M
Marat Dukhan
Researcher at Google
Publications - 5
Citations - 891
Marat Dukhan is an academic researcher from Google. The author has contributed to research in topics: Deep learning & Bayesian optimization. The author has an hindex of 5, co-authored 5 publications receiving 581 citations. Previous affiliations of Marat Dukhan include Facebook.
Papers
More filters
Proceedings ArticleDOI
Machine Learning at Facebook: Understanding Inference at the Edge
Carole-Jean Wu,David Brooks,Kevin Chen,Douglas Chen,Sy Choudhury,Marat Dukhan,Kim Hazelwood,Eldad Isaac,Yangqing Jia,Bill Jia,Tommer Leyvand,Hao Lu,Yang Lu,Lin Qiao,Brandon Reagen,Joe Spisak,Fei Sun,Andrew Tulloch,Peter Vajda,Xiaodong Wang,Yanghan Wang,Bram Wasti,Yiming Wu,Ran Xian,Sungjoo Yoo,Sungjoo Yoo,Peizhao Zhang +26 more
TL;DR: This paper takes a datadriven approach to present the opportunities and design challenges faced by Facebook in order to enable machine learning inference locally on smartphones and other edge platforms.
Proceedings ArticleDOI
ChamNet: Towards Efficient Network Design Through Platform-Aware Model Adaptation
Xiaoliang Dai,Yangqing Jia,Peter Vajda,Matthew T. Uyttendaele,Niraj K. Jha,Peizhao Zhang,Bichen Wu,Hongxu Yin,Fei Sun,Yanghan Wang,Marat Dukhan,Yunqing Hu,Yiming Wu +12 more
TL;DR: The results show that adapting computation resources to building blocks is critical to model performance, and a novel algorithm to search for optimal architectures aided by efficient accuracy and resource (latency and/or energy) predictors is proposed.
Posted Content
ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation
Xiaoliang Dai,Peizhao Zhang,Bichen Wu,Hongxu Yin,Fei Sun,Yanghan Wang,Marat Dukhan,Yunqing Hu,Yiming Wu,Yangqing Jia,Peter Vajda,Matthew T. Uyttendaele,Niraj K. Jha +12 more
TL;DR: Chameleon as mentioned in this paper proposes an efficient neural network (NN) architecture design methodology called Chameleon that honors given resource constraints instead of developing new building blocks or using computationally-intensive reinforcement learning algorithms, instead of exploiting hardware traits and adapting computation resources to fit target latency and/or energy constraints.
Proceedings ArticleDOI
Fast Sparse ConvNets
TL;DR: This work introduces a family of efficient sparse kernels for several hardware platforms, and shows that sparse versions of MobileNet v1 and Mobile net v2 architectures substantially outperform strong dense baselines on the efficiency-accuracy curve.
Posted Content
Fast Sparse ConvNets
TL;DR: In this article, instead of combining standard primitives (such as convolution) with their sparse counterparts, the authors advocate for the replacement of these dense primitives with the sparse counterparts.