NG
Noah Golowich
cs.LGstat.MLcs.AIcs.DScs.GTmath.OCcs.CRmath.COcs.CCcs.CL
On Valency
published · living versionsW_mrk9pjzv·v1 · currentpublished
ReAPO: Retry-Aware Policy Optimization for Efficient Exploration in LLM Reasoning
with Nghi Dao, Calder Morton-Ferguson, Adam Block
1 version
W_6synj4me·v2published
Preprints & journals
60 papers in the corpus · 2013–2026ReAPO: Retry-Aware Policy Optimization for Efficient Exploration in LLM Reasoning2610.28770v1 · Nghi Dao, Calder Morton-Ferguson, Noah Golowich et al.2026 · 0 citationsarXivon Valency
Normal-Form Correlation in Markov Games2610.03621v1 · Ioannis Anagnostides, Constantinos Daskalakis, Gabriele Farina et al.2026 · 0 citationsarXiv
The Fine-Grained Complexity of Approximate Nash Equilibrium and Free Games2609.07136v2 · Noah Golowich2026 · 0 citationsarXivon Valency
Learning with Simulators: No Regret in a Computationally Bounded World2606.13576v1 · Sasha Voitovych, Abhishek Shetty, Noah Golowich et al.2026 · 0 citationsarXiv
The Power of Test-Time Training for Approximate Sampling2606.11437v1 · Noah Golowich, Ankur Moitra, Dhruv Rohatgi2026 · 0 citationsarXiv
On the Complexity of Correlated Equilibria Beyond Normal-Form Games2605.17665v1 · Ioannis Anagnostides, Constantinos Daskalakis, Gabriele Farina et al.2026 · 0 citationsarXiv
Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference2603.07887v1 · Noah Golowich, Fan Chen, Dhruv Rohatgi et al.2026 · 0 citationsarXiv
Subliminal Effects in Your Data: A General Mechanism via Log-Linearity2602.04863v1 · Ishaq Aden-Ali, Noah Golowich, Allen Liu et al.2026 · 0 citationsarXiv
Provably Learning from Modern Language Models via Low Logit Rank2512.09892v1 · Noah Golowich, Allen Liu, Abhishek Shetty2025 · 0 citationsarXiv
Improved Pseudorandom Codes from Permuted Puzzles2512.08918v2 · Miranda Christ, Noah Golowich, Sam Gunn et al.2025 · 1 citationarXiv
Sequences of Logits Reveal the Low Rank Structure of Language Models2510.24966v1 · Noah Golowich, Allen Liu, Abhishek Shetty2025 · 0 citationsarXiv
The Coverage Principle: How Pre-Training Enables Post-Training2510.15020v2 · Fan Chen, Audrey Huang, Noah Golowich et al.2025 · 0 citationsarXiv
The Hidden Game Problem2510.03845v1 · Gon Buzaglo, Noah Golowich, Elad Hazan2025 · 0 citationsarXiv
High-Dimensional Calibration from Swap Regret2505.21460v2 · Maxwell Fishelson, Noah Golowich, Mehryar Mohri et al.2025 · 0 citationsarXiv
The Role of Sparsity for Length Generalization in Transformers2502.16792v1 · Noah Golowich, Samy Jelassi, David Brandfonbrener et al.2025 · 0 citationsarXiv
A Lower Bound on Swap Regret in Extensive-Form Games2406.13116v1 · Constantinos Daskalakis, Gabriele Farina, Noah Golowich et al.2024 · 1 citationarXiv
Breaking the Barrier for Sequential Calibration2406.13668v4 · Yuval Dagan, Constantinos Daskalakis, Maxwell Fishelson et al.2024 · 0 citationsarXiv
Linear Bellman Completeness Suffices for Efficient Online Reinforcement Learning with Few Actions2406.11640v2 · Noah Golowich, Ankur Moitra2024 · 0 citationsarXiv
Is Efficient PAC Learning Possible with an Oracle That Responds 'Yes' or 'No'?2406.11667v3 · Constantinos Daskalakis, Noah Golowich2024 · 0 citationsarXiv
The Role of Inherent Bellman Error in Offline Reinforcement Learning with Linear Function Approximation2406.11686v2 · Noah Golowich, Ankur Moitra2024 · 0 citationsarXiv
Near-Optimal Learning and Planning in Separated Latent MDPs2406.07920v1 · Fan Chen, Constantinos Daskalakis, Noah Golowich et al.2024 · 0 citationsarXiv
Edit Distance Robust Watermarks via Indexing Pseudorandom Codes2406.02633v2 · Noah Golowich, Ankur Moitra2024 · 4 citationsarXiv
Online Control in Population Dynamics2406.01799v2 · Noah Golowich, Elad Hazan, Zhou Lu et al.2024 · 0 citationsarXiv
On Learning Parities with Dependent Noise2404.11325v1 · Noah Golowich, Ankur Moitra, Dhruv Rohatgi2024 · 0 citationsarXiv
Exploration is Harder than Prediction: Cryptographically Separating Reinforcement Learning from Supervised Learning2404.03774v1 · Noah Golowich, Ankur Moitra, Dhruv Rohatgi2024 · 0 citationsarXiv
From External to Swap Regret 2.0: An Efficient Reduction and Oblivious Adversary for Large Action Spaces2310.19786v4 · Yuval Dagan, Constantinos Daskalakis, Maxwell Fishelson et al.2023 · 2 citationsarXiv
Smooth Nash Equilibria: Algorithms and Complexity2309.12226v2 · Constantinos Daskalakis, Noah Golowich, Nika Haghtalab et al.2023 · 0 citationsarXiv
Exploring and Learning in Sparse Linear MDPs without Computationally Intractable Oracles2309.09457v2 · Noah Golowich, Ankur Moitra, Dhruv Rohatgi2023 · 3 citationsarXiv
On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring2305.00684v1 · Dylan J. Foster, Dean P. Foster, Noah Golowich et al.2023 · 3 citationsarXiv
Hardness of Independent Learning and Sparse Equilibrium Computation in Markov Games2303.12287v1 · Dylan J. Foster, Noah Golowich, Sham M. Kakade2023 · 0 citationsarXiv
Tight Guarantees for Interactive Decision Making with the Decision-Estimation Coefficient2301.08215v1 · Dylan J. Foster, Noah Golowich, Yanjun Han2023 · 2 citationsarXiv
Model-Free Reinforcement Learning with the Decision-Estimation Coefficient2211.14250v2 · Dylan J. Foster, Noah Golowich, Jian Qian et al.2022 · 4 citationsarXiv
STay-ON-the-Ridge: Guaranteed Convergence to Local Minimax Equilibrium in Nonconvex-Nonconcave Games2210.09769v1 · Constantinos Daskalakis, Noah Golowich, Stratis Skoulakis et al.2022 · 1 citationarXiv
Learning in Observable POMDPs, without Computationally Intractable Oracles2206.03446v1 · Noah Golowich, Ankur Moitra, Dhruv Rohatgi2022 · 7 citationsarXiv
Smoothed Online Learning is as Easy as Statistical Learning2202.04690v3 · Adam Block, Yuval Dagan, Noah Golowich et al.2022 · 3 citationsarXiv
Planning in Observable POMDPs in Quasipolynomial Time2201.04735v2 · Noah Golowich, Ankur Moitra, Dhruv Rohatgi2022 · 4 citationsarXiv
Differentially Private Nonparametric Regression Under a Growth Condition2111.12786v1 · Noah Golowich2021 · 1 citationarXiv
Fast Rates for Nonparametric Online Learning: From Realizability to Learning in Games2111.08911v2 · Constantinos Daskalakis, Noah Golowich2021 · 9 citationsarXiv
Near-Optimal No-Regret Learning for Correlated Equilibria in Multi-Player General-Sum Games2111.06008v3 · Ioannis Anagnostides, Constantinos Daskalakis, Gabriele Farina et al.2021 · 17 citationsarXiv
Can Q-Learning be Improved with Advice?2110.13052v1 · Noah Golowich, Ankur Moitra2021 · 3 citationsarXiv
Near-Optimal No-Regret Learning in General Games2108.06924v2 · Constantinos Daskalakis, Maxwell Fishelson, Noah Golowich2021 · 14 citationsarXiv
Littlestone Classes are Privately Online Learnable2106.13513v1 · Noah Golowich, Roi Livni2021 · 0 citationsarXiv
Deep Learning with Label Differential Privacy2102.06062v2 · Badih Ghazi, Noah Golowich, Ravi Kumar et al.2021 · 47 citationsarXiv
Independent Policy Gradient Methods for Competitive Reinforcement Learning2101.04233v1 · Constantinos Daskalakis, Dylan J. Foster, Noah Golowich2021 · 42 citationsarXiv
Sample-efficient proper PAC learning with approximate differential privacy2012.03893v1 · Badih Ghazi, Noah Golowich, Ravi Kumar et al.2020 · 11 citationsarXiv
Tight last-iterate convergence rates for no-regret learning in multi-player games2010.13724v1 · Noah Golowich, Sarath Pattathil, Constantinos Daskalakis2020 · 17 citationsarXiv
Near-tight closure bounds for Littlestone and threshold dimensions2007.03668v1 · Badih Ghazi, Noah Golowich, Ravi Kumar et al.2020 · 3 citationsarXiv
Pure Differentially Private Summation from Anonymous Messages2002.01919v1 · Badih Ghazi, Noah Golowich, Ravi Kumar et al.2020 · 26 citationsarXiv
Last Iterate is Slower than Averaged Iterate in Smooth Convex-Concave Saddle Point Problems2002.00057v2 · Noah Golowich, Sarath Pattathil, Constantinos Daskalakis et al.2020 · 29 citationsarXiv
Round Complexity of Common Randomness Generation: The Amortized Setting1909.00323v1 · Noah Golowich, Madhu Sudan2019 · 3 citationsarXiv
Career total: 75 works. 60 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.