1 rich Libsyn https://www.libsyn.com 90 600 What's going on with deep learning? What sorts of models get learned, and what are the learning dynamics? Singular learning theory is a theory of Bayesian statistics broad enough in scope to encompass deep neural networks that may help answer these questions. In this episode, I speak with Daniel Murfet about this research program and what it tells us. Patreon: patreon.com/axrpodcast Ko-fi: ko-fi.com/axrpodcast Topics we discuss, and timestamps: 0:00:26 - What is singular learning theory? 0:16:00 - Phase transitions 0:35:12 - Estimating the local learning coefficient 0:44:37 - Singular learning theory and generalization 1:00:39 - Singular learning theory vs other deep learning theory 1:17:06 - How singular learning theory hit AI alignment 1:33:12 - Payoffs of singular learning theory for AI alignment 1:59:36 - Does singular learning theory advance AI capabilities? 2:13:02 - Open problems in singular learning theory for AI alignment 2:20:53 - What is the singular fluctuation? 2:25:33 - How geometry relates to information 2:30:13 - Following Daniel Murfet's work &amp;nbsp; The transcript: https://axrp.net/episode/2024/05/07/episode-31-singular-learning-theory-dan-murfet.html Daniel Murfet's twitter/X account: https://twitter.com/danielmurfet Developmental interpretability website: https://devinterp.com Developmental interpretability YouTube channel: https://www.youtube.com/@Devinterp &amp;nbsp; Main research discussed in this episode: - Developmental Landscape of In-Context Learning:&amp;nbsp;https://arxiv.org/abs/2402.02364 - Estimating the Local Learning Coefficient at Scale:&amp;nbsp;https://arxiv.org/abs/2402.03698 - Simple versus Short: Higher-order degeneracy and error-correction:&amp;nbsp;https://www.lesswrong.com/posts/nWRj6Ey8e5siAEXbK/simple-versus-short-higher-order-degeneracy-and-error-1 &amp;nbsp; Other links: - Algebraic Geometry and Statistical Learning Theory (the grey book):&amp;nbsp;https://www.cambridge.org/core/books/algebraic-geometry-and-statistical-learning-theory/9C8FD1BDC817E2FC79117C7F41544A3A - Mathematical Theory of Bayesian Statistics (the green book): https://www.routledge.com/Mathematical-Theory-of-Bayesian-Statistics/Watanabe/p/book/9780367734817 In-context learning and induction heads: https://transformer-circuits.pub/2022/in-context-learning-and-induction-heads/index.html - Saddle-to-Saddle Dynamics in Deep Linear Networks: Small Initialization Training, Symmetry, and Sparsity:&amp;nbsp;https://arxiv.org/abs/2106.15933 - A mathematical theory of semantic development in deep neural networks: https://www.pnas.org/doi/abs/10.1073/pnas.1820226116 - Consideration on the Learning Efficiency Of Multiple-Layered Neural Networks with Linear Units:&amp;nbsp;https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4404877 - Neural Tangent Kernel: Convergence and Generalization in Neural Networks:&amp;nbsp;https://arxiv.org/abs/1806.07572 - The Interpolating Information Criterion for Overparameterized Models:&amp;nbsp;https://arxiv.org/abs/2307.07785 - Feature Learning in Infinite-Width Neural Networks:&amp;nbsp;https://arxiv.org/abs/2011.14522 - A central AI alignment problem: capabilities generalization, and the sharp left turn: https://www.lesswrong.com/posts/GNhMPAWcfBCASy8e6/a-central-ai-alignment-problem-capabilities-generalization - Quantifying degeneracy in singular models via the learning coefficient:&amp;nbsp;https://arxiv.org/abs/2308.12108 &amp;nbsp; Episode art by Hamish Doodles:&amp;nbsp;hamishdoodles.com AXRP - the AI X-risk Research Podcast https://axrp.net <iframe title="Libsyn Player" style="border: none" src="//html5-player.libsyn.com/embed/episode/id/31169122/height/90/theme/custom/thumbnail/yes/direction/forward/render-playlist/no/custom-color/88AA3C/" height="90" width="600" scrolling="no" allowfullscreen webkitallowfullscreen mozallowfullscreen oallowfullscreen msallowfullscreen></iframe> https://assets.libsyn.com/secure/content/171708452