Showing 1–20 of 22 results
/ Date/ Name
Jun 18, 2020Exact posterior distributions of wide Bayesian neural networksJun 30, 2021The Evolution of Out-of-Distribution Robustness Throughout Fine-TuningOct 11, 2018Bayesian Deep Convolutional Networks with Many Channels are Gaussian ProcessesJun 18, 2020Infinite attention: NNGP and NTK for deep attention networksFeb 18, 2019Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient DescentMar 11, 2013Detecting Majorana fermions in quasi-one-dimensional topological phases using nonlocal order parametersFeb 23, 2018Sensitivity and Generalization in Neural Networks: an Empirical StudyFeb 14, 2025Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like ModelsFeb 16, 2026Symmetry in language statistics shapes the geometry of model representationsMar 5, 2024Quantum Many-Body Physics Calculations with Large Language ModelsNov 1, 2017Deep Neural Networks as Gaussian ProcessesMar 4, 2020The large learning rate phase of deep learning: the catapult mechanismJul 15, 2013Localization and topology protected quantum coherence at the edge of 'hot' matterAug 28, 2014Stable non-Fermi liquid phase of itinerant spin-orbit coupled ferromagnetsFeb 12, 2021Explaining Neural Scaling LawsSep 4, 2023Les Houches Lectures on Deep Learning at Large & Infinite WidthMay 24, 2025On the Emergence of Linear Analogies in Word EmbeddingsJun 9, 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelsJan 29, 2026Context Structure Reshapes the Representational Geometry of Language ModelsJun 14, 2018Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks