104 citations · 270 across the 46 of their papers we have counts for
8 papers · 1 filter
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…