Searching for Fast Model Families on Datacenter Accelerators

Computer Vision and Pattern Recognition (CVPR), 2021

10 February 2021

Mingxing Tan

Papers citing "Searching for Fast Model Families on Datacenter Accelerators"

21 / 21 papers shown

Title
Composer: A Search Framework for Hybrid Neural Architecture Design Bilge Acun Prasoon Sinha Newsha Ardalani Sangmin Bae Alicia Golden Chien-Yu Lin Meghana Madhyastha Fei Sun N. Yadwadkar Carole-Jean Wu 184 1 0 01 Oct 2025
MSPT: A Lightweight Face Image Quality Assessment Method with Multi-stage Progressive Training Xiongwei Xiao Baoying Chen Jishen Zeng Jianquan Yang CVBM 72 1 0 11 Aug 2025
Lightweight Deep Learning for Resource-Constrained Environments: A Survey Hou-I Liu Marco Galindo Hongxia Xie Lai-Kuan Wong Hong-Han Shuai Yung-Hui Li Wen-Huang Cheng 283 139 0 08 Apr 2024
Neural network scoring for efficient computing Hugo Waltsburger Erwan Libessart Chengfang Ren A. Kolar R. Guinvarc’h 121 0 0 14 Oct 2023
TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for EmbeddingsInternational Symposium on Computer Architecture (ISCA), 2023 N. Jouppi George Kurian Sheng Li Peter C. Ma R. Nagarajan ... Brian Towles C. Young Xiaoping Zhou Zongwei Zhou David A. Patterson BDL VLM 403 511 0 04 Apr 2023
Less is More: Selective Layer Finetuning with SubTuning Gal Kaplun Andrey Gurevich Tal Swisa Mazor David Shai Shalev-Shwartz Eran Malach 183 10 0 13 Feb 2023
Tiered Pruning for Efficient Differentialble Inference-Aware Neural Architecture Search Slawomir Kierat Mateusz Sieniawski Denys Fridman Chendi Yu Szymon Migacz Pawel M. Morkisz A. Fit-Florea 3DPC 163 0 0 23 Sep 2022
Design Automation for Fast, Lightweight, and Effective Deep Learning Models: A Survey Dalin Zhang Kaixuan Chen Yan Zhao B. Yang Li-Ping Yao Christian S. Jensen 241 4 0 22 Aug 2022
Restructurable Activation Networks Kartikeya Bhardwaj James Ward Caleb Tung Dibakar Gope Lingchuan Meng Igor Fedorov A. Chalfin P. Whatmough Danny Loh 222 6 0 17 Aug 2022
ScaleNet: Searching for the Model to ScaleEuropean Conference on Computer Vision (ECCV), 2022 Jiyang Xie Xiu Su Shan You Zhanyu Ma Fei Wang Chao Qian 191 5 0 15 Jul 2022
Revisiting Architecture-aware Knowledge Distillation: Smaller Models and Faster Search Taehyeon Kim Heesoo Myeong Se-Young Yun 148 3 0 27 Jun 2022
GPUNet: Searching the Deployable Convolution Neural Networks for GPUsComputer Vision and Pattern Recognition (CVPR), 2022 Linnan Wang Chenhan D. Yu Satish Salian Slawomir Kierat Szymon Migacz A. Fit-Florea 110 11 0 26 Apr 2022
The Carbon Footprint of Machine Learning Training Will Plateau, Then Shrink David A. Patterson Joseph E. Gonzalez Urs Holzle Quoc V. Le Chen Liang Lluís-Miquel Munguía D. Rothchild David R. So Maud Texier J. Dean AI4CE 233 333 0 11 Apr 2022
U-Boost NAS: Utilization-Boosted Differentiable Neural Architecture SearchEuropean Conference on Computer Vision (ECCV), 2022 A. C. Yüzügüler Nikolaos Dimitriadis P. Frossard 121 3 0 23 Mar 2022
AutoDistill: an End-to-End Framework to Explore and Distill Hardware-Efficient Language Models Xiaofan Zhang Zongwei Zhou Deming Chen Yu Emma Wang 143 12 0 21 Jan 2022
FBNetV5: Neural Architecture Search for Multiple Tasks in One Run Bichen Wu Chaojian Li Hang Zhang Xiaoliang Dai Peizhao Zhang Matthew Yu Jialiang Wang Yingyan Lin Peter Vajda ViT 483 30 0 19 Nov 2021
ISyNet: Convolutional Neural Networks design for AI accelerator Alexey Letunovskiy Vladimir Korviakov V. Polovnikov Anastasiia Kargapoltseva I. Mazurenko Yepan Xiong 188 1 0 04 Sep 2021
A Full-Stack Search Technique for Domain Optimized Deep Learning AcceleratorsInternational Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2021 Dan Zhang Safeen Huda Ebrahim M. Songhori Kartik Prabhu Quoc V. Le Anna Goldie Azalia Mirhoseini 215 54 0 26 May 2021
Measuring what Really Matters: Optimizing Neural Networks for TinyML Lennart Heim Andreas Biri Zhongnan Qu Lothar Thiele 184 32 0 21 Apr 2021
Carbon Emissions and Large Neural Network Training David A. Patterson Joseph E. Gonzalez Quoc V. Le Chen Liang Lluís-Miquel Munguía D. Rothchild David R. So Maud Texier J. Dean AI4CE 657 866 0 21 Apr 2021
EfficientNetV2: Smaller Models and Faster TrainingInternational Conference on Machine Learning (ICML), 2021 Mingxing Tan Quoc V. Le EgoV 1.1K 3,570 0 01 Apr 2021