math.OC · 2026-10-20 · No. 149
Optimization and Control, 2026-10-20.
2 new papers in math.OC. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
2 entries-
01
Newton-Based Methods for Bilevel Optimization Beyond Lower-Level Strong Convexity
Youran Dong, Junfeng Yang, Wei Yao, Jin Zhang
math.OC · cs.LG
Bilevel optimization provides a framework for machine learning tasks such as hyperparameter optimization, data reweighting, and meta-learning. Existing Newton-based bilevel methods typically rely on the classical hypergradient formula, which is generally unavailable when lower-level solutions are nonunique and the lower-level Hessian is singular. We develop two Newton-based methods beyond lower-level strong convexity by exploiting curvature...
-
02
Gradient descent reaches arbitrary accuracy in a fixed number of large steps on multiclass logistic regression
Andreea-Alexandra Musat, Nicolas Boumal
math.OC · cs.LG
We show that gradient descent (GD) with step size $η$ can achieve $\varepsilon$ optimality gap on the multiclass logistic regression loss in a number of iterations $T$ that is independent of $\varepsilon$. To do so, the step size $η$ must be chosen large enough as a function of $\varepsilon$ (and properties of the linearly separable dataset), while $T$ is a constant that only depends on the data. The relevant properties of the data include...
This edition is part of The Daily Abstract — math.OC archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.