arXiv Machine Learning

Nonmaximal sums of maximally monotone operators under Rockafellar's constraint qualification

arXiv Machine Learning
Sep 18

The First-Order Oracle Complexity of Lipschitz Convex Optimization in Nondual Settings

arXiv:2609. 20687v1 Announce Type: cross Abstract: We study first-order black-box convex optimization over an $\ell_p$-ball for objectives Lipschitz in the $\ell_q$-norm, solving in the affirmative the nonsmooth version of the COLT open question (Guz15b) on whether the geometry of a smaller feasible set ($p < q$) can improve convergence rates in convex optimization, and matching prior lower bounds up to logarithmic factors.

By David Mart\'inez-Rubio, Brian Bullins, Crist\'obal Guzm\'an, Mathieu Molina
arXiv AI
Jul 28

Formalizing Flag Algebras in Lean

arXiv:2607. 23500v1 Announce Type: cross Abstract: Razborov's flag algebra method is a powerful tool for proving asymptotic inequalities in extremal graph theory, often reducing the task to finding a finite certificate by semidefinite programming.

By Gyeongwon Jeong, Seonghun Park, Jihoon Hyun, Sang-il Oum, Hongseok Yang
arXiv Machine Learning
Sep 11

Thompson Sampling for Non-Monotone Convex Ridge Bandits: Monotonicity Is Not Needed for Polynomial Regret

arXiv:2609. 10981v1 Announce Type: new Abstract: Bakhtiari, Lattimore and Szepesv\'ari (COLT 2025) proved that Thompson sampling (TS) has Bayesian regret $\tilde O(d^{5/2}\sqrt n)$ for bandit convex optimisation with convex \emph{monotone} ridge losses $f(x)=\ell(\ip{x}{\theta})$, and asked whether monotonicity of the link is necessary.

By Xuan Li
arXiv Machine Learning
Sep 10

Expressivity of Contradiction Graphs

arXiv:2605.20434v2 Announce Type: replace-cross Abstract: We study the contradiction graphs associated with a binary concept class. For a class $H\subseteq\{0,1\}^X$, the order-$m$ contradiction grap...

By Jesse Campbell, Daniel Ibaibarriaga, Lev Reyzin
Hugging Face Trending Papers
Sep 24

Anchored Extra-Proximal Methods: Optimal Higher-Order Methods for Monotone Inclusion Problems

The paper introduces the Anchored Extra-Proximal (AEP) framework for solving composite monotone inclusion problems, combining anchored extrapolation with an inexact anchored proximal update. By replacing the operator in the implicit update with its Taylor approximation and using a bisection line search, the authors derive a pth-order method that achieves a tangent-residual error ε in “~O(ε^{-2/(3p-1)})” oracle calls for every p ≥ 2. This complexity matches a proven lower bound, establishing the method as optimally efficient for deterministic algorithms in the pth-order oracle model.