activity
20182022
most citedUnderspecification Presents Challenges for Credibility in Modern Machine Learning

430 citations · 460 across the 4 of their papers we have counts for

collaborators

10 papers

stat.ML202215 cited

Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks

Neil Band, Tim G. J. Rudner, Qixuan Feng +6

Bayesian deep learning seeks to equip deep neural networks with the ability to precisely quantify their predictive uncertainty, and has promised to make deep learning more reliable…

cs.LG20216 cited

A Loss Curvature Perspective on Training Instability in Deep Learning

Justin Gilmer, Behrooz Ghorbani, Ankush Garg +6

In this work, we study the evolution of the loss Hessian across many classification tasks in order to understand the effect the curvature of the loss has on the training dynamics.…

cs.LG2021

A Large Batch Optimizer Reality Check: Traditional, Generic Optimizers Suffice Across Batch Sizes

Zachary Nado, Justin M. Gilmer, Christopher J. Shallue +2

Recently the LARS and LAMB optimizers have been proposed for training neural networks faster using large batch sizes. LARS and LAMB add layer-wise normalization to the update rules…

cs.LG2020430 cited

Underspecification Presents Challenges for Credibility in Modern Machine Learning

Alexander D'Amour, Katherine Heller, Dan Moldovan +37

ML models often exhibit unexpectedly poor behavior when they are deployed in real-world domains. We identify underspecification as a key reason for these failures. An ML pipeline i…

cs.LG20209 cited

Revisiting One-vs-All Classifiers for Predictive Uncertainty and Out-of-Distribution Detection in Neural Networks

Shreyas Padhy, Zachary Nado, Jie Ren +3

Accurate estimation of predictive uncertainty in modern neural networks is critical to achieve well calibrated predictions and detect out-of-distribution (OOD) inputs. The most pro…

cs.LG2020

Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift

Zachary Nado, Shreyas Padhy, D. Sculley +3

Covariate shift has been shown to sharply degrade both predictive accuracy and the calibration of uncertainty estimates for deep learning models. This is worrying, because covariat…