paper-with-me

Papers

Zeroth-Order Hard-Thresholding: Gradient Error vs. Expansivity

2022-10-11 · William de Vazelhes, Hualin Zhang, Huimin Wu, Xiao-Tong Yuan, Bin Gu

$\ell_0$ constrained optimization is prevalent in machine learning, particularly for high-dimensional problems, because it is a fundamental approach to achieve sparse learning. Hard-thresholding gradient descent is a dominant technique to solve this problem. However, first-order gradients of the objective function may be either unavailable or expensive to calculate in a lot of real-world problems, where zeroth-order (ZO) gradients could be a good surrogate. Unfortunately, whether ZO gradients can work with the hard-thresholding operator is still an unsolved problem. To solve this puzzle, in this paper, we focus on the $\ell_0$ constrained black-box stochastic optimization problems, and propose a new stochastic zeroth-order gradient hard-thresholding (SZOHT) algorithm with a general ZO gradient estimator powered by a novel random support sampling. We provide the convergence analysis of SZOHT under standard assumptions. Importantly, we reveal a conflict between the deviation of ZO estimators and the expansivity of the hard-thresholding operator, and provide a theoretical minimal value of the number of random directions in ZO gradients. In addition, we find that the query complexity of SZOHT is independent or weakly dependent on the dimensionality under different settings. Finally, we illustrate the utility of our method on a portfolio optimization problem as well as black-box adversarial attacks.

📄 PDF Abstract BibTeX arXiv:2210.05279

Code (0)

등록된 구현이 없습니다.

Tasks

Portfolio OptimizationSparse LearningStochastic Optimization

Similar Papers 제목 키워드 기반

New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions

2026-05-18 · Xinzhe Yuan, William de Vazelhes, Bin Gu, Huan Xiong arxiv

Hard-thresholding is an important type of algorithm in machine learning that is used to solve $\ell_0$ constrained optimization problems. However, the true gradient of the objective function can be difficult to access in…

Less is More: Dimension Reduction Finds On-Manifold Adversarial Examples in Hard-Label Attacks

2021-09-29 · Washington Garcia, Pin-Yu Chen, Somesh Jha, Hamilton Scott Clouse 외

Designing deep networks robust to adversarial examples remains an open problem. Likewise, recent zeroth-order hard-label attacks on image classification models have shown comparable performance to their first-order, grad…

Dimensionality Reductionimage-classificationImage Classification

Hard-label Manifolds: Unexpected Advantages of Query Efficiency for Finding On-manifold Adversarial Examples

2021-03-04 · Washington Garcia, Pin-Yu Chen, Somesh Jha, Scott Clouse 외

Designing deep networks robust to adversarial examples remains an open problem. Likewise, recent zeroth order hard-label attacks on image classification models have shown comparable performance to their first-order, grad…

Dimensionality Reductionimage-classificationImage Classification

Poor Man's Training on MCUs: A Memory-Efficient Quantized Back-Propagation-Free Approach

2024-11-07 · Yequan Zhao, Hai Li, Ian Young, Zheng Zhang

Back propagation (BP) is the default solution for gradient computation in neural network training. However, implementing BP-based training on various edge devices such as FPGA, microcontrollers (MCUs), and analog computi…

Dimensionality Reduction

Fine-Grained Theoretical Analysis of Federated Zeroth-Order Optimization

2023-09-21 · NeurIPS 2023 11

Federated zeroth-order optimization (FedZO) algorithm enjoys the advantages of both zeroth-order optimization and federated learning, and has shown exceptional performance on black-box attack and softmax regression tasks…