activity
20182022
most citedSubspace Inference for Bayesian Deep Learning

19 citations · 22 across the 3 of their papers we have counts for

collaborators

6 papers

cs.LG2020

The Benefits of Pairwise Discriminators for Adversarial Training

Shangyuan Tong, Timur Garipov, Tommi Jaakkola

Adversarial training methods typically align distributions by solving two-player games. However, in most current formulations, even if the generator aligns perfectly with data, a s…

cs.LG201919 cited

Subspace Inference for Bayesian Deep Learning

Pavel Izmailov, Wesley J. Maddox, Polina Kirichenko +3

Bayesian inference was once a gold standard for learning with neural networks, providing accurate full predictive distributions and well calibrated uncertainty. However, scaling Ba…

cs.LG2019

A Simple Baseline for Bayesian Uncertainty in Deep Learning

Wesley Maddox, Timur Garipov, Pavel Izmailov +2

We propose SWA-Gaussian (SWAG), a simple, scalable, and general purpose approach for uncertainty representation and calibration in deep learning. Stochastic Weight Averaging (SWA),…

stat.ML2018

Bayesian Incremental Learning for Deep Neural Networks

Max Kochurov, Timur Garipov, Dmitry Podoprikhin +3

In industrial machine learning pipelines, data often arrive in parts. Particularly in the case of deep neural networks, it may be too expensive to train the model from scratch each…

cs.LG2018

Averaging Weights Leads to Wider Optima and Better Generalization

Pavel Izmailov, Dmitrii Podoprikhin, Timur Garipov +2

Deep neural networks are typically trained by optimizing a loss function with an SGD variant, in conjunction with a decaying learning rate, until convergence. We show that simple a…

stat.ML2018

Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs

Timur Garipov, Pavel Izmailov, Dmitrii Podoprikhin +2

The loss functions of deep neural networks are complex and their geometric properties are not well understood. We show that the optima of these complex loss functions are in fact c…