paper-with-me

Papers

A Unified Framework for Entropy Search and Expected Improvement in Bayesian Optimization

2025-01-30 · Nuojin Cheng, Leonard Papenmeier, Stephen Becker, Luigi Nardi

Bayesian optimization is a widely used method for optimizing expensive black-box functions, with Expected Improvement being one of the most commonly used acquisition functions. In contrast, information-theoretic acquisition functions aim to reduce uncertainty about the function's optimum and are often considered fundamentally distinct from EI. In this work, we challenge this prevailing perspective by introducing a unified theoretical framework, Variational Entropy Search, which reveals that EI and information-theoretic acquisition functions are more closely related than previously recognized. We demonstrate that EI can be interpreted as a variational inference approximation of the popular information-theoretic acquisition function, named Max-value Entropy Search. Building on this insight, we propose VES-Gamma, a novel acquisition function that balances the strengths of EI and MES. Extensive empirical evaluations across both low- and high-dimensional synthetic and real-world benchmarks demonstrate that VES-Gamma is competitive with state-of-the-art acquisition functions and in many cases outperforms EI and MES.

📄 PDF Abstract BibTeX arXiv:2501.18756

Code (0)

등록된 구현이 없습니다.

Tasks

Bayesian OptimizationVariational Inference

Methods 이 논문이 사용한 방법론

Variational Inference 설명 없음

Similar Papers 제목 키워드 기반

Variational Entropy Search for Adjusting Expected Improvement

2024-02-17 · Nuojin Cheng, Stephen Becker

Bayesian optimization is a widely used technique for optimizing black-box functions, with Expected Improvement (EI) being the most commonly utilized acquisition function in this domain. While EI is often viewed as distin…

Bayesian OptimizationVariational Inference

Predictive Entropy Search for Bayesian Optimization with Unknown Constraints

2015-02-18 · José Miguel Hernández-Lobato, Michael A. Gelbart, Matthew W. Hoffman, Ryan P. Adams 외

Unknown constraints arise in many types of expensive black-box optimization problems. Several methods have been proposed recently for performing Bayesian optimization with constraints, based on the expected improvement (…

Bayesian Optimization

Edge Entropy as an Indicator of the Effectiveness of GNNs over CNNs for Node Classification

2020-12-16 · Lavender Yao Jiang, John Shi, Mark Cheung, Oren Wright 외

Graph neural networks (GNNs) extend convolutional neural networks (CNNs) to graph-based data. A question that arises is how much performance improvement does the underlying graph structure in the GNN provide over the CNN…

Node Classification

Targeted Exploration via Unified Entropy Control for Reinforcement Learning

2026-04-16 · Chen Wang, Lai Wei, Yanzhi Zhang, Chenyang Shao 외 arxiv

Recent advances in reinforcement learning (RL) have improved the reasoning capabilities of large language models (LLMs) and vision-language models (VLMs). However, the widely used Group Relative Policy Optimization (GRPO…

Reinforcement Learning

Maximum Entropy Heterogeneous-Agent Reinforcement Learning

2023-06-19 · Jiarong Liu, Yifan Zhong, Siyi Hu, Haobo Fu 외

Multi-agent reinforcement learning (MARL) has been shown effective for cooperative games in recent years. However, existing state-of-the-art methods face challenges related to sample complexity, training instability, and…

MuJoCoMulti-agent Reinforcement Learningreinforcement-learningReinforcement Learning+1