Filters








12 Hits in 1.9 sec

Lightweight Convolutional Representations for On-Device Natural Language Processing [article]

Shrey Desai, Geoffrey Goh, Arun Babu, Ahmed Aly
<span title="2020-02-04">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Proceedings of the 3 rd MLSys Conference, Austin, TX, USA, 2020. Copyright 2020 by the author(s). Table 2.  ...  Future work will explore the viability of this representation in more language tasks. 1 The University of Texas at Austin 2 Facebook Assistant.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.01535v1">arXiv:2002.01535v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3klnig23jnfqdntfh7uhffk5sy">fatcat:3klnig23jnfqdntfh7uhffk5sy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321103553/https://arxiv.org/pdf/2002.01535v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.01535v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Efficient Memory Management for Deep Neural Net Inference [article]

Yury Pisarchyk, Juhyun Lee
<span title="2020-02-16">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
2020 Conference, Austin, TX, USA, 2020.  ...  (Chen et al., 2016) LG] 16 Feb 2020 Figure 1 .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2001.03288v3">arXiv:2001.03288v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wzs4z3jo5fcqtnk4egw4lycmji">fatcat:wzs4z3jo5fcqtnk4egw4lycmji</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321130653/https://arxiv.org/pdf/2001.03288v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2001.03288v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Optimizing JPEG Quantization for Classification Networks [article]

Zhijing Li, Christopher De Sa, Adrian Sampson
<span title="2020-03-05">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Conference, Austin, TX, USA, 2020.  ...  Fig. 1 1 shows an overview of the standard JPEG compression 1 Cornell University.Correspondence to: Zhijing Li <zl679@cornell.edu>.Resource-Constrained Machine Learning (ReCoML) Workshop of MLSys 2020  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.02874v1">arXiv:2003.02874v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hes5emi6cndcrod7gamqkryhme">fatcat:hes5emi6cndcrod7gamqkryhme</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200320232433/https://arxiv.org/pdf/2003.02874v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.02874v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

MNN: A Universal and Efficient Inference Engine [article]

Xiaotang Jiang, Huan Wang, Yiliu Chen, Ziqi Wu, Lichuan Wang, Bin Zou, Yafeng Yang, Zongyang Cui, Yu Cai, Tianhang Yu, Chengfei Lv, Zhihua Wu
<span title="2020-02-27">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Proceedings of the 3 rd MLSys Conference, Austin, TX, USA, 2020. Copyright 2020 by the author(s). and different operators.  ...  arXiv:2002.12418v1 [cs.CV] 27 Feb 2020 (3) Resource limitation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.12418v1">arXiv:2002.12418v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ppeykiv57nc6bfqa74lyzse3by">fatcat:ppeykiv57nc6bfqa74lyzse3by</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200323112605/https://arxiv.org/pdf/2002.12418v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2002.12418v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Adaptive Dense-to-Sparse Paradigm for Pruning Online Recommendation System with Non-Stationary Data [article]

Mao Ye, Dhruv Choudhary, Jiecao Yu, Ellie Wen, Zeliang Chen, Jiyan Yang, Jongsoo Park, Qiang Liu, Arun Kejariwal
<span title="2020-10-21">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Submitted to Proceedings of the 3 rd MLSys Conference, Austin, TX, USA, 2020. Copyright 2020 by the author(s). 2018), and distillation (Polino et al., 2018) have been developed and deployed.  ...  Hence, a number of model compression techniques (Gupta & Agrawal, 2020) such as pruning, quantization (Choi et al., 1 University of Texas, Austin 2 Facebook Inc.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.08655v2">arXiv:2010.08655v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ua5fh45fjzgbvmkas7n2q2pbeq">fatcat:ua5fh45fjzgbvmkas7n2q2pbeq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201025160907/https://arxiv.org/pdf/2010.08655v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/20/03/20033e4bed3955165bfac2bc3512dd6dc78d51d3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.08655v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

On-device Federated Learning with Flower [article]

Akhil Mathur, Daniel J. Beutel, Pedro Porto Buarque de Gusmão, Javier Fernandez-Marques, Taner Topal, Xinchi Qiu, Titouan Parcollet, Yan Gao, Nicholas D. Lane
<span title="2021-04-07">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Correspondence to: Akhil Mathur <akhilmathurs@gmail.com>.Proceedings of the 3 rd MLSys Conference, Austin, TX, USA, 2020. Copyright 2020 by the author(s).  ...  TFF (Google, 2020) , PySyft (Ryffel et al., 2018) , LEAF (Caldas et al., 2018) , FedML (He et al., 2020) are other open-source frameworks that support research and experimentation of FL workloads.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.03042v1">arXiv:2104.03042v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/giqpwt5uqvhlpets3o5vhxgzxa">fatcat:giqpwt5uqvhlpets3o5vhxgzxa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210409042954/https://arxiv.org/pdf/2104.03042v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/12/db/12dbe4a44d86b9d48da40533d2afb36448642f1f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.03042v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

AutoPhase: Juggling HLS Phase Orderings in Random Forests with Deep Reinforcement Learning [article]

Qijing Huang, Ameer Haj-Ali, William Moses, John Xiang, Ion Stoica, Krste Asanovic, John Wawrzynek
<span title="2020-03-04">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Proceedings of the 3 rd MLSys Conference, Austin, TX, USA, 2020. Copyright 2020 by the author(s). and the hand-optimized one produced by experts.  ...  NeuroVectorizer (Haj-Ali et al., 2020; 2019a) used deep RL for automatically tuning compiler pragmas such as vectorization and interleaving factors.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.00671v2">arXiv:2003.00671v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xemglojhkfhllo7oeo4aosqala">fatcat:xemglojhkfhllo7oeo4aosqala</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200320183235/https://arxiv.org/pdf/2003.00671v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.00671v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Distributed Hierarchical GPU Parameter Server for Massive Scale Deep Learning Ads Systems [article]

Weijie Zhao, Deping Xie, Ronglai Jia, Yulei Qian, Ruiquan Ding, Mingming Sun, Ping Li
<span title="2020-03-12">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Proceedings of the 3 rd MLSys Conference, Austin, TX, USA, 2020. Copyright 2020 by the author(s).  ...  The node pulls the required parameters from other nodes and arXiv:2003.05622v1 [cs.DC] 12 Mar 2020 computes the gradients.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.05622v1">arXiv:2003.05622v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kfl2uv7oarfsfa7zpkgps76h6e">fatcat:kfl2uv7oarfsfa7zpkgps76h6e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200320182729/https://arxiv.org/pdf/2003.05622v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.05622v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

MLPerf Training Benchmark [article]

Peter Mattson, Christine Cheng, Cody Coleman, Greg Diamos, Paulius Micikevicius, David Patterson, Hanlin Tang, Gu-Yeon Wei, Peter Bailis, Victor Bittorf, David Brooks, Dehao Chen (+24 others)
<span title="2020-03-02">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Proceedings of the 3 rd MLSys Conference, Austin, TX, USA, 2020.  ...  LG] 2 Mar 2020 above challenges unaddressed or lacked critical workloads representative of modern ML.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.01500v3">arXiv:1910.01500v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ciwfjyu3x5crrm2fy2275g3wiy">fatcat:ciwfjyu3x5crrm2fy2275g3wiy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200322113423/https://arxiv.org/pdf/1910.01500v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.01500v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Federated Optimization in Heterogeneous Networks [article]

Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, Virginia Smith
<span title="2020-04-21">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
At each iteration, FedAvg first locally performs E epochs of stochastic gra-Proceedings of the 3 rd MLSys Conference, Austin, TX, USA, 2020.  ...  Copyright 2020 by the author(s). 1 Privacy is a third key challenge in the federated setting.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.06127v5">arXiv:1812.06127v5</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ol4wcatdynetldegch45wkppia">fatcat:ol4wcatdynetldegch45wkppia</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200901134320/https://arxiv.org/pdf/1812.06127v5.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/5f/37/5f37ffb2ecfc702de603bf8af300b7dd413760b7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.06127v5" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Differentially Private Federated Learning on Heterogeneous Data [article]

Maxence Noble, Aurélien Bellet, Aymeric Dieuleveut
<span title="2022-02-22">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In Proceedings of the 3rd MLSys Conference, Austin, TX, USA, 2020a. arXiv: 1812.06127. Yurii Nesterov et al. Lectures on convex optimization, volume 137. Springer, 2004.  ...  ., 2020; Karimireddy et al., 2020b) .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.09278v2">arXiv:2111.09278v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6ur77f3gsjhlzid2di33hcik34">fatcat:6ur77f3gsjhlzid2di33hcik34</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211122172033/https://arxiv.org/pdf/2111.09278v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/94/d5/94d5e1772a252704c415cdd61709deb151b4c1d1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.09278v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Multiplying Matrices Without Multiplying [article]

Davis Blalock, John Guttag
<span title="2021-06-21">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Fast 2020, MLSys 2020, Austin, TX, USA, March 2-4, 2020. Monte Carlo Algorithms for Matrices II: Com- mlsys.org, 2020. URL https://proceedings.  ...  Cambridge, MA, USA.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.10860v1">arXiv:2106.10860v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uny4gzjt4reblemp5ectkmccmi">fatcat:uny4gzjt4reblemp5ectkmccmi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210911103654/https://arxiv.org/pdf/2106.10860v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/21/7d/217d1b66d45adfe73c9324a6751890d651e99dd5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.10860v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>