Zobrazeno 1 - 10
of 42
pro vyhledávání: '"Varma, Rohan"'
Autor:
Zhao, Yanli, Gu, Andrew, Varma, Rohan, Luo, Liang, Huang, Chien-Chin, Xu, Min, Wright, Less, Shojanazeri, Hamid, Ott, Myle, Shleifer, Sam, Desmaison, Alban, Balioglu, Can, Damania, Pritam, Nguyen, Bernard, Chauhan, Geeta, Hao, Yuchen, Mathews, Ajit, Li, Shen
It is widely acknowledged that large models have the potential to deliver superior performance across a broad range of domains. Despite the remarkable progress made in the field of machine learning systems research, which has enabled the development
Externí odkaz:
http://arxiv.org/abs/2304.11277
Autor:
Li, Shen, Zhao, Yanli, Varma, Rohan, Salpekar, Omkar, Noordhuis, Pieter, Li, Teng, Paszke, Adam, Smith, Jeff, Vaughan, Brian, Damania, Pritam, Chintala, Soumith
This paper presents the design, implementation, and evaluation of the PyTorch distributed data parallel module. PyTorch is a widely-adopted scientific computing package used in deep learning research and applications. Recent advances in deep learning
Externí odkaz:
http://arxiv.org/abs/2006.15704
Publikováno v:
IEEE Transactions on Signal and Information Processing over Networks, vol. 6, pp. 48-62, 2020
This work studies the denoising of piecewise smooth graph signals that exhibit inhomogeneous levels of smoothness over a graph, where the value at each node can be vector-valued. We extend the graph trend filtering framework to denoising vector-value
Externí odkaz:
http://arxiv.org/abs/1905.12692
Autor:
Varma, Rohan, Kovačević, Jelena
In this paper, we extend the sampling theory on graphs by constructing a framework that exploits the structure in product graphs for efficient sampling and recovery of bandlimited graph signals that lie on them. Product graphs are graphs that are com
Externí odkaz:
http://arxiv.org/abs/1809.10049
We present a framework for representing and modeling data on graphs. Based on this framework, we study three typical classes of graph signals: smooth graph signals, piecewise-constant graph signals, and piecewise-smooth graph signals. For each class,
Externí odkaz:
http://arxiv.org/abs/1512.05406
This paper builds theoretical foundations for the recovery of a newly proposed class of smooth graph signals, approximately bandlimited graph signals, under three sampling strategies: uniform sampling, experimentally designed sampling and active samp
Externí odkaz:
http://arxiv.org/abs/1512.05405
In this paper, we consider a statistical problem of learning a linear model from noisy samples. Existing work has focused on approximating the least squares solution by using leverage-based scores as an importance sampling distribution. However, no f
Externí odkaz:
http://arxiv.org/abs/1507.05870
We study signal recovery on graphs based on two sampling strategies: random sampling and experimentally designed sampling. We propose a new class of smooth graph signals, called approximately bandlimited, which generalizes the bandlimited class and i
Externí odkaz:
http://arxiv.org/abs/1504.05427
We propose a sampling theory for signals that are supported on either directed or undirected graphs. The theory follows the same paradigm as classical sampling theory. We show that perfect recovery is possible for graph signals bandlimited under the
Externí odkaz:
http://arxiv.org/abs/1503.05432
Publikováno v:
The Oxford Compendium of Visual Illusions, 2017, ill.
Externí odkaz:
https://doi.org/10.1093/acprof:oso/9780199794607.003.0089