Y
Yu Sun
Researcher at University of California, Berkeley
Publications - 21
Citations - 9316
Yu Sun is an academic researcher from University of California, Berkeley. The author has contributed to research in topics: Information privacy & Causal inference. The author has an hindex of 14, co-authored 19 publications receiving 6414 citations. Previous affiliations of Yu Sun include Washington University in St. Louis & Cornell University.
Papers
More filters
Posted Content
On Calibration of Modern Neural Networks
TL;DR: It is discovered that modern neural networks, unlike those from a decade ago, are poorly calibrated, and on most datasets, temperature scaling -- a single-parameter variant of Platt Scaling -- is surprisingly effective at calibrating predictions.
Proceedings Article
On calibration of modern neural networks
TL;DR: This article found that depth, width, weight decay, and batch normalization are important factors influencing confidence calibration of neural networks, and that temperature scaling is surprisingly effective at calibrating predictions.
Proceedings Article
From Word Embeddings To Document Distances
TL;DR: It is demonstrated on eight real world document classification data sets, in comparison with seven state-of-the-art baselines, that the Word Mover's Distance metric leads to unprecedented low k-nearest neighbor document classification error rates.
Book ChapterDOI
Deep Networks with Stochastic Depth
TL;DR: Stochastic depth is proposed, a training procedure that enables the seemingly contradictory setup to train short networks and use deep networks at test time and reduces training time substantially and improves the test error significantly on almost all data sets that were used for evaluation.
Posted Content
Deep Networks with Stochastic Depth
TL;DR: Stochastic depth as discussed by the authors randomly drops a subset of layers during training and bypasses them with the identity function, which can increase the depth of residual networks even beyond 1200 layers and still yield meaningful improvements in test error.