KJ
Kevin Jamieson
cs.LGstat.MLcs.AIcs.GTcs.ROcs.CLcs.ITcs.SYeess.SYmath.IT
On Valency
published · living versionsW_u7fa5rax·v1 · currentpublished
MLSys: The New Frontier of Machine Learning Systems
with Alexander Ratner, Dan Alistarh, Gustavo Alonso, David G. Andersen +64
1 version
Preprints & journals
85 papers in the corpus · 2011–2026Efficient Uncoupled Learning Dynamics with $\tilde{O}\!\left(T^{-1/4}\right)$ Last-Iterate Convergence in Bilinear Saddle-Point Problems over Convex Sets under Bandit Feedback2602.21436v2 · Arnab Maiti, Claire Jie Zhang, Kevin Jamieson et al.2026 · 0 citationsarXiv
Minimax Optimal Strategy for Delayed Observations in Online Reinforcement Learning2603.03480v2 · Harin Lee, Kevin Jamieson2026 · 0 citationsarXiv
Revisiting the Bertrand Paradox via Equilibrium Analysis of No-regret Learners2602.21620v2 · Arnab Maiti, Junyan Liu, Kevin Jamieson et al.2026 · 0 citationsarXiv
Batched Stochastic Linear Bandits with 1-Bit Communication Constraints2605.30976v1 · Ivan Lau, Daniel McMorrow, Kevin Jamieson et al.2026 · 0 citationsarXiv
Near-Optimal Regret in Adversarial Kernel Bandits2605.26585v1 · Yu-Jie Zhang, Hao Qiu, Jonathan Scarlett et al.2026 · 0 citationsarXiv
On the Power of Adaptivity for $\varepsilon$-Best Arm Identification in Linear Bandits2605.15663v1 · Arnab Maiti, Yunbei Xu, Kevin Jamieson2026 · 0 citationsarXiv
Optimal Posterior Sampling for Policy Identification in Tabular Markov Decision Processes2605.03921v1 · Cyrille Kone, Kevin Jamieson2026 · 0 citationsarXiv
On The Complexity of Best-Arm Identification in Non-Stationary Linear Bandits2603.10346v1 · Leo Maynard-Zhang, Zhihan Xiong, Kevin Jamieson et al.2026 · 0 citationsarXiv
High Effort, Low Gain: Fundamental Limits of Active Learning for Linear Dynamical Systems2509.11907v2 · Nicolas Chatzikiriakos, Kevin Jamieson, Andrea Iannelli2025 · 0 citationsarXiv
Improved Regret Bounds for Linear Bandits with Heavy-Tailed Rewards2506.04775v3 · Artin Tajdini, Jonathan Scarlett, Kevin Jamieson2025 · 0 citationsarXiv
Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback2510.17103v2 · Shinji Ito, Kevin Jamieson, Haipeng Luo et al.2025 · 0 citationsarXiv
On the Universal Near Optimality of Hedge in Combinatorial Settings2510.17099v2 · Zhiyuan Fan, Arnab Maiti, Kevin Jamieson et al.2025 · 1 citationarXiv
Active learning of neural population dynamics using two-photon holographic optogenetics.39679275 · Wagenmaker, Andrew, Mi, Lu, Rozsa, Marton et al.2025 · 1 citationArXiv. 2025
Learning to Incentivize in Repeated Principal-Agent Problems with Adversarial Agent Arrivals2505.23124v2 · Junyan Liu, Arnab Maiti, Artin Tajdini et al.2025 · 0 citationsarXiv
On the Limitations and Possibilities of Nash Regret Minimization in Zero-Sum Matrix Games under Noisy Feedback2306.13233v3 · Arnab Maiti, Kevin Jamieson, Lillian J. Ratliff2023 · 0 citationsarXiv
Active learning of neural population dynamics using two-photon holographic optogenetics2412.02529v4 · Andrew Wagenmaker, Lu Mi, Marton Rozsa et al.2024 · 2 citationsarXiv
Stow: Robotic Packing of Items into Fabric Pods2505.04572v1 · Nicolas Hudson, Josh Hooks, Rahul Warrier et al.2025 · 0 citationsarXiv
Efficient Near-Optimal Algorithm for Online Shortest Paths in Directed Acyclic Graphs with Bandit Feedback Against Adaptive Adversaries2504.00461v1 · Arnab Maiti, Zhiyuan Fan, Kevin Jamieson et al.2025 · 0 citationsarXiv
CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning2405.19547v2 · Yiping Wang, Yifang Chen, Wendan Yan et al.2024 · 4 citationsarXiv
Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning2406.10522v2 · Jifan Zhang, Lalit Jain, Yang Guo et al.2024 · 2 citationsarXiv
Nearly Minimax Optimal Submodular Maximization with Bandit Feedback2310.18465v2 · Artin Tajdini, Lalit Jain, Kevin Jamieson2023 · 0 citationsarXiv
Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL2410.20254v1 · Andrew Wagenmaker, Kevin Huang, Liyiming Ke et al.2024 · 11 citationsarXiv
Query-Efficient Algorithm to Find all Nash Equilibria in a Two-Player Zero-Sum Matrix Game2310.16236v3 · Arnab Maiti, Ross Boczar, Kevin Jamieson et al.2023 · 0 citationsarXiv
Cost-Effective Proxy Reward Model Construction with On-Policy and Active Learning2407.02119v2 · Yifang Chen, Shuohang Wang, Ziyi Yang et al.2024 · 0 citationsarXiv
An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models2401.06692v3 · Gantavya Bhatt, Yifang Chen, Arnav M. Das et al.2024 · 7 citationsarXiv
Sample Complexity Reduction via Policy Difference Estimation in Tabular Reinforcement Learning2406.06856v1 · Adhyyan Narang, Andrew Wagenmaker, Lillian Ratliff et al.2024 · 0 citationsarXiv
LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient Learning2306.09910v4 · Jifan Zhang, Yifang Chen, Gregory Canal et al.2023 · 1 citationarXiv
A/B Testing and Best-arm Identification for Linear Bandits with Robustness to Non-stationarity2307.15154v2 · Zhihan Xiong, Romain Camilleri, Maryam Fazel et al.2023 · 0 citationsarXiv
Variance Alignment Score: A Simple But Tough-to-Beat Data Selection Method for Multimodal Contrastive Learning2402.02055v1 · Yiping Wang, Yifang Chen, Wendan Yan et al.2024 · 0 citationsarXiv
Fair Active Learning in Low-Data Regimes2312.08559v1 · Romain Camilleri, Andrew Wagenmaker, Jamie Morgenstern et al.2023 · 0 citationsarXiv
Near-Optimal Pure Exploration in Matrix Games: A Generalization of Stochastic Bandits & Dueling Bandits2310.16252v2 · Arnab Maiti, Ross Boczar, Kevin Jamieson et al.2023 · 0 citationsarXiv
Optimal Exploration is no harder than Thompson Sampling2310.06069v2 · Zhaoqi Li, Kevin Jamieson, Lalit Jain2023 · 2 citationsarXiv
Pick Planning Strategies for Large-Scale Package Manipulation2309.13224v2 · Shuai Li, Azarakhsh Keipour, Kevin Jamieson et al.2023 · 0 citationsarXiv
Instance-optimal PAC Algorithms for Contextual Bandits2207.02357v1 · Zhaoqi Li, Lillian Ratliff, Houssam Nassif et al.2022 · 3 citationsConference on Neural Information Processing Systems (NeurIPS'22), New Orleans, pp. 37590-37603, 2022
Instance-Dependent Near-Optimal Policy Identification in Linear MDPs via Online Experiment Design2207.02575v2 · Andrew Wagenmaker, Kevin Jamieson2022 · 6 citationsarXiv
Demonstrating Large-Scale Package Manipulation via Learned Metrics of Pick Success2305.10272v2 · Shuai Li, Azarakhsh Keipour, Kevin Jamieson et al.2023 · 6 citationsarXiv
Active Representation Learning for General Task Space with Applications in Robotics2306.08942v1 · Yifang Chen, Yingbing Huang, Simon S. Du et al.2023 · 0 citationsarXiv
Optimal Exploration for Model-Based RL in Nonlinear Systems2306.09210v1 · Andrew Wagenmaker, Guanya Shi, Kevin Jamieson2023 · 1 citationarXiv
Improved Active Multi-Task Representation Learning via Lasso2306.02556v1 · Yiping Wang, Yifang Chen, Kevin Jamieson et al.2023 · 0 citationsarXiv
The Simulator: Understanding Adaptive Sampling in the Moderate-Confidence Regime1702.05186v2 · Max Simchowitz, Kevin Jamieson, Benjamin Recht2017 · 16 citationsarXiv
Instance-dependent Sample Complexity Bounds for Zero-sum Matrix Games2303.10565v1 · Arnab Maiti, Kevin Jamieson, Lillian J. Ratliff2023 · 0 citationsarXiv
First-Order Regret in Reinforcement Learning with Linear Function Approximation: A Robust Estimation Approach2112.03432v4 · Andrew Wagenmaker, Yifang Chen, Max Simchowitz et al.2021 · 3 citationsarXiv
Sample-efficient identification of high-dimensional antibiotic synergy with a normalized diagonal sampling design.35849634 · Brennan, Jennifer, Jain, Lalit, Garman, Sofia et al.2022 · 2 citationsPLoS computational biology. 2022;18(7):e1010311
Beyond No Regret: Instance-Dependent PAC Reinforcement Learning2108.02717v2 · Andrew Wagenmaker, Max Simchowitz, Kevin Jamieson2021 · 4 citationsarXiv
Active Learning with Safety Constraints2206.11183v1 · Romain Camilleri, Andrew Wagenmaker, Jamie Morgenstern et al.2022 · 2 citationsarXiv
Reward-Free RL is No Harder Than Reward-Aware RL in Linear Markov Decision Processes2201.11206v2 · Andrew Wagenmaker, Yifang Chen, Max Simchowitz et al.2022 · 5 citationsarXiv
Active Multi-Task Representation Learning2202.00911v1 · Yifang Chen, Simon S. Du, Kevin Jamieson2022 · 1 citationarXiv
Best Arm Identification with Safety Constraints2111.12151v1 · Zhenlin Wang, Andrew Wagenmaker, Kevin Jamieson2021 · 2 citationsarXiv
Practical, Provably-Correct Interactive Learning in the Realizable Setting: The Power of True Believers2111.04915v1 · Julian Katz-Samuels, Blake Mason, Kevin Jamieson et al.2021 · 0 citationsarXiv
Selective Sampling for Online Best-arm Identification2110.14864v2 · Romain Camilleri, Zhihan Xiong, Maryam Fazel et al.2021 · 1 citationarXiv
Career total: 127 works. 85 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.