paper-with-me

Papers

Locality-aware Surrogates for Gradient-based Black-box Optimization

2025-01-31 · Ali Momeni, Stefan Uhlich, Arun Venkitaraman, Chia-Yu Hsieh, Andrea Bonetti, Ryoga Matsuo, Eisaku Ohbuchi, Lorenzo Servadei

In physics and engineering, many processes are modeled using non-differentiable black-box simulators, making the optimization of such functions particularly challenging. To address such cases, inspired by the Gradient Theorem, we propose locality-aware surrogate models for active model-based black-box optimization. We first establish a theoretical connection between gradient alignment and the minimization of a Gradient Path Integral Equation (GradPIE) loss, which enforces consistency of the surrogate's gradients in local regions of the design space. Leveraging this theoretical insight, we develop a scalable training algorithm that minimizes the GradPIE loss, enabling both offline and online learning while maintaining computational efficiency. We evaluate our approach on three real-world tasks - spanning automated in silico experiments such as coupled nonlinear oscillators, analog circuits, and optical systems - and demonstrate consistent improvements in optimization efficiency under limited query budgets. Our results offer dependable solutions for both offline and online optimization tasks where reliable gradient estimation is needed.

📄 PDF Abstract BibTeX arXiv:2501.19161

Code (0)

등록된 구현이 없습니다.

Tasks

Computational Efficiency

Similar Papers 제목 키워드 기반

Black-Box Optimization with Local Generative Surrogates

2020-02-11 · NeurIPS 2020 12 · Sergey Shirobokov, Vladislav Belavin, Michael Kagan, Andrey Ustyuzhanin 외

We propose a novel method for gradient-based optimization of black-box simulators using differentiable local surrogate models. In fields such as physics and engineering, many processes are modeled with non-differentiable…

Bayesian Optimization

Optimizing Black-box Metrics with Adaptive Surrogates

2020-02-20 · ICML 2020 1 · Qijia Jiang, Olaoluwa Adigun, Harikrishna Narasimhan, Mahdi Milani Fard 외

We address the problem of training models with black-box and hard-to-optimize metrics by expressing the metric as a monotonic function of a small number of easy-to-optimize surrogates. We pose the training problem as an …

End-to-End Optimal Detector Design with Mutual Information Surrogates

2025-03-18 · Kinga Anna Wozniak, Stephen Mulligan, Jan Kieseler, Markus Klute 외

We introduce a novel approach for end-to-end black-box optimization of high energy physics (HEP) detectors using local deep learning (DL) surrogates. These surrogates approximate a scalar objective function that encapsul…

Federated Zeroth-Order Optimization using Trajectory-Informed Surrogate Gradients

2023-08-08 · Yao Shu, Xiaoqiang Lin, Zhongxiang Dai, Bryan Kian Hsiang Low

Federated optimization, an emerging paradigm which finds wide real-world applications such as federated learning, enables multiple clients (e.g., edge devices) to collaboratively optimize a global function. The clients d…

Adversarial AttackFederated Learning

Defining Locality for Surrogates in Post-hoc Interpretablity

2018-06-19 · Thibault Laugel, Xavier Renard, Marie-Jeanne Lesot, Christophe Marsala 외

Local surrogate models, to approximate the local decision boundary of a black-box classifier, constitute one approach to generate explanations for the rationale behind an individual prediction made by the back-box. This …

Prediction