Natural Perturbations for Black-box Training of Neural Networks by Zeroth-Order Optimization

Hiroshi Sawada, Kazuo Aoyama, Yuya Hikima
2/14/2026

No confident code implementation found for this paper. 1 possible match can be shown below.

Semantic Scholar

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Adaptive Stochastic Gradient Algorithm for Black-box Multi-Objective Learning

93% match2026

Fast Rank-1 Lattice Targeted Sampling for Black-box Optimization

89% match2026

Model Shapley: Equitable Model Valuation with Black-box Access

88% match1 repo32026

Towards AutoAI: Optimizing a Machine Learning System with Black-box and Differentiable Components

87% match2026

KooNPro: A Variance-Aware Koopman Probabilistic Model Enhanced by Neural Process for Time Series Forecasting

80% match2026

ALAM: Averaged Low-Precision Activation for Memory-Efficient Training of Transformer Models

80% match2026

Cite this paper

@article{sawada2026natural,
  title  = {Natural Perturbations for Black-box Training of Neural Networks by Zeroth-Order Optimization},
  author = {Hiroshi Sawada and Kazuo Aoyama and Yuya Hikima},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:06e396e383a1a8b168a374ffdfdb46f30a6d8740},
  journal = {ICML 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/06e396e383a1a8b168a374ffdfdb46f30a6d8740.svg)](https://codeofpaper.com/paper/06e396e383a1a8b168a374ffdfdb46f30a6d8740)

Discussion