H
Hongyi Zhang
Researcher at Massachusetts Institute of Technology
Publications - 20
Citations - 6316
Hongyi Zhang is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Manifold & Stochastic optimization. The author has an hindex of 15, co-authored 19 publications receiving 3345 citations. Previous affiliations of Hongyi Zhang include Peking University.
Papers
More filters
Proceedings Article
mixup: Beyond Empirical Risk Minimization
TL;DR: This work proposes mixup, a simple learning principle that trains a neural network on convex combinations of pairs of examples and their labels, which improves the generalization of state-of-the-art neural network architectures.
Posted Content
mixup: Beyond Empirical Risk Minimization
TL;DR: Mixup as discussed by the authors trains a neural network on convex combinations of pairs of examples and their labels, and regularizes the neural network to favor simple linear behavior in between training examples, which improves the generalization of state-of-the-art neural network architectures.
Proceedings ArticleDOI
Physics 101: Learning Physical Object Properties from Unlabeled Videos.
TL;DR: An unsupervised representation learning model is proposed, which explicitly encodes basic physical laws into the structure and use them, with automatically discovered observations from videos, as supervision, and demonstrates how its generative nature enables solving other tasks such as outcome prediction.
Proceedings Article
Riemannian SVRG: fast stochastic optimization on riemannian manifolds
TL;DR: This paper introduces Riemannian SVRG (RSVRG), a new variance reduced RiemANNian optimization method, and presents the first non-asymptotic complexity analysis (novel even for the batch setting) for nonconvex Riem Mannian optimization.
Posted Content
Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds
TL;DR: The Riemannian SVRG (RSVRG) as discussed by the authors is a new variance reduced Riemmannian optimization method for finite sums of geodesically smooth functions.