arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

International Conference on Machine Learning · 会议 · Machine Learning

2026-04-28 至 2026-04-28 共收录 5
2604.24537 2026-04-28 cs.LG stat.ML

Stochastic simultaneous optimistic optimization

随机同时乐观优化

Michal Valko, Alexandra Carpentier, Rémi Munos

机构 * INRIA Lille - Nord Europe, SequeL team(INRIA里尔-北欧,SequeL团队) Statistical Laboratory, CMS, Wilberforce Road, CB3 0WB, University of Cambridge, United Kingdom(剑桥大学统计实验室,CMS,威尔伯福斯路,CB3 0WB,英国)

AI总结 本文研究在噪声干扰下有限次评估中全局最大化函数的问题,提出无需半度量知识的StoSOO算法,通过乐观策略构建层次划分的置信区间来选择下一步采样点,证明其在有限时间内性能接近最优调优算法。

Comments Published in International Conference on Machine Learning (ICML 2013)

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.23790 2026-04-28 cs.LG stat.ML

A General Representation-Based Approach to Multi-Source Domain Adaptation

多源领域适应的通用表示方法

Ignavier Ng, Yan Li, Zijian Li, Yujia Zheng, Guangyi Chen, Kun Zhang

机构 * Carnegie Mellon University(卡内基梅隆大学) Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)

AI总结 本文提出一种通用领域适应框架,通过学习紧凑的潜在表示来捕捉分布偏移,解决转移哪些表示的问题,并通过理论分析建立可识别性保证。

Comments ICML 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.23307 2026-04-28 cs.LG cs.AI

CombiMOTS: Combinatorial Multi-Objective Tree Search for Dual-Target Molecule Generation

CombiMOTS:基于双靶分子生成的组合多目标树搜索

Thibaud Southiratn, Bonil Koo, Yijingxiu Lu, Sun Kim

机构 * Department of Computer Science and Engineering, Seoul National University, Seoul, Republic of Korea(首尔国立大学计算机科学与工程系) Interdisciplinary Program in Bioinformatics, Seoul National University, Seoul, Republic of Korea(首尔国立大学生物信息学跨学科项目) AIGENDRUG Co., Ltd., Seoul, Republic of Korea(AIGENDRUG公司) Interdisciplinary Program in Artificial Intelligence, Seoul National University, Seoul, Republic of Korea(首尔国立大学人工智能跨学科项目)

AI总结 本文提出CombiMOTS,一种基于多目标树搜索的框架,用于生成双靶分子,通过向量优化约束平衡靶点亲和力与物理化学性质,实验表明其能生成高评分、多样化的双靶分子。

Comments Accepted as a poster at ICML 2025 (Main Track)

Journal ref Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:56650-56691, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.23056 2026-04-28 cs.LG cs.AI

K-Score: Kalman Filter as a Principled Alternative to Reward Normalization in Reinforcement Learning

K-Score:卡尔曼滤波作为强化学习中奖励归一化的原理性替代方案

Zixuan Xia, Quanxi Li

机构 * University of Bern, Bern, Switzerland(伯恩大学)

AI总结 本文提出一种简单有效的奖励归一化替代方法,通过整合一维卡尔曼滤波进行在线奖励估计,递归估计潜在奖励均值,降低高方差回报并适应非平稳环境,实验表明其加速收敛并减少训练方差。

Comments Accepted in NewInML Workshop, The 42nd International Conference on Machine Learning (ICML 2025).\href{https://icml.cc/virtual/2025/affinity-event/39980}{Event Page}

详情

展开后加载摘要…

URL PDF HTML 收藏
2105.04332 2026-04-28 cs.LG stat.ML

Bayesian Optimistic Optimisation with Exponentially Decaying Regret

基于指数衰减遗憾的贝叶斯乐观优化

Hung Tran-The, Sunil Gupta, Santu Rana, Svetha Venkatesh

机构 * Applied Artificial Intelligence Institute, Deakin University, Geelong, Australia(应用人工智能研究所,德金大学,澳大利亚格里尔镇)

AI总结 本文提出BOO算法,在无噪声环境下通过结合贝叶斯优化与基于树的乐观优化方法,实现指数级遗憾界O(N^{-√N})。

Comments To appear at ICML 2021 (21 pages)

Journal ref PMLR 139:10390-10400, 2021

详情

展开后加载摘要…

URL PDF HTML 收藏