170 citations · 876 across the 146 of their papers we have counts for
176 papers
Task-Based MoE for Multitask Multilingual Machine Translation
Hai Pham, Young Jin Kim, Subhabrata Mukherjee +3
Mixture-of-experts (MoE) architecture has been proven a powerful method for diverse tasks in training deep models in many applications. However, current MoE implementations are tas…
-Regression in the Arbitrary Partition Model of Communication
Yi Li, Honghao Lin, David P. Woodruff
We consider the randomized communication complexity of the distributed -regression problem in the coordinator model, for . In this problem, there is a coordinat…
Improved Algorithms for White-Box Adversarial Streams
Ying Feng, David P. Woodruff
We study streaming algorithms in the white-box adversarial stream model, where the internal state of the streaming algorithm is revealed to an adversary who adaptively generates th…
Fast -Approximation Algorithms for Binary Matrix Factorization
Ameya Velingker, Maximilian Vötsch, David P. Woodruff +1
We introduce efficient -approximation algorithms for the binary matrix factorization (BMF) problem, where the inputs are a matrix $\mathbf{A}\in\{0,1\}^{n\times d}…
Learning the Positions in CountSketch
Yi Li, Honghao Lin, Simin Liu +2
We consider sketching algorithms which first compress data by multiplication with a random sketch matrix, and then apply the sketch to quickly solve an optimization problem, e.g.,…
Sharper Bounds for Sensitivity Sampling
David P. Woodruff, Taisuke Yasuda
In large scale machine learning, random sampling is a popular way to approximate datasets by a small representative subset of examples. In particular, sensitivity sampling is an in…