Rethinking Parameter Counting in Deep Models: Effective Dimensionality Revisited

4 March 2020

Papers citing "Rethinking Parameter Counting in Deep Models: Effective Dimensionality Revisited"

16 / 16 papers shown

Title
Just How Flexible are Neural Networks in Practice? Ravid Shwartz-Ziv Micah Goldblum Arpit Bansal C. Bayan Bruss Yann LeCun Andrew Gordon Wilson 43 4 0 17 Jun 2024
Gradients of Functions of Large Matrices Nicholas Krämer Pablo Moreno-Muñoz Hrittik Roy Søren Hauberg 40 0 0 27 May 2024
Leveraging Active Subspaces to Capture Epistemic Model Uncertainty in Deep Generative Models for Molecular Design A. N. M. N. Abeer Sanket R. Jantre Nathan M. Urban Byung-Jun Yoon 52 1 0 30 Apr 2024
Learning Active Subspaces for Effective and Scalable Uncertainty Quantification in Deep Neural Networks Sanket R. Jantre Nathan M. Urban Xiaoning Qian Byung-Jun Yoon BDL UQCV 26 4 0 06 Sep 2023
Bayesian Neural Networks for Geothermal Resource Assessment: Prediction with Uncertainty Stephen R. Brown W. Rodi Marco Seracini Chengxi Gu Michael Fehler J. Faulds Connor M. Smith S. Treitel 23 0 0 30 Sep 2022
Why neural networks find simple solutions: the many regularizers of geometric complexity Benoit Dherin Michael Munn M. Rosca David Barrett 55 31 0 27 Sep 2022
Adapting the Linearised Laplace Model Evidence for Modern Deep Learning Javier Antorán David Janz J. Allingham Erik A. Daxberger Riccardo Barbano Eric T. Nalisnick José Miguel Hernández-Lobato UQCV BDL 30 28 0 17 Jun 2022
Adversarial robustness of sparse local Lipschitz predictors Ramchandran Muthukumar Jeremias Sulam AAML 32 13 0 26 Feb 2022
Bayesian Model Selection, the Marginal Likelihood, and Generalization Sanae Lotfi Pavel Izmailov Gregory W. Benton Micah Goldblum A. Wilson UQCV BDL 52 56 0 23 Feb 2022
Rotationally Equivariant Super-Resolution of Velocity Fields in Two-Dimensional Fluids Using Convolutional Neural Networks Y. Yasuda R. Onishi 25 5 0 22 Feb 2022
Laplace Redux -- Effortless Bayesian Deep Learning Erik A. Daxberger Agustinus Kristiadi Alexander Immer Runa Eschenhagen Matthias Bauer Philipp Hennig BDL UQCV 58 289 0 28 Jun 2021
Loss Surface Simplexes for Mode Connecting Volumes and Fast Ensembling Gregory W. Benton Wesley J. Maddox Sanae Lotfi A. Wilson UQCV 25 67 0 25 Feb 2021
Simplifying Hamiltonian and Lagrangian Neural Networks via Explicit Constraints Marc Finzi Ke Alexander Wang A. Wilson AI4CE 34 126 0 26 Oct 2020
Deep Learning is Singular, and That's Good Daniel Murfet Susan Wei Biwei Huang Hui Li Jesse Gell-Redman T. Quella UQCV 24 26 0 22 Oct 2020
GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding Dmitry Lepikhin HyoukJoong Lee Yuanzhong Xu Dehao Chen Orhan Firat Yanping Huang M. Krikun Noam M. Shazeer Z. Chen MoE 31 1,108 0 30 Jun 2020
On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima N. Keskar Dheevatsa Mudigere J. Nocedal M. Smelyanskiy P. T. P. Tang ODL 308 2,890 0 15 Sep 2016