no code implementations • 12 Mar 2024 • Romain Cosson
We show that a simple variant of depth-first search achieves collective exploration in $m$ synchronous time-steps, where $m$ is the number of edges of the graph.
no code implementations • 16 Jun 2022 • Romain Cosson, Ali Jadbabaie, Anuran Makur, Amirhossein Reisizadeh, Devavrat Shah
When $r \ll p$, these complexities are smaller than the known complexities of $\mathcal{O}(p \log(1/\epsilon))$ and $\mathcal{O}(p/\epsilon^2)$ of {\gd} in the strongly convex and non-convex settings, respectively.
no code implementations • 21 Jan 2022 • Moise Blanchard, Romain Cosson, Steve Hanneke
We resolve an open problem of Hanneke on the subject of universally consistent online learning with non-i. i. d.
no code implementations • 29 Dec 2021 • Moïse Blanchard, Romain Cosson
However, when the loss function is bounded, the class of processes admitting strong universal consistency is much richer and its characterization could be dependent on the response setting (Hanneke).
no code implementations • 19 Feb 2021 • Romain Cosson, Devavrat Shah
Specifically, we argue that (a variant of) TRW produces an estimate that is within factor $\frac{1}{\sqrt{\kappa(G)}}$ of the true log-partition function for any discrete pairwise graphical model over graph $G$, where $\kappa(G) \in (0, 1]$ captures how far $G$ is from tree structure with $\kappa(G) = 1$ for trees and $2/N$ for the complete graph over $N$ vertices.