paper-with-me

홈 › Papers

ZeroShotOpt: Towards Zero-Shot Pretrained Models for Efficient Black-Box Optimization

2025-10-03 · Jamison Meindl, Yunsheng Tian, Tony Cui, Veronika Thost, Zhang-Wei Hong, Johannes Dürholt, Jie Chen, Wojciech Matusik, Mina Konaković Luković arxiv

Global optimization of expensive, derivative-free black-box functions requires extreme sample efficiency. While Bayesian optimization (BO) is the current state-of-the-art, its performance hinges on surrogate and acquisition function hyper-parameters that are often hand-tuned and fail to generalize across problem landscapes. We present ZeroShotOpt, a general-purpose, pretrained model for continuous black-box optimization tasks ranging from 2D to 20D. Our approach leverages offline reinforcement learning on large-scale optimization trajectories collected from 12 BO variants. To scale pretraining, we generate millions of synthetic Gaussian process-based functions with diverse landscapes, enabling the model to learn transferable optimization policies. As a result, ZeroShotOpt achieves robust zero-shot generalization on a wide array of unseen benchmarks, matching or surpassing the sample efficiency of leading global optimizers, including BO, while also offering a reusable foundation for future extensions and improvements. Our open-source code, dataset, and model are available at: https://github.com/jamisonmeindl/zeroshotopt

📄 PDF Abstract BibTeX arXiv:2510.03051

Code (0)

등록된 구현이 없습니다.

Tasks

Zero-shot GeneralizationReinforcement Learning

Similar Papers 제목 키워드 기반

Pretrained Optimization Model for Zero-Shot Black Box Optimization

2024-05-06 · XiaoBin Li, Kai Wu, Yujian Betterest Li, XiaoYu Zhang 외

Zero-shot optimization involves optimizing a target task that was not seen during training, aiming to provide the optimal solution without or with minimal adjustments to the optimizer. It is crucial to ensure reliable an…

Evolutionary Algorithms

Survival of the Most Influential Prompts: Efficient Black-Box Prompt Search via Clustering and Pruning

2023-10-19 · Han Zhou, Xingchen Wan, Ivan Vulić, Anna Korhonen

Prompt-based learning has been an effective paradigm for large pretrained language models (LLM), enabling few-shot or even zero-shot learning. Black-box prompt search has received growing interest recently for its distin…

Combinatorial OptimizationZero-Shot Learning

InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models

2023-06-05 · Lichang Chen, Jiuhai Chen, Tom Goldstein, Heng Huang 외

Large language models~(LLMs) are instruction followers, but it can be challenging to find the best instruction for different situations, especially for black-box LLMs on which backpropagation is forbidden. Instead of dir…

Bayesian Optimization

Zero-shot Cross-lingual Transfer is Under-specified Optimization

2021-10-16 · ACL ARR October 2021 10 · Anonymous

Pretrained multilingual encoders enable zero-shot cross-lingual transfer performance, but often produce unreliable models that exhibit high performance variance on the target language. We postulate that high variance res…

Cross-Lingual TransferZero-Shot Cross-Lingual Transfer

VoiceTTA: Enhancing Zero-Shot Text-to-Speech via Reinforcement Learning-Based Test-Time Adaptation

2026-06-25 · Tianxin Xie, Chenxing Li, Dong Yu, Li Liu arxiv

Recently, zero-shot text-to-speech (TTS) has enabled high-fidelity and expressive speech synthesis, but it often fails to imitate unseen speaking styles from uncommon scenarios (e.g., crosstalk, dialects). Moreover, fine…

Reinforcement LearningTest-time AdaptationSpeech Synthesis