activity
20152026
most citedTraining a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

391 citations · 1.4k across the 26 of their papers we have counts for

collaborators
Showing 2021Show all

5 papers · 1 filter

cs.LG2021★ 107 cited

Exploring the Limits of Out-of-Distribution Detection

Stanislav Fort, Jie Ren, Balaji Lakshminarayanan

Near out-of-distribution detection (OOD) is a major challenge for deep neural networks. We demonstrate that large-scale pre-trained transformers can significantly improve the state…

cs.LG2021

How many degrees of freedom do we need to train deep networks: a loss landscape perspective

Brett W. Larsen, Stanislav Fort, Nic Becker +1

A variety of recent works, spanning pruning, lottery tickets, and training within random subspaces, have shown that deep neural networks can be trained using far fewer degrees of f…

cs.LG2021★ 71 cited

A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection

Jie Ren, Stanislav Fort, Jeremiah Liu +3

Mahalanobis distance (MD) is a simple and popular post-processing method for detecting out-of-distribution (OOD) inputs in neural networks. We analyze its failure modes for near-OO…

cs.LG2021

Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error

Stanislav Fort, Andrew Brock, Razvan Pascanu +2

In computer vision, it is standard practice to draw a single sample from the data augmentation procedure for each unique image in the mini-batch. However recent work has suggested…

cs.LG2021★ 7 cited

Analyzing Monotonic Linear Interpolation in Neural Network Loss Landscapes

James Lucas, Juhan Bae, Michael R. Zhang +3

Linear interpolation between initial neural network parameters and converged parameters after training with stochastic gradient descent (SGD) typically leads to a monotonic decreas…