Search Results for author:
Found 5 papers, 0 papers with code
Ariadne and Theseus: Exploration and Rendezvous with Two Mobile Agents in an Unknown Graph
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.
Gradient Descent for Low-Rank Functions
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.
Universal Online Learning with Unbounded Losses: Memory Is All You Need
We resolve an open problem of Hanneke on the subject of universally consistent online learning with non-i. i. d.
Universal Online Learning with Bounded Loss: Reduction to Binary Classification
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).
Quantifying Variational Approximation for the Log-Partition Function
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.
