[2002.10689] A Theory of Usable Information Under Computational Constraints

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status

[2002.10689] A Theory of Usable Information Under Computational Constraints Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Machine Learning arXiv:2002.10689 (cs) [Submitted on 25 Feb 2020] Title: A Theory of Usable Information Under Computational Constraints Authors: Yilun Xu , Shengjia Zhao , Jiaming Song , Russell Stewart , Stefano Ermon View a PDF of the paper titled A Theory of Usable Information Under Computational Constraints, by Yilun Xu and 4 other authors View PDF Abstrac

related reading

• [2512.19428] Attention Is Not What You Needarxiv.org
• [2406.17583] Towards Compositional Interpretability for XAIarxiv.org
• Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Reviewarxiv.org
• [2402.12875] Chain of Thought Empowers Transformers to Solve Inherently Serial Problemsarxiv.org
• [1709.08568] The Consciousness Priorarxiv.org
• [2309.01809] Are Emergent Abilities in Large Language Models just In-Context Learning?arxiv.org
• [2509.14786] Pre-training under infinite computearxiv.org
• [2312.15159] Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inferencearxiv.org
• Interactive Machine Learning: A State of the Art Reviewarxiv.org
• [2406.02061] Alice in Wonderland: Simple Tasks Showing Complete Reasoning Breakdown in State-Of-the-Art Large Language Modelsarxiv.org
• [2406.04219] Multi-Agent Imitation Learning: Value is Easy, Regret is Hardarxiv.org
• [2109.03853] A Bayesian Framework for Information-Theoretic Probingarxiv.org