{"ID":2865957,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.21049","arxiv_id":"2509.21049","title":"Physics of Learning: A Lagrangian perspective to different learning paradigms","abstract":"We study the problem of building an efficient learning system. Efficient learning processes information in the least time, i.e., building a system that reaches a desired error threshold with the least number of observations. Building upon least action principles from physics, we derive classic learning algorithms, Bellman's optimality equation in reinforcement learning, and the Adam optimizer in generative models from first principles, i.e., the Learning $\\textit{Lagrangian}$. We postulate that learning searches for stationary paths in the Lagrangian, and learning algorithms are derivable by seeking the stationary trajectories.","short_abstract":"We study the problem of building an efficient learning system. Efficient learning processes information in the least time, i.e., building a system that reaches a desired error threshold with the least number of observations. Building upon least action principles from physics, we derive classic learning algorithms, Bell...","url_abs":"https://arxiv.org/abs/2509.21049","url_pdf":"https://arxiv.org/pdf/2509.21049v1","authors":"[\"Siyuan Guo\",\"Bernhard Schölkopf\"]","published":"2025-09-25T12:00:22Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.NE\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\"]","has_code":false}