Georgia Institute of Technology College of Sciences

In these lectures we discuss some statistical problems with an interesting combinatorial structure behind. We start by reviewing the "hidden clique" problem, a simple prototypical example with a surprisingly rich structure. We also discuss various "combinatorial" testing problems and their connections to high-dimensional random geometric graphs. Time permitting, we study the problem of estimating the mean of a random variable.

Spectral algorithms, such as principal component analysis and spectral clustering, typically require careful data transformations to be effective: upon observing a matrix A, one may look at the spectrum of ψ(A) for a properly chosen ψ. We propose a simple and generic construction for sparse graphs based on graph powering. It is shown that graph powering regularizes the graph and decontaminates its spectrum in the following sense: (i) If the graph is drawn from the sparse Erd˝os-R´enyi ensemble, which has no spectral gap, it is shown that graph powering produces a “maximal” spectral gap, with the latter justified by establishing an Alon-Boppana result for powered graphs; (ii) If the graph is drawn from the sparse SBM, graph powering is shown to achieve the fundamental limit for weak recovery. (Joint work with E. Abbe, E. Boix, C. Sandon.)

At the heart of most algorithms today there is an optimization engine trying to learn online and provide the best decision, for e.g. rankings of objects, at any time with the partial information observed thus far in time. Often it becomes difficult to find near optimal solutions to many problems due to their inherent combinatorial structure that leads to certain computational bottlenecks. Submodularity is a discrete analogue of convexity and is a key property often exploited in tackling combinatorial optimization problems. In the first part of the talk, we will focus on computational bottlenecks that involve submodular functions: (a) convex function minimization over submodular base polytopes (for e.g. permutahedron) and (b) movement along a line inside submodular base polytopes. We give a conceptually simple and strongly polynomial algorithm Inc-Fix for the former, which is useful in computing Bregman projections in first-order projection-based methods like online mirror descent. For the latter, we will bound the iterations of the discrete Newton method which gives a running time improvement of at least n^6 over the state of the art. This is joint work with Michel Goemans and Patrick Jaillet. In the second part of the talk, we will consider the dual problem of (a), i.e. minimization of composite convex and submodular objectives. We will resolve Bach's conjecture from 2015 about the running time of a popular Kelley's cutting plane variant to minimize these composite objectives. This is joint work with Madeleine Udell and Song Zhou.

In this talk, we introduce several models of the so-called forward-forward Mean-Field Games (MFGs). The forward-forward models arise in the study of numerical schemes to approximate stationary MFGs. We establish a link between these models and a class of hyperbolic conservation laws. Furthermore, we investigate the existence of solutions and examine long-time limit properties. Joint work with Diogo Gomes and Levon Nurbekyan.