arXiv Machine Learning July 16, 2026 By Chen Xu

Power Homotopy for Zeroth-Order Non-Convex Optimizations

Read the original on arXiv Machine Learning →

arXiv:2511. 13592v2 Announce Type: replace-cross Abstract: The existing method of GS-PowerOpt solves the non-convex optimization problem of the form $\max_{\boldsymbol{x} \in \mathbb{R}^d} f(\boldsymbol{x})$ through maximizing a Gaussian-smoothed surrogate $F_{N,\sigma}(\boldsymbol{\mu}) = \mathbb{E}_{\boldsymbol{x}\sim\mathcal{N}(\boldsymbol{\mu},\sigma^2 I_d)}[e^{N f(\boldsymbol{x})}]$.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

safety

arXiv Machine Learning

Jun 2

Accelerating Min-Max Optimization via Power-Law Stepsizes

arXiv:2606. 01764v1 Announce Type: cross Abstract: We revisit the convergence guarantees of the Extragradient (EG) method for unconstrained biaffine min-max optimization.

By Yue Wu, Weiqiang Zheng, Yang Cai, Haipeng Luo

arXiv Machine Learning

Jul 13

Accelerated Fully First-Order Methods for Bilevel and Minimax Optimization

arXiv:2405. 00914v4 Announce Type: replace-cross Abstract: We present in this paper novel accelerated fully first-order methods in \emph{Bilevel Optimization} (BLO).

By Chris Junchi Li

benchmarks

arXiv AI

Aug 10

Fast LapSum: Exact Differentiable Top-k at Million Scale

arXiv:2608. 06912v1 Announce Type: new Abstract: The top-$k$ operation is a fundamental building block of modern sparse computation, enabling token routing, expert activation, memory selection, and attention pruning.

By {\L}ukasz Struski, Joanna Wojciechowicz, Jakub Antczak, Marcin Mazur, Kamil Ksi\k{a}\.zek, Jacek Tabor

efficiency benchmarks safety

arXiv Machine Learning

Jul 15

Gradient-Free Topology Adaptation for Power Flow Surrogates via In-Context Whitening

arXiv:2607. 12241v1 Announce Type: cross Abstract: Machine-learned surrogates for the AC power flow (ACPF) problem amortize the cost of repeated solves on a fixed network, but lose one to two orders of magnitude of accuracy when a line outage changes the topology.

By Ayushi Jolotia, Parikshit Pareek

arXiv Machine Learning

Jul 15

Same Loss, Same Noise, Opposite Schedules: Noise Structure and Optimizer Normalization Jointly Determine Whether Learning-Rate Cooldown Helps

arXiv:2607. 12360v1 Announce Type: new Abstract: The cooldown phase of a warmup-stable-decay (WSD) learning-rate schedule, now a default in large-model pretraining, lowers the final training loss in some settings and does nothing in others.

By Subham Singh, Ashutosh Mishra, Subha Raut

arXiv Machine Learning

Jun 16

OptEMA: Adaptive Exponential Moving Average for Stochastic Optimization with Zero-Noise Optimality

arXiv:2603. 09923v4 Announce Type: replace Abstract: Exponential moving averages (EMAs) are a central component of widely used adaptive optimizers such as Adam.

By Ganzhao Yuan

Related stories

Accelerating Min-Max Optimization via Power-Law Stepsizes

Accelerated Fully First-Order Methods for Bilevel and Minimax Optimization

Fast LapSum: Exact Differentiable Top-k at Million Scale

Gradient-Free Topology Adaptation for Power Flow Surrogates via In-Context Whitening

Same Loss, Same Noise, Opposite Schedules: Noise Structure and Optimizer Normalization Jointly Determine Whether Learning-Rate Cooldown Helps

OptEMA: Adaptive Exponential Moving Average for Stochastic Optimization with Zero-Noise Optimality