paper-with-me

홈 › Papers

Hierarchical Zero-Order Optimization for Deep Neural Networks

2026-02-11 · Sansheng Cao, Zhengyu Ma, Yonghong Tian arxiv

Zeroth-order (ZO) optimization has long been favored for its biological plausibility and its capacity to handle non-differentiable objectives, yet its computational complexity has historically limited its application in deep neural networks. Challenging the conventional paradigm that gradients propagate layer-by-layer, we propose Hierarchical Zeroth-Order (HZO) optimization, a novel divide-and-conquer strategy that decomposes the depth dimension of the network. We prove that HZO reduces the query complexity from $O(ML^2)$ to $O(ML \log L)$ for a network of width $M$ and depth $L$, representing a significant leap over existing ZO methodologies. Furthermore, we provide a detailed error analysis showing that HZO maintains numerical stability by operating near the unitary limit ($L_{lip} \approx 1$). Extensive evaluations on CIFAR-10 and ImageNet demonstrate that HZO achieves competitive accuracy compared to backpropagation.

📄 PDF Abstract BibTeX arXiv:2602.10607

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Zeroth-order non-convex learning via hierarchical dual averaging

2021-09-13 · Amélie Héliou, Matthieu Martin, Panayotis Mertikopoulos, Thibaud Rahier

We propose a hierarchical version of dual averaging for zeroth-order online non-convex optimization - i.e., learning processes where, at each stage, the optimizer is facing an unknown non-convex loss function and only re…

Hi-ZFO: Hierarchical Zeroth- and First-Order LLM Fine-Tuning via Importance-Guided Tensor Selection

2026-01-09 · Feihu Jin, Ying Tan arxiv

Fine-tuning large language models (LLMs) using standard first-order (FO) optimization often drives training toward sharp, poorly generalizing minima. Conversely, zeroth-order (ZO) methods offer stronger exploratory behav…

A Randomized Zeroth-Order Hierarchical Framework for Heterogeneous Federated Learning

2025-04-02 · Yuyang Qiu, Kibaek Kim, Farzad Yousefian

Heterogeneity in federated learning (FL) is a critical and challenging aspect that significantly impacts model performance and convergence. In this paper, we propose a novel framework by formulating heterogeneous FL as a…

Federated Learningimage-classificationImage Classification

Distributed Zeroth-Order Optimization: Convergence Rates That Match Centralized Counterpart

2021-09-29 · Deming Yuan, Lei Wang, Alexandre Proutiere, Guodong Shi

Zeroth-order optimization has become increasingly important in complex optimization and machine learning when cost functions are impossible to be described in closed analytical forms. The key idea of zeroth-order o…

ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models

2017-08-14 · Pin-Yu Chen, huan zhang, Yash Sharma, Jin-Feng Yi 외

Deep neural networks (DNNs) are one of the most prominent technologies of our time, as they achieve state-of-the-art performance in many machine learning tasks, including but not limited to image classification, text min…

Adversarial AttackAdversarial DefenseAutonomous DrivingDimensionality Reduction+2