104 citations · 270 across the 46 of their papers we have counts for
54 papers
ReAPO: Retry-Aware Policy Optimization for Efficient Exploration in LLM Reasoning
Nghi Dao, Calder Morton-Ferguson, Noah Golowich +1
RLVR improves language-model reasoning, but commonly relies on independent stochastic rollouts for exploration, which can repeatedly sample similar failed strategies. Prior work ha…
Normal-Form Correlation in Markov Games
Ioannis Anagnostides, Constantinos Daskalakis, Gabriele Farina +3
There has been a surge of recent work on correlated equilibrium concepts in Markov games. However, existing results focus on concepts weaker than normal-form correlated equilibria…
The Fine-Grained Complexity of Approximate Nash Equilibrium and Free Games
Noah Golowich
We study the fine-grained complexity of computing approximate Nash equilibria and approximating the value of free games in the regime where the approximation error vanishes. Under…
Learning with Simulators: No Regret in a Computationally Bounded World
Sasha Voitovych, Abhishek Shetty, Noah Golowich +1
Understanding the minimal assumptions necessary for generalization is the fundamental question in learning theory. Unfortunately, most results rely heavily on independence (or some…
The Power of Test-Time Training for Approximate Sampling
Noah Golowich, Ankur Moitra, Dhruv Rohatgi
Efficiently sampling from a complex probability distribution is a fundamental problem which has become increasingly pertinent in recent years with the rise of generative AI, as sop…
On the Complexity of Correlated Equilibria Beyond Normal-Form Games
Ioannis Anagnostides, Constantinos Daskalakis, Gabriele Farina +3
Correlated equilibria are a fundamental solution concept in game theory. However, despite decades of research, the complexity beyond games of polynomial type -- such as extensive-f…
Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference
Noah Golowich, Fan Chen, Dhruv Rohatgi +4
Inference-time methods that aggregate and prune multiple samples have emerged as a powerful paradigm for steering large language models, yet we lack any principled understanding of…
Subliminal Effects in Your Data: A General Mechanism via Log-Linearity
Ishaq Aden-Ali, Noah Golowich, Allen Liu +3
Training modern large language models (LLMs) has become a veritable smorgasbord of algorithms and datasets designed to elicit particular behaviors, making it critical to develop te…
Provably Learning from Modern Language Models via Low Logit Rank
Noah Golowich, Allen Liu, Abhishek Shetty
While modern language models and their inner workings are incredibly complex, recent work (Golowich, Liu & Shetty; 2025) has proposed a simple and potentially tractable abstraction…
Improved Pseudorandom Codes from Permuted Puzzles
Miranda Christ, Noah Golowich, Sam Gunn +2
Watermarks are an essential tool for identifying AI-generated content. Recently, Christ and Gunn (CRYPTO '24) introduced pseudorandom error-correcting codes (PRCs), which are equiv…
Sequences of Logits Reveal the Low Rank Structure of Language Models
Noah Golowich, Allen Liu, Abhishek Shetty
A major problem in the study of large language models is to understand their inherent low-dimensional structure. We introduce an approach to study the low-dimensional structure of…
The Coverage Principle: How Pre-Training Enables Post-Training
Fan Chen, Audrey Huang, Noah Golowich +5
Language models demonstrate remarkable abilities when pre-trained on large text corpora and fine-tuned for specific tasks, but how and why pre-training shapes the success of the fi…
The Hidden Game Problem
Gon Buzaglo, Noah Golowich, Elad Hazan
This paper investigates a class of games with large strategy spaces, motivated by challenges in AI alignment and language games. We introduce the hidden game problem, where for eac…
High-Dimensional Calibration from Swap Regret
Maxwell Fishelson, Noah Golowich, Mehryar Mohri +1
We study online calibration of multi-dimensional forecasts over an arbitrary convex set relative to an arbitrary norm . We connect this to externa…
The Role of Sparsity for Length Generalization in Transformers
Noah Golowich, Samy Jelassi, David Brandfonbrener +2
Training large language models to predict beyond their training context lengths has drawn much attention in recent years, yet the principles driving such behavior of length general…
A Lower Bound on Swap Regret in Extensive-Form Games
Constantinos Daskalakis, Gabriele Farina, Noah Golowich +2
Recent simultaneous works by Peng and Rubinstein [2024] and Dagan et al. [2024] have demonstrated the existence of a no-swap-regret learning algorithm that can reach average sw…
The Role of Inherent Bellman Error in Offline Reinforcement Learning with Linear Function Approximation
Noah Golowich, Ankur Moitra
In this paper, we study the offline RL problem with linear function approximation. Our main structural assumption is that the MDP has low inherent Bellman error, which stipulates t…
Linear Bellman Completeness Suffices for Efficient Online Reinforcement Learning with Few Actions
Noah Golowich, Ankur Moitra
One of the most natural approaches to reinforcement learning (RL) with function approximation is value iteration, which inductively generates approximations to the optimal value fu…
Near-Optimal Learning and Planning in Separated Latent MDPs
Fan Chen, Constantinos Daskalakis, Noah Golowich +1
We study computational and statistical aspects of learning Latent Markov Decision Processes (LMDPs). In this model, the learner interacts with an MDP drawn at the beginning of each…
Online Control in Population Dynamics
Noah Golowich, Elad Hazan, Zhou Lu +2
The study of population dynamics originated with early sociological works but has since extended into many fields, including biology, epidemiology, evolutionary game theory, and ec…
Breaking the Barrier for Sequential Calibration
Yuval Dagan, Constantinos Daskalakis, Maxwell Fishelson +3
A set of probabilistic forecasts is calibrated if each prediction of the forecaster closely approximates the empirical distribution of outcomes on the subset of timesteps where tha…
Is Efficient PAC Learning Possible with an Oracle That Responds 'Yes' or 'No'?
Constantinos Daskalakis, Noah Golowich
The empirical risk minimization (ERM) principle has been highly impactful in machine learning, leading both to near-optimal theoretical guarantees for ERM-based learning algorithms…
Edit Distance Robust Watermarks via Indexing Pseudorandom Codes
Noah Golowich, Ankur Moitra
Motivated by the problem of detecting AI-generated text, we consider the problem of watermarking the output of language models with provable guarantees. We aim for watermarks which…
On Learning Parities with Dependent Noise
Noah Golowich, Ankur Moitra, Dhruv Rohatgi
In this expository note we show that the learning parities with noise (LPN) assumption is robust to weak dependencies in the noise distribution of small batches of samples. This pr…