paper-with-me

Papers

Sparse Stochastic Zeroth-Order Optimization with an Application to Bandit Structured Prediction

2018-06-12 · Artem Sokolov, Julian Hitschler, Mayumi Ohta, Stefan Riezler

Stochastic zeroth-order (SZO), or gradient-free, optimization allows to optimize arbitrary functions by relying only on function evaluations under parameter perturbations, however, the iteration complexity of SZO methods suffers a factor proportional to the dimensionality of the perturbed function. We show that in scenarios with natural sparsity patterns as in structured prediction applications, this factor can be reduced to the expected number of active features over input-output pairs. We give a general proof that applies sparse SZO optimization to Lipschitz-continuous, nonconvex, stochastic objectives, and present an experimental evaluation on linear bandit structured prediction tasks with sparse word-based feature representations that confirm our theoretical results.

📄 PDF Abstract BibTeX arXiv:1806.04458

Code (0)

등록된 구현이 없습니다.

Tasks

PredictionStructured Prediction

Similar Papers 제목 키워드 기반

An Enhanced Zeroth-Order Stochastic Frank-Wolfe Framework for Constrained Finite-Sum Optimization

2025-01-13 · Haishan Ye, Yinghui Huang, Hao Di, Xiangyu Chang

We propose an enhanced zeroth-order stochastic Frank-Wolfe framework to address constrained finite-sum optimization problems, a structure prevalent in large-scale machine-learning applications. Our method introduces a no…

Computational EfficiencyRobust classification

Zeroth-order Asynchronous Doubly Stochastic Algorithm with Variance Reduction

2016-12-05 · Bin Gu, Zhouyuan Huo, Heng Huang

Zeroth-order (derivative-free) optimization attracts a lot of attention in machine learning, because explicit gradient calculations may be computationally expensive or infeasible. To handle large scale problems both in v…

Sparse Perturbations for Improved Convergence in Stochastic Zeroth-Order Optimization

2020-06-02 · Mayumi Ohta, Nathaniel Berger, Artem Sokolov, Stefan Riezler

Interest in stochastic zeroth-order (SZO) methods has recently been revived in black-box optimization scenarios such as adversarial black-box attacks to deep neural networks. SZO methods only require the ability to evalu…

Zeroth-Order Methods for Stochastic Nonconvex Nonsmooth Composite Optimization

2025-10-06 · Ziyi Chen, Peiran Yu, Heng Huang arxiv

This work aims to solve a stochastic nonconvex nonsmooth composite optimization problem. Previous works on composite optimization problem requires the major part to satisfy Lipschitz smoothness or some relaxed smoothness…

Zeroth-order Nonconvex Stochastic Optimization: Handling Constraints, High-Dimensionality and Saddle-Points

2018-09-17 · NeurIPS 2018 · Krishnakumar Balasubramanian, Saeed Ghadimi

In this paper, we propose and analyze zeroth-order stochastic approximation algorithms for nonconvex and convex optimization, with a focus on addressing constrained optimization, high-dimensional setting and saddle-point…

Stochastic OptimizationVocal Bursts Intensity Prediction