Hong Jun Jeon: PublicationsPublications are listed below by year of posting if they have not been published, or year of publication. 2024Saurabh Kumar, Hong Jun Jeon, Alex Lewandowski, and Benjamin Van Roy, The Need for a Big World Simulator: A Scientific Challenge for Continual Learning , [RLC 2024 Finding the Frame Workshop (oral)]. Hong Jun Jeon and Benjamin Van Roy, Information-Theoretic Foundations for Machine Learning, [Foundations and Trends Submission]. Hong Jun Jeon and Benjamin Van Roy, Information-Theoretic Foundations for Neural Scaling Laws. Hong Jun Jeon, Jason D. Lee, Qi Lei, and Benjamin Van Roy, An Information-Theoretic Analysis of In-Context Learning, [ICML 2024]. Anmol Kagrecha, Henrik Marklund, Benjamin Van Roy, Hong Jun Jeon, and Richard Zeckhauser, Adaptive Crowdsourcing Via Self-Supervised Learning. 2023Saurabh Kumar, Henrik Marklund, Ashish Rao, Yifan Zhu, Hong Jun Jeon, Yueyang Liu, and Benjamin Van Roy, Continual Learning as Computationally Constrained Reinforcement Learning, [Foundations and Trends Submission]. Hong Jun Jeon, Yifan Zhu, and Benjamin Van Roy, An Information-Theoretic Framework for Supervised Learning. 2022Hong Jun Jeon and Benjamin Van Roy, An Information-Theoretic Analysis of Compute-Optimal Neural Scaling Laws Yifan Zhu, Hong Jun Jeon, and Benjamin Van Roy, Is Stochastic Gradient Descent Near Optimal? Hong Jun Jeon and Benjamin Van Roy, An Information-Theoretic Framework for Deep Learning, [Neurips, 2022]. Dylan P Losey, Hong Jun Jeon, Mengxi Li, Krishnan Srinivasan, Ajay Mandlekar, Animesh Garg, Jeannette Bohg, and Dorsa Sadigh, Learning latent actions to control assistive robots 2020Hong Jun Jeon, Dylan P Losey, Dorsa Sadigh, Shared autonomy with learned latent actions, [RSS 2020], (Best Student Paper Finalist). Hong Jun Jeon, Smitha Milli, Anca Dragan, Reward-rational (implicit) choice: A unifying formalism for reward learning, [Neurips, 2020]. 2018Hong Jun Jeon, Anca Dragan, Configuration Space Metrics, [IROS 2018], (Best Student Paper Finalist). |