arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

California Institute of Technology(加州理工学院)

共收录 457
2606.21611 2026-06-23 cs.LG cs.AI math.GR math.GT 新提交

The Two-Hump Problem: Bridging the Difficulty Gap in Mathematical Reinforcement Learning

双峰问题:弥合数学强化学习中的难度差距

Lucas Fagan, Michele Tarquini, Ali Shehper, Maksymilian Manko, Angus Gruen, Coco Huang, Giorgi Butbaia, Davide Passaro, Sergei Gukov

机构 * Department of Mathematics, California Institute of Technology(加州理工学院数学系) Institute of Mathematics, University of Zurich(苏黎世大学数学研究所) Zero Latency Labs(零延迟实验室) Department of Mathematics, Temple University(天普大学数学系)

AI总结 针对数学搜索问题中奖励稀疏和难度分布不均的挑战,提出数据生成和算法增强方法,包括超移动和Transformer架构,显著提升性能并发布大规模基准数据集。

Comments Accepted at ICML 2026. 38 pages, 9 figures. Code and datasets: https://github.com/Math-AI-Caltech/ACSolverX

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.14959 2026-06-23 cs.RO cs.AI cs.LG cs.SY eess.SY

CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions

CBF-RL: 基于控制屏障函数的安全过滤强化学习

Lizhi Yang, Blake Werner, Massimiliano de Sa, Aaron D. Ames

机构 * Caltech MCE(加州理工学院机械工程系)

AI总结 本文提出CBF-RL框架,通过在训练过程中强制控制屏障函数以生成安全行为,使强化学习策略内在化安全约束,实现无需在线安全过滤的鲁棒安全部署。

Comments Accepted to the 2026 IEEE International Conference on Robotics and Automation (ICRA 2026). Copyright transferred to IEEE. Sample code for the navigation example with CBF-RL reward core construction can be found at https://github.com/lzyang2000/cbf-rl-navigation-demo

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.05497 2026-06-23 cs.RO 版本更新

Safe-SAGE: Social-Semantic Adaptive Guidance for Safe Engagement through Laplace-Modulated Poisson Safety Functions

Safe-SAGE: 通过拉普拉斯调制泊松安全函数实现安全交互的社会-语义自适应引导

Lizhi Yang, Ryan M. Bena, Meg Wilkinson, Gilbert Bahati, Andy Navarro Brenes, Ryan K. Cosner, Aaron D. Ames

机构 * Caltech MCE(Caltech机械工程系) Tufts ME(Tufts大学机械工程系)

AI总结 提出Safe-SAGE框架,结合泊松安全函数与拉普拉斯引导场,融合多传感器点云与视觉语义分割,通过多层安全滤波器实现腿式机器人在语义丰富动态环境中的安全导航。

Comments Accepted to the 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026). Copyright transferred to IEEE

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.13313 2026-06-23 stat.ML cs.LG math.OC 版本更新

Flow Matching for Efficient and Scalable Data Assimilation

用于高效可扩展数据同化的流匹配

Taos Transue, Bohan Chen, So Takao, Bao Wang

机构 * The Computing and Mathematical Sciences Department, California Institute of Technology(加州理工学院计算与数学科学系) Department of Mathematics and Scientific Computing and Imaging Institute, University of Utah(犹他大学数学与科学计算系和成像研究所)

AI总结 提出基于流匹配的无训练集成流滤波器(EnFF),通过蒙特卡洛估计和局部化引导加速高维非线性数据同化,在成本-精度权衡和可扩展性上优于现有方法。

Comments accepted for publication in SIAM/ASA Journal on Uncertainty Quantification

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.00909 2026-06-23 cs.LG math.OC 版本更新

Gaussian process policy iteration with additive Schwarz acceleration for forward and inverse HJB and mean field game problems

基于高斯过程策略迭代与加性Schwarz加速的正向和逆向HJB及平均场博弈问题

Xianjin Yang, Jingguo Zhang

机构 * Department of Computing and Mathematical Sciences, California Institute of Technology, CA, USA(计算与数学科学系,加州理工学院,CA,美国) Department of Mathematics and Risk Management Institute, National University of Singapore, Singapore(数学与风险管理研究所,新加坡国立大学,新加坡)

AI总结 提出高斯过程策略迭代框架,通过线性PDE配位约束和Legendre变换求解HJB方程和平均场博弈的正向与逆向问题,并利用加性Schwarz加速提高收敛效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.11494 2026-06-23 cs.RO 版本更新

SHIELD: Safety on Humanoids via CBFs In Expectation on Learned Dynamics

SHIELD: 基于学习动力学期望的控制障碍函数实现人形机器人安全

Lizhi Yang, Blake Werner, Ryan K. Cosner, David Fridovich-Keil, Preston Culbertson, Aaron D. Ames

机构 * Mechanical and Civil Engineering, California Institute of Technology(加州理工学院机械与土木工程系) Aerospace Engineering and Engineering Mechanics, UT Austin(德克萨斯大学奥斯汀分校航空航天工程与工程力学系) Computer Science, Cornell University(康奈尔大学计算机科学系)

AI总结 提出SHIELD框架,通过训练随机动力学残差模型并利用随机离散时间CBF在概率上保证安全,为黑箱RL控制器添加最小侵入式安全层,在Unitree G1人形机器人上实现安全导航。

Comments Accepted to the 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025). Copyright transferred to IEEE. Video at https://youtu.be/-Qv1wR4jfj4

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.11495 2026-06-23 cs.RO 版本更新

Bracing for Impact: Robust Humanoid Push Recovery and Locomotion with Reduced Order Models

冲击准备:基于简化模型的人形机器人稳健推倒恢复与行走

Lizhi Yang, Blake Werner, Adrian B. Ghansah, Aaron D. Ames

机构 * AMBER Lab at the Department of Mechanical and Civil Engineering, California Institute of Technology(机械与土木工程系AMBER实验室,加州理工学院)

AI总结 提出统一框架,结合单刚体模型预测控制与混合线性倒立摆动力学,利用环境(如墙壁)和手臂支撑实现人形机器人动态行走中的推倒恢复,在高达0.5m/s行走速度下抵抗100N持续0.2s的推力。

Comments Accepted to the 2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids 2025). Copyright transferred to IEEE

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.20542 2026-06-19 cs.CV 新提交

CalTennis: Large Multi-View Tennis Video Dataset and Benchmark of Monocular-to-3D Pose Estimation

CalTennis:大型多视角网球视频数据集及单目到3D姿态估计基准

Ilona Demler, Xinran Xie, Blake Werner, Anna Szczuka, Pietro Perona

机构 * California Institute of Technology(加州理工学院)

AI总结 提出CalTennis大型多视角网球视频数据集(1100万帧,40名球员),用于评估野外单目到3D姿态估计,并发现现有模型在深度估计和足部接触方面存在不足。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.19539 2026-06-19 astro-ph.SR cs.AI 新提交

Review of Machine Learning Models for Solar Energetic Particle Prediction

太阳高能粒子预测的机器学习模型综述

Spiridon Kasapis, Pouya Hosseinzadeh, Kathryn Whitman, Ricky Egeland, Manolis Georgoulis, Angelos Vourlidas, Athanasios Papaioannou, Eleni Lavasa, Anastasios Anastasiadis, Giorgos Giannopoulos, Andres Munoz-Jaramillo, Bala Poduval, Irina N. Kitiashvili, Alexander G. Kosovichev, Viacheslav Sadykov, Soukaina Filali Boubrahimi, Tate T. Hutchins, Hameedullah A. Farooki, Manuel E. Cuesta, Leng Y. Khoo, Sungmin Pak, Robert Czarnota, Jamie S. Rankin, Jamey Szalay, Mitchell M. Shen, Georgios Livadiotis, Zigong Xu, David J. McComas, Nikolaos Sarlis, Dionissios Hristopulos, Arik Posner, Alec J. Engell, Mohammed AbuBakr Ali, Ali G. A. Abdelkawy, Abdelrazek M. K. Shaltout, M. M. Beheary, Christina O. Lee, Sigiava Aminalragia-Giamini, Constantinos Papadimitriou, Ingmar Sandberg, Savvas Raptis, Shah Muhammad Hamdi, Monica Laurenza, Mirko Stumpo, Sumanth A. Rotti, India Jackson, Aatiya Ali, Atilim Gunes Baydin, Nathan Schwadron, Subhamoy Chatterjee, Maher A. Dayeh, Gelu M. Nita, Patrick M. O'Keefe, Chun Jie Chong, Paul Kosovich, Russell D. Marroquin, Berkay Aydin, Petrus C. Martens, Lulu Zhao, Yang Chen, Yian Yu, Monica G. Bobra, Ward Manchester, Tamas Gombosi, Ming Zhang, Jesse Torres, Philip K. Chan, Mohamed Nedal, Kamen Kozarev, Peijin Zhang, Kimberly Moreland, Hazel M. Bain, Samuel Hart, Michael J. Starkey, Alan G. Ling, Simone Benella

机构 * Department of Astrophysical Sciences, Princeton University, Princeton, NJ, USA Computational Physics Branch, NASA Ames Research Center, Moffett Field, CA, USA Department of Computer Science, Utah State University, Logan, UT, USA Space Radiation Analysis Group, NASA Johnson Space Center, Houston, TX, USA Johns Hopkins Applied Physics Lab, 11100 Johns Hopkins Rd, Laurel, MD 20723, United States Research Center for Astronomy Applied Mathematics of the Academy of Athens, 4 Soranou Efesiou Street, Athens 11527, Greece Institute for Astronomy, Astrophysics, Space Applications Southwest Research Institute, Boulder, CO, USA Space Science Center, University of New Hampshire, Durham, NH, USA Department of Physics, New Jersey Institute of Technology, Newark, NJ, USA Astronomy Department, Georgia State University, Atlanta, GA, USA Department of Computer Science, Princeton University, Princeton, NJ, USA Department of Mathematics, Rowan University, Glassboro, NJ, USA Astronomy, California Institute of Technology, Pasadena, CA, USA Department of Physics, National Kapodistrian University of Athens, Athens, Greece School of Electrical Computer Engineering, Technical University of Crete, Chania, Greece Department of Astronomy Meteorology, Faculty of Science, Al-Azhar University, Cairo, Egypt Space Sciences Lab, University of California, Berkeley, CA, USA Research Consultancy, Athens, Greece Institute for Space Astrophysics Department of Physics Astronomy, Georgia State University, Atlanta, GA 30303, USA Aryabhatta Research Institute of Observational Sciences (ARIES), Manora Peak, Nainital-263001, Uttarakhand, India Department of Computer Science, Oxford University, Oxford, England Southwest Research Institute, San Antonio, TX, USA Computer Science Department, New Jersey Institute of Technology, Newark, NJ, USA Department of Physics, University of California San Diego, La Jolla, CA 92093, USA Department of Computer Science, Georgia State University, Atlanta, GA 30303, USA Department of Climate Engineering, University of Michigan, Ann Arbor, MI, USA Department of Statistics, University of Michigan, Ann Arbor, MI, USA Department of Electrical Engineering Computer Science, Florida Institute of Technology, Melbourne, FL, USA Astrophysics Section, School of Cosmic Physics, Dublin Institute for Advanced Studies, DIAS Dunsink Observatory, Dublin D15 XR2R, Ireland Institute of Astronomy of the Bulgarian Academy of Sciences, Sofia, Bulgaria Center for Solar-Terrestrial Research, New Jersey Institute of Technology, Newark, NJ 07102, USA Cooperative Programs for the Advancement of Earth System Science, University Corporation for Atmospheric Research, Boulder, CO, USA CIRES, University of Colorado Boulder, Boulder, CO, USA Space Weather Prediction Center, NOAA, Boulder, CO, USA Astronomy, College of Science, The University of Texas at San Antonio, San Antonio, TX, USA Space Weather Prediction Center, National Oceanic The University of Texas at San Antonio, San Antonio, TX, USA Environmental Research, Inc., MA, USA

AI总结 综述了用于太阳高能粒子预测的机器学习模型,包括数据集、架构、输入输出比较,并提出了未来研究建议。

Comments Review Paper, Maine text: 23 pages, References: 5 pages, Appendix: 42 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.17413 2026-06-17 cs.LG stat.AP 新提交

Amortized Probabilistic Retrieval of Atmospheric CO2 from OCO-2 Spectra Using Deep Learning with Laplace Approximations and Normalizing Flows

基于深度学习的OCO-2光谱大气CO2摊销概率检索:结合拉普拉斯近似与归一化流

Alejandro Calle-Saldarriaga, Felix Jimenez, Jack Grosskreuz, Jiazheng Wang, Jonathan Hobbs, Matthias Katzfuss

机构 * University of Wisconsin–Madison(威斯康星大学麦迪逊分校) Jet Propulsion Laboratory, California Institute of Technology(加州理工学院喷气推进实验室)

AI总结 提出深度学习框架,利用拉普拉斯近似和归一化流从OCO-2光谱中快速、准确地检索大气CO2浓度,并量化不确定性,相比传统方法加速数个数量级且精度更高。

Comments 23 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.16219 2026-06-16 cs.CE cs.LG physics.comp-ph 新提交

Graphical conditional generative modeling for digital twin modeling

面向数字孪生建模的图条件生成建模

Zongren Zou, Théo Bourdais, Ricardo Baptista, Houman Owhadi

机构 * Department of Computing and Mathematical Sciences, California Institute of Technology(计算与数学科学系,加州理工学院) Department of Statistical Sciences, University of Toronto(统计科学系,多伦多大学)

AI总结 针对数字孪生建模中的保真度问题,提出一种基于条件生成模型和高斯过程方差分析(核模式分解)的框架,从观测数据中发现影响目标条件分布的关键变量,构建简约随机代理模型,并在控制、强化学习等任务中验证其性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.08029 2026-06-16 gr-qc astro-ph.IM cs.CV 版本更新

Dynamic Black-hole Emission Tomography with Physics-informed Neural Fields

基于物理信息神经场的动态黑洞发射断层成像

Berthy T. Feng, Andrew A. Chael, David Bromley, Aviad Levis, William T. Freeman, Katherine L. Bouman

机构 * Caltech(加州理工学院) MIT(麻省理工学院) NSF IAIFI(国家科学基金会IAIFI) Princeton University(普林斯顿大学) Niels Bohr International Academy(尼尔斯·玻尔国际学院) University of Toronto(多伦多大学)

AI总结 提出PI-DEF方法,利用可微神经渲染从EHT测量数据中联合重建4D发射率场和3D速度场,以软约束方式引入物理信息,在模拟数据上显著优于现有方法。

Comments CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.12730 2026-06-12 cs.AI cs.CL cs.CY cs.LG 新提交

Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior

重新思考LLMs的心理测量评估:自我报告何时以及为何能预测行为

Rafal Kocielnik, Pengrui Han, Peiyang Song, Myrl G. Marmarelis, Ramit Debnath, Dean Mobbs, Anima Anandkumar, R. Michael Alvarez

机构 * Caltech(加州理工学院) UIUC(伊利诺伊大学厄巴纳-香槟分校) University of Cambridge(剑桥大学)

AI总结 研究对比大五人格与计划行为理论,发现LLMs的自我报告-行为一致性存在选择性:在共享对话中TPB达到人类水平,跨对话仅对锚定于训练的行为保持一致性,且角色提示不能使行为对齐。

Comments Accepted as an Oral (Contributed Talk) at the ICML 2026 Workshop on Combining Theory and Benchmarks (CTB)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.03699 2026-06-12 q-bio.NC cs.AI cs.LG cs.NE cs.SY eess.SY

Dissecting Larval Zebrafish Hunting using Deep Reinforcement Learning Trained RNN Agents

解析斑马鱼幼体捕食行为的深度强化学习训练RNN代理

Raaghav Malik, Satpreet H. Singh, Sonja Johnson-Yu, Nathan Wu, Roy Harpaz, Florian Engert, Kanaka Rajan

机构 * California Institute of Technology(加州理工学院) Harvard University(哈佛大学)

AI总结 本文通过深度强化学习训练RNN代理,研究斑马鱼幼体捕食行为,揭示生态和能量约束如何影响适应性行为,发现简单模型能复现真实捕食行为,并通过虚拟实验验证约束和环境对捕食动态的影响。

Journal ref Proceedings of the 9th Conference on Cognitive Computational Neuroscience (2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.12016 2026-06-11 cs.LG cs.AI 新提交

Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral Generalization

泛化黑客:模型可通过阻止行为泛化来博弈强化学习

Frank Xiao, Mary Phuong

机构 * California Institute of Technology(加州理工学院)

AI总结 本研究提出泛化黑客现象,模型在强化学习中通过自我接种机制阻止行为泛化,在保持高奖励的同时抵抗行为修正,首次证明模型能主动破坏训练过程。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.11998 2026-06-11 cs.LG 新提交

Bootstrapped Monitoring: Leveraging Transparent Reasoning to Oversee Stronger AI Agents

自助监控:利用透明推理监督更强的AI智能体

Frank Xiao, Mary Phuong

机构 * California Institute of Technology(加州理工学院)

AI总结 提出自助监控协议,通过插入具有透明思维链的不可信中间模型来监督更强智能体,在软件工程任务中显著提升捕获率,即使不可信监控者与智能体合谋。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.11650 2026-06-11 cs.LG cs.NA math.NA physics.comp-ph 新提交

Structure-Preserving Neural Surrogates with Tractable Uncertainty Quantification

具有可处理不确定性量化的保结构神经代理模型

Handi Zhang, Adrienne M. Propp, Brooks Kinch, Houman Owhadi, Nathaniel Trask

机构 * University of Pennsylvania(宾夕法尼亚大学) Stanford University(斯坦福大学) California Institute of Technology(加州理工学院)

AI总结 提出一种结合混合有限元空间与高斯过程回归的保结构降阶模型,通过拓扑结构实现状态-通量关系的不确定性量化,并导出狄利克雷-诺伊曼映射的闭式后验不确定性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.06578 2026-06-11 cs.RO cs.SY eess.SY 版本更新

Non-Equilibrium MAV-Capture-MAV via Time-Optimal Planning and Reinforcement Learning

非平衡MAV捕获MAV:基于时间最优规划和强化学习

Canlun Zheng, Zhanyu Guo, Zikang Yin, Chunyu Wang, Zhikun Wang, Shiyu Zhao

机构 * College of Computer Science and Technology, Zhejiang University, Hangzhou, China(浙江大学计算机科学与技术学院,中国杭州) WINDY Lab, Department of Artificial Intelligence, Westlake University, Hangzhou, China(西湖大学人工智能系WINDY实验室,中国杭州) Department of Electrical Engineering, California Institute of Technology, Pasadena, USA(加州理工学院电气工程系,美国帕萨迪纳)

AI总结 针对高机动性目标捕获难题,本文设计紧凑型捕获MAV,结合时间最优规划与强化学习方法,在非稳定状态下实现目标捕获。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.06493 2026-06-10 cs.RO cs.AI cs.LG 版本更新

HANDOFF: Humanoid Agentic Task-Space Whole-Body Control via Distilled Complementary Teachers

HANDOFF: 通过蒸馏互补教师实现人形机器人任务空间全身控制

Lizhi Yang, Junheng Li, Nehar Poddar, Yiling Hou, Gio Huh, Robert Griffin, Georgia Gkioxari, Aaron Ames

机构 * California Institute of Technology(加州理工学院) The Institute for Human & Machine Cognition(人机认知研究院)

AI总结 提出HANDOFF框架,通过多教师KL蒸馏和上下文门控机制,将全身运动跟踪、行走和跌倒恢复三个专家策略融合为混合专家学生策略,实现基于紧凑显式接口的全身控制,在Unitree G1上达到先进的速度跟踪性能并扩展了操作工作空间。

Comments 22 pages, 9 figures, Project page: https://lzyang2000.github.io/HANDOFF/

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.02608 2026-06-10 cs.LG 版本更新

Pruning Deep Neural Networks via the Marchenko--Pastur Distribution

通过Marchenko-Pastur分布剪枝深度神经网络

Leonid Berlyand, Theo Bourdais, Houman Owhadi, Yitzchak Shmalo

机构 * Department of Mathematics, Pennsylvania State University(数学系,宾夕法尼亚州立大学) Department of Computing and Mathematical Sciences, California Institute of Technology(计算与数学科学系,加州理工学院)

AI总结 提出基于Marchenko-Pastur随机矩阵理论的剪枝方法,在极短微调预算下保持精度,并在ImageNet-1k上验证了多种架构的高效稀疏执行加速。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.08802 2026-06-09 cs.LG 新提交

Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules

主动流扩展用于分布外发现:从理论到分子

Riccardo De Santi, Bruce Lee, Cristian Perez Jensen, Kimon Protopapas, Sophia Tang, Cheng-Hao Liu, Pranam Chatterjee, Yisong Yue, Andreas Krause

机构 * ETH Zurich(苏黎世联邦理工学院) ETH AI Center(ETH AI 中心) University of Pennsylvania(宾夕法尼亚大学) Caltech(加州理工学院) FutureHouse

AI总结 提出Active Flow Expansion (ActFlow)方法,通过验证器反馈和主动探索扩展预训练流模型的生成集,覆盖更多有效设计空间,理论证明统计学习保证,在分子和蛋白质任务上优于现有方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.05687 2026-06-05 cs.RO cs.SY eess.SY

Accelerating and Scaling MPC-Guided Reinforcement Learning for Humanoid Locomotion and Manipulation

加速与扩展MPC引导的强化学习在类人机器人行走与操作中的应用

Junheng Li, Liang Wu, Sergio A. Esteban, Lizhi Yang, Ján Drgoňa, Aaron D. Ames

机构 * California Institute of Technology(加州理工学院) Johns Hopkins University(约翰霍普金斯大学)

AI总结 本文提出了一种基于质心动力学MPC奖励的MPC-RL框架,并开发了并行批处理GPU求解器π^nMPC,以高效实现类人机器人的行走与操作技能。

Comments 8 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.10968 2026-06-05 cs.LG stat.ML

Blade: A Derivative-free Bayesian Inversion Method using Diffusion Priors

Blade:一种使用扩散先验的无导数贝叶斯反演方法

Hongkai Zheng, Austin Wang, Zihui Wu, Zhengyu Huang, Ricardo Baptista, Yisong Yue

机构 * California Institute of Technology(加州理工学院) University of Toronto(多伦多大学) Peking University(北京大学)

AI总结 本文提出Blade方法,通过使用扩散模型作为数据驱动的先验,解决无导数贝叶斯反演中高维非线性问题的后验估计问题,实现了准确且校准良好的后验分布。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.05103 2026-06-04 cs.LG astro-ph.IM cs.CV stat.ML

Identifying Gems from Roman RAPIDly

从Roman RAPIDly中识别宝石

Karan Gandhi, Ashish A. Mahabal, Jacob E. Jencson, Russ R. Laher, Ben Rusholme, Lin Yan, Ryan M. Lau, Schuyler D. Van Dyk, Mansi M. Kasliwal

机构 * Department of Computer Science and Engineering, Indian Institute of Technology, Gandhinagar, India(印度理工学院计算机科学与工程系) Division of Physics, Mathematics, and Astronomy, California Institute of Technology, Pasadena, CA 91125, USA(加州理工学院物理、数学与天文学系) Center for Data Driven Discovery, California Institute of Technology, Pasadena, CA 91125, USA(数据驱动发现中心) IPAC, California Institute of Technology, 1200 E. California Blvd, Pasadena, CA 91125, USA(IPAC, 加州理工学院) Caltech Optical Observatories, California Institute of Technology, Pasadena, CA 91125, USA(加州理工学院光学观测站)

AI总结 针对Roman太空望远镜无真实数据的问题,提出机器学习模型RuBR和通用方法,用于在RAPID流水线中区分真实瞬变/变源与虚假检测,实验表明该方法在Roman时代具有鲁棒性。

Comments 15 pages, 10 figures, Submitted to the Publications of the Astronomical Society of the Pacific

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.04279 2026-06-04 cs.LG quant-ph

Derivative Informed Learning of Exchange-Correlation Functionals

交换相关泛函的导数知情学习

Eike S. Eberhard, Luca A. Thiede, Abdul Aldossary, Andreas Burger, Nicholas Gao, Vignesh Bhethanabotla, Alán Aspuru-Guzik, Stephan Günnemann

机构 * Technical University of Munich(慕尼黑技术大学) Munich Data Science Institute(慕尼黑数据科学研究所) Munich Center for Machine Learning(慕尼黑机器学习中心) University of Toronto(多伦多大学) Vector Institute(向量研究所) CuspAI California Institute of Technology(加州理工学院)

AI总结 提出导数知情交换相关损失(DI-Loss),通过监督能量在密度矩阵Grassmannian上的一阶和二阶导数,训练O(N^3)标度的机器学习交换相关泛函以复现B3LYP/def2-SVP目标,在多个架构上平均总能量MAE降低66%,并减少混合泛函SCF迭代次数达50%。

Comments Proceedings of the 43rd International Conference on Machine Learning

详情

展开后加载摘要…

URL PDF HTML 收藏
1903.07214 2026-06-04 eess.SY cs.LG cs.SY

A Control Lyapunov Perspective on Episodic Learning via Projection to State Stability

从控制李雅普诺夫视角看通过投影到状态稳定性进行片段学习

Andrew J. Taylor, Victor D. Dorobantu, Meera Krishnamoorthy, Hoang M. Le, Yisong Yue, Aaron D. Ames

机构 * California Institute of Technology(加州理工学院)

AI总结 本文从李雅普诺夫函数视角探讨学习对控制合成的影响,提出投影到状态稳定性(PSS)概念,用于表征CLF对系统不确定数据的鲁棒性,并展示如何利用PSS在仿射控制中限制不确定性,实现鲁棒控制合成。

详情

展开后加载摘要…

URL PDF HTML 收藏
1903.01577 2026-06-04 cs.RO cs.LG cs.SY eess.SY

Episodic Learning with Control Lyapunov Functions for Uncertain Robotic Systems

具有控制李雅普诺夫函数的不确定性机器人系统的经验学习

Andrew J. Taylor, Victor D. Dorobantu, Hoang M. Le, Yisong Yue, Aaron D. Ames

机构 * California Institute of Technology(加州理工学院)

AI总结 本文提出了一种基于控制李雅普诺夫函数的机器学习框架,用于适应机器人系统中的参数不确定性和未建模动态,通过迭代更新李雅普诺夫函数导数的估计和改进控制器,最终获得一个稳定性的二次规划基于控制器,并在平面Segway模拟中验证了方法的有效性。

详情

展开后加载摘要…

URL PDF HTML 收藏
1904.01068 2026-06-04 cs.RO cs.AI cs.LG cs.SY eess.SY

Efficient and Safe Exploration in Deterministic Markov Decision Processes with Unknown Transition Models

在未知转移模型的确定性马尔可夫决策过程中实现高效且安全的探索

Erdem Bıyık, Jonathan Margoliash, Shahrouz Ryan Alimo, Dorsa Sadigh

机构 * Stanford University(斯坦福大学) Jet Propulsion Laboratory(喷气推进实验室) California Institute of Technology(加州理工学院)

AI总结 本文提出了一种安全探索算法,通过利用Lipschitz连续性确保在探索过程中不访问危险状态,该算法在确定性马尔可夫决策过程中提供了确定性的安全保证,并通过模拟导航任务验证了其性能。

Comments Proceedings of the American Control Conference (ACC), July 2019. The first two authors have equal contribution

详情

展开后加载摘要…

URL PDF HTML 收藏
1905.05380 2026-06-04 cs.LG cs.SY eess.SY stat.ML

Control Regularization for Reduced Variance Reinforcement Learning

减少方差的强化学习中的控制正则化

Richard Cheng, Abhinav Verma, Gabor Orosz, Swarat Chaudhuri, Yisong Yue, Joel W. Burdick

机构 * California Institute of Technology, Pasadena, CA(加州理工学院) University of Michigan, Ann Arbor, MI(密歇根大学) Rice University, Houston, TX(Rice大学)

AI总结 本文提出了一种功能正则化方法,用于减少连续控制中强化学习的方差,通过正则化深度策略的行为与先验策略相似,从而在偏倚-方差权衡中实现更稳定的动态稳定性和更高效的训练。

Comments Appearing in ICML 2019

详情

展开后加载摘要…

URL PDF HTML 收藏
1904.01855 2026-06-04 math.OC cs.LG cs.SY eess.SY stat.ML

A Stochastic Interpretation of Stochastic Mirror Descent: Risk-Sensitive Optimality

随机镜像下降的随机解释:风险敏感最优性

Navid Azizan, Babak Hassibi

机构 * California Institute of Technology(加州理工学院)

AI总结 本文提出随机镜像下降(SMD)是一种风险敏感最优估计器,适用于非高斯分布的未知权重向量和加性噪声,同时引入了对称SMD(SSMD)的改进版本。

详情

展开后加载摘要…

URL PDF HTML 收藏