Uehara, Masatoshi
- Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding
2024/08/15 by Li, Xiner, Zhao, Yulai, Wang, Chenyu +8 · 32 citations
#Artificial Intelligence (cs.AI) #FOS: Biological sciences #FOS: Computer and information sciences #Genomics (q-bio.GN) #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Fine-Tuning of Continuous-Time Diffusion Models as Entropy-Regularized Control
2024/02/23 by Masatoshi Uehara, Uehara, Masatoshi, Yulai Zhao +15 · 20 citations
Computer Science · Mathematics · Physics and Astronomy · #Advanced Mathematical Modeling in Engineering #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Model Reduction and Neural Networks #Numerical methods in inverse problems
- A Review of Off-Policy Evaluation in Reinforcement Learning
2022/12/13 by Masatoshi Uehara, Chengchun Shi, Uehara, Masatoshi +3 · 1 voice · 9 citations
Computer Science · #Reinforcement Learning in Robotics #cs.LG #math.ST #stat.ME #stat.ML
- Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review
2024/07/18 by Masatoshi Uehara, Uehara, Masatoshi, Yulai Zhao +5 · 19 citations
Engineering · #Artificial Intelligence (cs.AI) #FOS: Biological sciences #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Quantitative Methods (q-bio.QM) #Traffic control and management
- Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes
2019/08/22 by Nathan Kallus, Kallus, Nathan, Masatoshi Uehara +1 · 11 citations
Mathematics · Computer Science · Biochemistry, Genetics and Molecular Biology · #Advanced Causal Inference Techniques #Reinforcement Learning in Robotics #Gene Regulatory Network Analysis
- Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Review
2025/01/16 by Masatoshi Uehara, Uehara, Masatoshi, Yulai Zhao +11 · 1 voice · 16 citations
Physics and Astronomy · #Model Reduction and Neural Networks #cs.AI #cs.LG #q-bio.QM #stat.ML
- Minimax Weight and Q-Function Learning for Off-Policy Evaluation
2019/10/28 by Masatoshi Uehara, Uehara, Masatoshi, Jiawei Huang +3 · 6 citations
Computer Science · #Evolutionary Algorithms and Applications #FOS: Computer and information sciences #Formal Methods in Verification #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Reinforcement Learning in Robotics
- Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design
2024/10/17 by Chenyu Wang, Wang, Chenyu, Masatoshi Uehara +17 · 15 citations
Biochemistry, Genetics and Molecular Biology · #DNA and Nucleic Acid Chemistry
- Provable Offline Preference-Based Reinforcement Learning
2023/05/24 by Wenhao Zhan, Zhan, Wenhao, Masatoshi Uehara +7 · 6 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · #Receptor Mechanisms and Signaling #Reinforcement Learning in Robotics #Formal Methods in Verification
- Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage
2021/07/13 by Masatoshi Uehara, Uehara, Masatoshi, W. Sun +1 · 4 citations
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Reinforcement Learning in Robotics
- Feedback Efficient Online Fine-Tuning of Diffusion Models
2024/02/26 by Masatoshi Uehara, Uehara, Masatoshi, Yulai Zhao +15 · 6 citations
Mathematics · Computer Science · Physics and Astronomy · #Numerical methods for differential equations #Matrix Theory and Algorithms #Model Reduction and Neural Networks
- Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models
2024/05/30 by Uehara, Masatoshi, Zhao, Yulai, Hajiramezanali, Ehsan +5 · 7 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Localized Debiased Machine Learning: Efficient Inference on Quantile Treatment Effects and Beyond
2019/12/30 by Nathan Kallus, Xiaojie Mao, Kallus, Nathan +3 · 3 citations
Mathematics · #Advanced Causal Inference Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Methodology (stat.ME) #Statistical Methods and Bayesian Inference #Statistical Methods and Inference
- Dynamic Search for Inference-Time Alignment in Diffusion Models
2025/03/03 by Xiner Li, Masatoshi Uehara, Li, Xiner +13 · 11 citations
Physics and Astronomy · #Model Reduction and Neural Networks
- Efficiently Breaking the Curse of Horizon in Off-Policy Evaluation with Double Reinforcement Learning
2019/09/12 by Kallus, Nathan, Uehara, Masatoshi · 3 citations
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC)
- Provable Reward-Agnostic Preference-Based Reinforcement Learning
2023/05/29 by Wenhao Zhan, Zhan, Wenhao, Masatoshi Uehara +5 · 4 citations
Computer Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Reinforcement Learning in Robotics #Statistics Theory (math.ST)
- Representation Learning for Online and Offline RL in Low-rank MDPs
2021/10/09 by Masatoshi Uehara, Uehara, Masatoshi, Xuezhou Zhang +3 · 3 citations
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Reinforcement Learning in Robotics
- Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems
2022/06/24 by Masatoshi Uehara, Uehara, Masatoshi, Ayush Sekhari +7 · 3 citations
Computer Science · #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Methodology (stat.ME) #Reinforcement Learning in Robotics #Statistics Theory (math.ST)
- PAC Reinforcement Learning for Predictive State Representations
2022/07/12 by Zhan, Wenhao, Uehara, Masatoshi, Sun, Wen +1 · 3 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG)
- Finite Sample Analysis of Minimax Offline Reinforcement Learning: Completeness, Fast Rates and First-Order Efficiency
2021/02/05 by Masatoshi Uehara, Uehara, Masatoshi, Masaaki Imaizumi +9 · 6 citations
Computer Science · #FOS: Computer and information sciences #FOS: Mathematics #Formal Methods in Verification #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Reinforcement Learning in Robotics #Software Reliability and Analysis Research #Statistics Theory (math.ST)
- Inference on Strongly Identified Functionals of Weakly Identified Functions
2022/08/17 by Nathan Kallus, Bennett, Andrew, Xiaojie Mao +5 · 2 citations
Mathematics · #Advanced Causal Inference Techniques #Econometrics (econ.EM) #FOS: Computer and information sciences #FOS: Economics and business #FOS: Mathematics #Machine Learning (stat.ML) #Methodology (stat.ME) #Statistical Methods and Bayesian Inference #Statistical Methods and Inference #Statistics Theory (math.ST)
- A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes
2021/11/12 by Shi, Chengchun, Uehara, Masatoshi, Huang, Jiawei +1 · 2 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Distributional Offline Policy Evaluation with Predictive Error Guarantees
2023/02/19 by Wu, Runzhe, Uehara, Masatoshi, Sun, Wen · 2 citations
#FOS: Computer and information sciences #Machine Learning (cs.LG)
- Adding Conditional Control to Diffusion Models with Reinforcement Learning
2024/06/17 by Zhao, Yulai, Uehara, Masatoshi, Scalia, Gabriele +4 · 3 citations
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Future-Dependent Value-Based Off-Policy Evaluation in POMDPs
2022/07/26 by Masatoshi Uehara, Haruka Kiyohara, Uehara, Masatoshi +13 · 2 citations
Engineering · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Smart Grid Energy Management
- Off-Policy Evaluation and Learning for External Validity under a\n Covariate Shift
2020/02/26 by Masahiro Kato, Masatoshi Uehara, Kato, Masahiro +3 · 7 citations
Mathematics · Engineering · Economics, Econometrics and Finance · #Advanced Causal Inference Techniques #Nuclear reactor physics and engineering #Economic Policies and Impacts
- Generative Adversarial Nets from a Density Ratio Estimation Perspective
2016/10/10 by Uehara, Masatoshi, Sato, Issei, Suzuki, Masahiro +2 · 1 citation
#FOS: Computer and information sciences #Machine Learning (stat.ML)
- Statistically Efficient Off-Policy Policy Gradients
2020/02/10 by Kallus, Nathan, Uehara, Masatoshi · 1 citation
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC)
- Doubly Robust Off-Policy Value and Gradient Estimation for Deterministic Policies
2020/06/06 by Kallus, Nathan, Uehara, Masatoshi · 1 citation
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC)
- Efficient Evaluation of Natural Stochastic Policies in Offline Reinforcement Learning
2020/06/06 by Kallus, Nathan, Uehara, Masatoshi · 1 citation
#FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC)
- Reward-Guided Iterative Refinement in Diffusion Models at Test-Time with Applications to Protein and DNA Design
2025/02/20 by Masatoshi Uehara, Xingyu Su, Uehara, Masatoshi +13 · 1 voice · 3 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Physics and Astronomy · #Gene Regulatory Network Analysis #Generative Adversarial Networks and Image Synthesis #Model Reduction and Neural Networks
- Optimal Off-Policy Evaluation from Multiple Logging Policies
2020/10/21 by Kallus, Nathan, Saito, Yuta, Uehara, Masatoshi · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Methodology (stat.ME)
- Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage
2021/06/06 by Jonathan Chang, Masatoshi Uehara, Chang, Jonathan D. +7 · 3 citations
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Reinforcement Learning in Robotics
- Causal Inference Under Unmeasured Confounding With Negative Controls: A Minimax Learning Approach
2021/03/25 by Nathan Kallus, Xiaojie Mao, Kallus, Nathan +3 · 1 citation
Computer Science · Mathematics · #Advanced Causal Inference Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Methodology (stat.ME) #Statistical Methods and Inference
- Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage
2023/02/05 by Masatoshi Uehara, Uehara, Masatoshi, Nathan Kallus +5 · 2 citations
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #Adversarial Robustness in Machine Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Reinforcement Learning in Robotics
- Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings
2022/06/24 by Uehara, Masatoshi, Sekhari, Ayush, Lee, Jason D. +2 · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Methodology (stat.ME)
- Minimax Instrumental Variable Regression and L2 Convergence Guarantees without Identification or Closedness
2023/02/10 by Andrew F. Bennett, Bennett, Andrew, Nathan Kallus +9 · 1 citation
Computer Science · Mathematics · #Distributed Sensor Networks and Detection Algorithms #Econometrics (econ.EM) #FOS: Computer and information sciences #FOS: Economics and business #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Methodology (stat.ME) #Statistical Methods and Inference #Statistics Theory (math.ST)
- Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning Approach
2022/01/31 by Zhang, Xuezhou, Song, Yuda, Uehara, Masatoshi +3 · 1 citation
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Iterative Distillation for Reward-Guided Fine-Tuning of Diffusion Models in Biomolecular Design
2025/07/01 by Su, Xingyu, Li, Xiner, Uehara, Masatoshi +7 · 5 citations
#Artificial Intelligence (cs.AI) #FOS: Biological sciences #FOS: Computer and information sciences #Machine Learning (cs.LG) #Quantitative Methods (q-bio.QM)
- Fast Rates for the Regret of Offline Reinforcement Learning
2021/01/31 by Yichun Hu, Nathan Kallus, Hu, Yichun +3 · 1 citation
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #Artificial Intelligence (cs.AI) #Distributed Sensor Networks and Detection Algorithms #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC) #Reinforcement Learning in Robotics
- Functional Graphical Models: Structure Enables Offline Data-Driven Optimization
2024/01/08 by Jakub Grudzien Kuba, Kuba, Jakub Grudzien, Masatoshi Uehara +5 · 1 citation
Computer Science · Materials Science · #Artificial Intelligence (cs.AI) #Computational Drug Discovery Methods #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification #Machine Learning in Materials Science