Showing 1–20 of 82 results
/ Date/ Name
Jun 12, 2018Differentiable Compositional Kernel Learning for Gaussian ProcessesMay 15, 2019EigenDamage: Structured Pruning in the Kronecker-Factored EigenbasisNov 30, 2018Eigenvalue Corrected Noisy Natural GradientDec 6, 2017Noisy Natural Gradient as Variational InferenceJun 20, 2024Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training DataNov 6, 2020Beyond Marginal Uncertainty: How Accurately can Bayesian Regression Models Estimate Posterior Predictive Correlations?Jul 6, 2020INT: An Inequality Benchmark for Evaluating Generalization in Theorem ProvingJan 15, 2021LIME: Learning Inductive Bias for Primitives of Mathematical ReasoningSep 12, 2022If Influence Functions are the Answer, Then What is the Question?Aug 7, 2023Studying Large Language Model Generalization with Influence FunctionsOct 25, 2018Reversible Recurrent Neural NetworksSep 23, 2020A Unified Analysis of First-Order Methods for Smooth Games via Integral Quadratic ConstraintsJul 21, 2021Differentiable Annealed Importance Sampling and the Perils of Gradient NoiseJul 13, 2020Regularized linear autoencoders recover the principal components, eventuallyFeb 3, 2016A Kronecker-factored approximate Fisher matrix for convolution layersApr 26, 2024Probabilistic Inference in Language Models via Twisted Sequential Monte CarloMay 27, 2019Fast Convergence of Natural Gradient Descent for Overparameterized Neural NetworksJun 18, 2020When Does Preconditioning Help or Hurt Generalization?Apr 22, 2021Analyzing Monotonic Linear Interpolation in Neural Network Loss LandscapesFeb 28, 2022Amortized Proximal Optimization