arXiv cs.AI· Yonatan Gideoni, Yarin Gal·· 3 天前AI 评分26
分布匹配进化算法（DME）：无需更新权重即可从全局目标分布采样
Distribution Matching Evolutionary Algorithms for Rare Event Sampling
AI 导读
研究者提出分布匹配进化算法（DME），将多种进化算法解释为近似马尔可夫链蒙特卡洛，从而在不更新模型权重的情况下从全局目标分布中采样，可用于罕见事件采样与发现。在需要大量采样才能找到解的问题上，DME 的样本效率高于现有方法。
正文 · 原文
Abstract:A novel discovery is one which is both useful and surprising: a generative model's output is a useful discovery if it has a low probability of being generated (it's surprising) and a high reward (it's useful). Global optimization can directly increase the probability of sampling high rewards but typically requires updating model weights. Such gradient based optimization is expensive and bars using capable closed-source models. Instead, modern search methods for discovery sacrifice the global target, and use evolutionary algorithms with local reward maximizing objectives, permitting the search to focus only on high probability samples. In this paper, we interpret various evolutionary algorithms as approximate Markov Chain Monte Carlo, an optimization-free method to sample from complex distributions. This interpretation allows developing Distribution Matching Evolutionary Algorithms (DME), a class of search methods which sample from a global target distribution without updating weights. Empirically, DME has a higher sample efficiency than existing methods on problems requiring many samples to find a solution.
| Subjects: | Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.03833 [cs.NE] |
| (or arXiv:2610.03833v2 [cs.NE] for this version) | |
| https://doi.org/10.48550/arXiv.2610.03833 arXiv-issued DOI via DataCite |
Submission history
From: Yonatan Gideoni [view email]
[v1]
Fri, 2 Oct 2026 12:31:06 UTC (182 KB)
[v2]
Tue, 13 Oct 2026 12:42:15 UTC (182 KB)
来源：arXiv cs.AI · arxiv.org