Should We Learn Most Likely Functions or Parameters?

Should We Learn Most Likely Functions or Parameters?

27 November 2023

Tim G. J. Rudner

Sanyam Kapoor

Andrew Gordon Wilson

Papers citing "Should We Learn Most Likely Functions or Parameters?"

7 / 7 papers shown

Title
Preferential Normalizing Flows Petrus Mikkola Luigi Acerbi Arto Klami 33 1 0 11 Oct 2024
Can a Confident Prior Replace a Cold Posterior? Martin Marek Brooks Paige Pavel Izmailov UQCV BDL 42 4 0 02 Mar 2024
Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI Theodore Papamarkou Maria Skoularidou Konstantina Palla Laurence Aitchison Julyan Arbel ... David Rügamer Yee Whye Teh Max Welling Andrew Gordon Wilson Ruqi Zhang UQCV BDL 44 27 0 01 Feb 2024
Tractable Function-Space Variational Inference in Bayesian Neural Networks Tim G. J. Rudner Zonghao Chen Yee Whye Teh Y. Gal 85 39 0 28 Dec 2023
Function-Space Regularization in Neural Networks: A Probabilistic Perspective Tim G. J. Rudner Sanyam Kapoor Shikai Qiu A. Wilson 37 12 0 28 Dec 2023
Informative Priors Improve the Reliability of Multimodal Clinical Data Classification L. J. L. Lopez Tim G. J. Rudner Karan Singhal 45 3 0 17 Nov 2023
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 2,892 0 15 Sep 2016