Signals 4 · free daily AI digest

Learned Preconditioning for a Primal-Dual Interior-Point Method

Paper recorded by Signals 4 on 2026-09-28 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-28 on arXiv · recorded by Signals 4 on 2026-09-29

Category: cs.LG · 机器学习 · first seen 2026-09-29

Abstract

Interior-point methods (IPMs) are among the most widely used algorithms for constrained optimization, yet their Newton-based search directions require costly second-order information and large linear-system solves. Learning to optimize offers cheaper updates learned from data, but the singular behavior of logarithmic barriers near constraint boundaries makes IPMs highly sensitive to perturbations,

Read on arXiv →

#12 most recent of 322 cs.LG papers we have recorded · ↑ newer: The Hidden Perception Constraint in Task-Aware Compression · ↓ older: Gap-free Differentially Private PCA for Gaussian Data
Cite this page: Learned Preconditioning for a Primal-Dual Interior-Point Method: the #12 most recent of 322 cs.LG papers we have recorded (as of 2026-09-28). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/learned-preconditioning-for-a-primal-dual-interior-point-method.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.LG papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions