5 papers
What Fits (Into Few Tokens) Doesn't Overfit: Compression and Generalization in ML Research Agents
Martin Andres Bertran, Aaron Roth, Zhiwei Steven Wu
Reusing a held-out benchmark adaptively should, in principle, invite overfitting. Yet benchmark-driven machine learning (ML) has produced surprisingly little overfitting in practic…
Replicable Reinforcement Learning with Linear Function Approximation
Eric Eaton, Marcel Hussing, Michael Kearns +3
Replication of experimental results has been a challenge faced by many scientific disciplines, including the field of machine learning. Recent work on the theory of machine learnin…
Networked Information Aggregation via Machine Learning
Michael Kearns, Aaron Roth, Emily Ryu
We study a distributed learning problem in which learning agents are embedded in a directed acyclic graph (DAG). There is a fixed and arbitrary distribution over feature/label pair…
Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval-Augmented Generation
Tobias Leemann, Periklis Petridis, Giuseppe Vietri +3
While retrieval-augmented generation (RAG) has been shown to enhance factuality of large language model (LLM) outputs, LLMs still suffer from hallucination, generating incorrect or…
Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces
Eric Eaton, Marcel Hussing, Michael Kearns +3
In traditional reinforcement learning (RL), the learner aims to solve a single objective optimization problem: find the policy that maximizes expected reward. However, in many real…