activity
20182021
most citedChoosing the Sample with Lowest Loss makes SGD Robust

11 citations · 18 across the 2 of their papers we have counts for

collaborators

7 papers

cs.CL2021

Hierarchical Learning for Generation with Long Source Sequences

Tobias Rohde, Xiaoxia Wu, Yinhan Liu

One of the challenges for current sequence to sequence (seq2seq) models is processing long sequences, such as those in summarization and document level machine translation tasks. T…

cs.LG20207 cited

When Do Curricula Work?

Xiaoxia Wu, Ethan Dyer, Behnam Neyshabur

Inspired by human learning, researchers have proposed ordering examples during training based on their difficulty. Both curriculum learning, exposing a network to easier examples e…

stat.ML202011 cited

Choosing the Sample with Lowest Loss makes SGD Robust

Vatsal Shah, Xiaoxia Wu, Sujay Sanghavi

The presence of outliers can potentially significantly skew the parameters of machine learning models trained via stochastic gradient descent (SGD). In this paper we propose a simp…

stat.ML2019

Linear Convergence of Adaptive Stochastic Gradient Descent

Yuege Xie, Xiaoxia Wu, Rachel Ward

We prove that the norm version of the adaptive stochastic gradient method (AdaGrad-Norm) achieves a linear convergence rate for a subset of either strongly convex functions or non-…

cs.LG2019

Global Convergence of Adaptive Gradient Methods for An Over-parameterized Neural Network

Xiaoxia Wu, Simon S. Du, Rachel Ward

Adaptive gradient methods like AdaGrad are widely used in optimizing neural networks. Yet, existing convergence guarantees for adaptive gradient methods require either convexity or…

stat.ML2018

AdaGrad stepsizes: Sharp convergence over nonconvex landscapes

Rachel Ward, Xiaoxia Wu, Leon Bottou

Adaptive gradient methods such as AdaGrad and its variants update the stepsize in stochastic gradient descent on the fly according to the gradients received along the way; such met…