arXiv Machine Learning

Computationally Efficient Collaborative Communication Via Regularity-Based Coarsening

arXiv:2608. 05327v1 Announce Type: cross Abstract: Our results show that the existence of a short high-utility protocol already suffices for efficient communication.

Hugging Face Trending Papers
Aug 5

Computationally Efficient Collaborative Communication Via Regularity-Based Coarsening

Our results show that the existence of a short high-utility protocol already suffices for efficient communication. In particular, in a game with $n$ possible observations and $m$ actions: (1) For any achievable target utility $α$, we give an algorithm with $\mathrm{poly}(n, m, 1/ε)$ runtime that designs a protocol achieving utility at least $α-ε$ using only $2^{\mathcal O(CC_α(G))}/ε^2$ bits of communication.

arXiv Machine Learning
Jul 17

PAC Learning in Turn-Based Stochastic Games with Reachability Objectives: A Decentralized Private Approach via Expected Conditional Distance

arXiv:2607. 14877v1 Announce Type: new Abstract: Reachability is the most fundamental logical objective, yet it is notoriously difficult to learn in reinforcement learning settings: even for Markov decision processes, PAC learning of reachability is impossible without additional assumptions.

By Ali Asadi, Krishnendu Chatterjee, Pavol Kebis
arXiv AI
Jun 2

Information-Theoretic Lower Bounds for Bit-Constrained Stochastic Optimization via a Reduction to Compressed Gaussian Mean Estimation

arXiv:2606. 00703v1 Announce Type: cross Abstract: Low-precision pretraining (FP8, MXFP4, NVFP4) is now standard for frontier language models, yet the literature is almost entirely achievability -- algorithms and empirical scaling laws -- with no matching characterization of what is information-theoretically possible.

By Munsik Kim
arXiv Machine Learning
Jun 5

Multi-Agent Lipschitz Bandits

arXiv:2602. 16965v2 Announce Type: replace Abstract: We study the decentralized multi-player stochastic bandit problem over a continuous, Lipschitz-structured action space where hard collisions yield zero reward.

By Sourav Chakraborty, Amit Kiran Rege, Claire Monteleoni, Lijun Chen
arXiv Machine Learning
5d ago

Decentralized Multi-Player Q-Learning in Episodic Markov Decision Processes with Information Asymmetry

arXiv:2608. 12753v1 Announce Type: new Abstract: We study decentralized multi-player reinforcement learning in episodic tabular Markov decision processes (MDPs) under three forms of information asymmetry: (A) unobserved actions with common rewards, (B) observed actions with independent rewards, and (C) unobserved actions with independent rewards.

By Larissa Xu, King Bi, William Chang
arXiv AI
Jul 10

Provably Optimal Learning Algorithms for Assistance Games

arXiv:2607. 08012v1 Announce Type: cross Abstract: This paper studies an online variant of the assistance games framework, where an informed agent and an uninformed agent repeatedly interact over $T$ timesteps to optimize a common reward function.

By Nivasini Ananthakrishnan, Mark Bedaywi, Michael I. Jordan, Stuart Russell, Nika Haghtalab