69 citations · 402 across the 23 of their papers we have counts for
7 papers · 1 filter
Towards a Theoretical Understanding of Hashing-Based Neural Nets
Yibo Lin, Zhao Song, Lin F. Yang
Parameter reduction has been an important topic in deep learning due to the ever-increasing size of deep neural network models and the need to train and run them on resource limite…
Universal Streaming of Subset Norms
Vladimir Braverman, Robert Krauthgamer, Lin F. Yang
Most known algorithms in the streaming model of computation aim to approximate a single function such as an -norm. In 2009, Nelson [\url{https://sublinear.info}, Open Probl…
On Landscape of Lagrangian Functions and Stochastic Search for Constrained Nonconvex Optimization
Zhehui Chen, Xingguo Li, Lin F. Yang +2
We study constrained nonconvex optimization problems in machine learning, signal processing, and stochastic control. It is well-known that these problems can be rewritten to a mini…
Near-Optimal Time and Sample Complexities for Solving Discounted Markov Decision Process with a Generative Model
Aaron Sidford, Mengdi Wang, Xian Wu +2
In this paper we consider the problem of computing an -optimal policy of a discounted Markov Decision Process (DMDP) provided we can only access its transition function through…
Revisiting Frequency Moment Estimation in Random Order Streams
Vladimir Braverman, Emanuele Viola, David Woodruff +1
We revisit one of the classic problems in the data stream literature, namely, that of estimating the frequency moments for of an underlying -dimensional vector…
Variance Reduction Methods for Sublinear Reinforcement Learning
Sham Kakade, Mengdi Wang, Lin F. Yang
There is a technical issue in the analysis that is not easily fixable. We, therefore, withdraw the submission. Sorry for the inconvenience.