization by Yurii Nesterov.
The webpage and resources for Fall 2019 can be found here.
Schedule
The schedule is available on the STAG Google Calendar
If you’re interested in attending the meetings, please signup here, and send an email to the LSTATSTAG with the subject “Add Me” and include your name and department in the body.