MW
Martin Wainwright
stat.MLmath.STstat.THcs.LGcs.ITmath.ITstat.MEmath.OCcs.AIstat.CO
On Valency
published · living versionsW_azdgxx9g·v1 · currentpublished
When is it Better to Compare than to Score?
with Nihar B. Shah, Sivaraman Balakrishnan, Joseph Bradley, Abhay Parekh +1
1 version
Preprints & journals
178 papers in the corpus · 1997–2026Exploiting Exogenous Structure for Sample-Efficient Reinforcement Learning2409.14557v5 · Jia Wan, Sean R. Sinclair, Devavrat Shah et al.2024 · 0 citationsarXiv
The information geometry of product-reference discrete diffusion: Interaction growth complexity and optimal scheduling2608.28949v1 · Martin J. Wainwright2026 · 0 citationsarXiv
Buying Data of Unknown Quality: Statistical Information Procurement Auctions2604.08821v2 · Yuchen Hu, Martin J. Wainwright, Stephen Bates2026 · 0 citationsarXiv
The data geometry of masking diffusion: Certified-optimal schedules via unmasking growth complexity2608.13520v1 · Martin J. Wainwright2026 · 0 citationsarXiv
Denoising growth complexity: Data geometry and certified schedules for diffusion sampling2607.26285v1 · Martin J. Wainwright2026 · 0 citationsarXiv
Information-theoretic lower bounds on the oracle complexity of stochastic convex optimization1009.0571v3 · Alekh Agarwal, Peter L. Bartlett, Pradeep Ravikumar et al.2010 · 243 citationsarXiv
TILT: Target-induced loss tilting under covariate shift2605.14280v1 · Kakei Yamamoto, Martin J. Wainwright2026 · 0 citationsarXiv
Residual-as-Teacher: Mitigating Bias Propagation in Student--Teacher Estimation2603.25466v1 · Kakei Yamamoto, Martin J. Wainwright2026 · 0 citationsarXiv
Instance-Adaptive Hypothesis Tests with Heterogeneous Agents2510.21178v1 · Flora C. Shi, Martin J. Wainwright, Stephen Bates2025 · 0 citationsarXiv
Inference under Staggered Adoption: Case Study of the Affordable Care Act2412.09482v2 · Eric Xia, Yuling Yan, Martin J. Wainwright2024 · 0 citationsarXiv
Finite-Sample Guarantees for Learning Dynamics in Zero-Sum Polymatrix Games2407.20128v3 · Fathima Zarin Faizal, Asuman Ozdaglar, Martin J. Wainwright2024 · 0 citationsarXiv
Wild refitting for black box prediction2506.21460v2 · Martin J. Wainwright2025 · 0 citationsarXiv
QuTE: decentralized multiple testing on sensor networks with false discovery rate control2210.04334v2 · Aaditya Ramdas, Jianbo Chen, Martin J. Wainwright et al.2022 · 7 citationsarXiv
Semi-parametric inference based on adaptively collected data2303.02534v2 · Licong Lin, Koulik Khamaru, Martin J. Wainwright2023 · 0 citationsarXiv
Sharp Results for Hypothesis Testing with Risk-Sensitive Agents2412.16452v1 · Flora C. Shi, Stephen Bates, Martin J. Wainwright2024 · 0 citationsarXiv
Prediction Aided by Surrogate Training2412.09364v1 · Eric Xia, Martin J. Wainwright2024 · 0 citationsarXiv
When is it worthwhile to jackknife? Breaking the quadratic barrier for Z-estimators2411.02909v1 · Licong Lin, Fangzhou Su, Wenlong Mou et al.2024 · 0 citationsarXiv
Instrumental variables: A non-asymptotic viewpoint2410.02015v1 · Eric Xia, Martin J. Wainwright, Whitney Newey2024 · 0 citationsarXiv
ROOT-SGD: Sharp Nonasymptotics and Near-Optimal Asymptotics in a Single Algorithm2008.12690v4 · Chris Junchi Li, Wenlong Mou, Martin J. Wainwright et al.2020 · 0 citationspublished at COLT 2022
Entrywise Inference for Missing Panel Data: A Simple and Instance-Optimal Approach2401.13665v2 · Yuling Yan, Martin J. Wainwright2024 · 2 citationsarXiv
Optimal and instance-dependent guarantees for Markovian linear stochastic approximation2112.12770v2 · Wenlong Mou, Ashwin Pananjady, Martin J. Wainwright et al.2021 · 6 citationsarXiv
Taming "data-hungry" reinforcement learning? Stability in continuous state-action spaces2401.05233v1 · Yaqi Duan, Martin J. Wainwright2024 · 1 citationarXiv
A decorrelation method for general regression adjustment in randomized experiments2311.10076v1 · Fangzhou Su, Wenlong Mou, Peng Ding et al.2023 · 0 citationsarXiv
Revisiting minimum description length complexity in overparameterized models2006.10189v4 · Raaz Dwivedi, Chandan Singh, Bin Yu et al.2020 · 3 citationsarXiv
Doubly High-Dimensional Contextual Bandits: An Interpretable Model for Joint Assortment-Pricing2309.08634v1 · Junhui Cai, Ran Chen, Martin J. Wainwright et al.2023 · 3 citationsarXiv
Challenges of the inconsistency regime: Novel debiasing methods for missing data models2309.01362v1 · Michael Celentano, Martin J. Wainwright2023 · 1 citationarXiv
Optimally tackling covariate shift in RKHS-based nonparametric regression2205.02986v2 · Cong Ma, Reese Pathak, Martin J. Wainwright2022 · 21 citationsarXiv
When is the estimated propensity score better? High-dimensional analysis and bias correction2303.17102v1 · Fangzhou Su, Wenlong Mou, Peng Ding et al.2023 · 0 citationsarXiv
Krylov-Bellman boosting: Super-linear policy evaluation in general state spaces2210.11377v1 · Eric Xia, Martin J. Wainwright2022 · 1 citationarXiv
Near-optimal inference in adaptive linear regression2107.02266v3 · Koulik Khamaru, Yash Deshpande, Tor Lattimore et al.2021 · 5 citationsarXiv
Noisy recovery from random linear observations: Sharp minimax rates under elliptical constraints2303.12613v1 · Reese Pathak, Martin J. Wainwright, Lin Xiao2023 · 2 citationsarXiv
Kernel-based off-policy estimation without overlap: Instance optimality beyond semiparametric efficiency2301.06240v1 · Wenlong Mou, Peng Ding, Martin J. Wainwright et al.2023 · 0 citationsarXiv
Optimal variance-reduced stochastic approximation in Banach spaces2201.08518v2 · Wenlong Mou, Koulik Khamaru, Martin J. Wainwright et al.2022 · 2 citationsarXiv
Policy evaluation from a single path: Multi-step methods, mixing and mis-specification2211.03899v1 · Yaqi Duan, Martin J. Wainwright2022 · 1 citationarXiv
Bellman Residual Orthogonalization for Offline Reinforcement Learning2203.12786v3 · Andrea Zanette, Martin J. Wainwright2022 · 0 citationsarXiv
Off-policy estimation of linear functionals: Non-asymptotic theory for semi-parametric efficiency2209.13075v1 · Wenlong Mou, Martin J. Wainwright, Peter L. Bartlett2022 · 0 citationsarXiv
A Diffusion Process Perspective on Posterior Contraction Rates for Parameters1909.00966v2 · Wenlong Mou, Nhat Ho, Martin J. Wainwright et al.2019 · 5 citationsarXiv
Stabilizing Q-learning with Linear Architectures for Provably Efficient Learning2206.00796v1 · Andrea Zanette, Martin J. Wainwright2022 · 0 citationsarXiv
Instability, Computational Efficiency and Statistical Accuracy2005.11411v2 · Nhat Ho, Koulik Khamaru, Raaz Dwivedi et al.2020 · 8 citationsarXiv
A new similarity measure for covariate shift with applications to nonparametric regression2202.02837v1 · Reese Pathak, Cong Ma, Martin J. Wainwright2022 · 6 citationsarXiv
Instance-Dependent Confidence and Early Stopping for Reinforcement Learning2201.08536v1 · Koulik Khamaru, Eric Xia, Martin J. Wainwright et al.2022 · 1 citationarXiv
Sharp Analysis of Expectation-Maximization for Weakly Identifiable Models1902.00194v4 · Raaz Dwivedi, Nhat Ho, Koulik Khamaru et al.2019 · 13 citationsarXiv
Optimal policy evaluation using kernel-based temporal difference methods2109.12002v1 · Yaqi Duan, Mengdi Wang, Martin J. Wainwright2021 · 6 citationsarXiv
Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning2108.08812v1 · Andrea Zanette, Martin J. Wainwright, Emma Brunskill2021 · 15 citationsarXiv
Instance-optimality in optimal value estimation: Adaptivity via variance-reduced Q-learning2106.14352v1 · Koulik Khamaru, Eric Xia, Martin J. Wainwright et al.2021 · 3 citationsarXiv
Preference learning along multiple criteria: A game-theoretic perspective2105.01850v1 · Kush Bhatia, Ashwin Pananjady, Peter L. Bartlett et al.2021 · 3 citationsarXiv
Minimax Off-Policy Evaluation for Multi-Armed Bandits2101.07781v1 · Cong Ma, Banghua Zhu, Jiantao Jiao et al.2021 · 4 citationsarXiv
A Permutation-based Model for Crowd Labeling: Optimal Estimation and Robustness1606.09632v3 · Nihar B. Shah, Sivaraman Balakrishnan, Martin J. Wainwright2016 · 45 citationsarXiv
Fast mixing of Metropolized Hamiltonian Monte Carlo: Benefits of multi-step gradients1905.12247v3 · Yuansi Chen, Raaz Dwivedi, Martin J. Wainwright et al.2019 · 32 citationsarXiv
Optimal oracle inequalities for solving projected fixed-point equations2012.05299v1 · Wenlong Mou, Ashwin Pananjady, Martin J. Wainwright2020 · 2 citationsarXiv
Career total: 434 works. 178 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.