Work

Near-Optimal Acceleration for Smooth $\ell_p$ / $\ell_q$ Nondual Convex First-Order Oracle Optimization

Year: 2026

Type: preprint

Abstract: We study the optimization of convex objectives with $(L,κ-1)$-Hölder-continuous gradients in $\ell_q$ over $R B_p^d$, $1<κ\le 2$. (MG26) provides selectors with a movement bound for the problem of chasing high-dimensional convex nested sets for every $p

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2609.21880

Authors: Martínez-Rubio, David, Bullins, Brian, Guzmán, Cristóbal, Molina, Mathieu

Institutions: IMDEA Software Institute, Tel Aviv University

Language: English

Topic: Stochastic Gradient Optimization Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: European Commission, Tel Aviv University, Agencia Nacional de Investigación y Desarrollo, HORIZON EUROPE Framework Programme

Awards: DIFFERENTIALLY PRIVATE NEURAL NETWORK LEARNING WITH PROVABLE GUARANTEES: A SPARSITY BASED APPROACH, NATIONAL CENTER FOR ARTIFICIAL INTELLIGENCE RESEARCH (NAIR)

OpenAlex ID: W7213865625

Cites: 1

Cited by: 1

Related to: 10