arXiv Machine Learning

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

arXiv:2609. 30212v1 Announce Type: cross Abstract: We study the deterministic oracle complexity of finding approximate solutions to composite monotone inclusion problems, formed by the sum of a smooth single-valued monotone operator and a maximally monotone set-valued operator, under the tangent-residual criterion.

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.

arXiv Machine Learning
Oct 3

Optimal Stochastic Bilevel Optimization with First-Order Oracles

The paper investigates nonconvex–strongly-convex bilevel optimization using a stochastic first-order oracle. It introduces MRT‑FD, a single-loop first‑order algorithm that tracks the upper-level variable, the lower-level solution, and an auxiliary response from implicit differentiation, updating all variables in each iteration and approximating second‑order derivative actions via order‑p finite differences. For any fixed finite smoothness order p ≥ 1, MRT‑FD achieves an ε‑stationary point with O(ε^{‑4‑2/p}) stochastic gradient queries, and the authors prove a matching Ω(ε^{‑4‑2/p}) lower bound, thereby closing the complexity gap in this setting.

By Linxuan Pan, Junchi Yang