Mixed Dimension Embeddings with Application to Memory-Efficient Recommendation Systems

Sep 25, 2019
Antonio Ginart, Maxim Naumov, Dheevatsa Mudigere, Jiyan Yang, James Zou


  Access Model/Code and Paper
Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems

Sep 04, 2019
Hao-Jun Michael Shi, Dheevatsa Mudigere, Maxim Naumov, Jiyan Yang

* 20 pages, 11 figures, 4 tables 

  Access Model/Code and Paper
The Architectural Implications of Facebook's DNN-based Personalized Recommendation

Jun 18, 2019
Udit Gupta, Xiaodong Wang, Maxim Naumov, Carole-Jean Wu, Brandon Reagen, David Brooks, Bradford Cottel, Kim Hazelwood, Bill Jia, Hsien-Hsin S. Lee, Andrey Malevich, Dheevatsa Mudigere, Mikhail Smelyanskiy, Liang Xiong, Xuan Zhang

* 11 pages 

  Access Model/Code and Paper
Deep Learning Recommendation Model for Personalization and Recommendation Systems

May 31, 2019
Maxim Naumov, Dheevatsa Mudigere, Hao-Jun Michael Shi, Jianyu Huang, Narayanan Sundaraman, Jongsoo Park, Xiaodong Wang, Udit Gupta, Carole-Jean Wu, Alisson G. Azzolini, Dmytro Dzhulgakov, Andrey Mallevich, Ilia Cherniavskii, Yinghai Lu, Raghuraman Krishnamoorthi, Ansha Yu, Volodymyr Kondratenko, Stephanie Pereira, Xianjie Chen, Wenlin Chen, Vijay Rao, Bill Jia, Liang Xiong, Misha Smelyanskiy

* 10 pages, 6 figures 

  Access Model/Code and Paper
Spatial-Winograd Pruning Enabling Sparse Winograd Convolution

Jan 08, 2019
Jiecao Yu, Jongsoo Park, Maxim Naumov


  Access Model/Code and Paper
On the Dimensionality of Embeddings for Sparse Features and Data

Jan 07, 2019
Maxim Naumov

* 8 pages, 2 figures 

  Access Model/Code and Paper
Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications

Nov 29, 2018
Jongsoo Park, Maxim Naumov, Protonu Basu, Summer Deng, Aravind Kalaiah, Daya Khudia, James Law, Parth Malani, Andrey Malevich, Satish Nadathur, Juan Pino, Martin Schatz, Alexander Sidorov, Viswanath Sivakumar, Andrew Tulloch, Xiaodong Wang, Yiming Wu, Hector Yuen, Utku Diril, Dmytro Dzhulgakov, Kim Hazelwood, Bill Jia, Yangqing Jia, Lin Qiao, Vijay Rao, Nadav Rotem, Sungjoo Yoo, Mikhail Smelyanskiy


  Access Model/Code and Paper
On Periodic Functions as Regularizers for Quantization of Neural Networks

Nov 24, 2018
Maxim Naumov, Utku Diril, Jongsoo Park, Benjamin Ray, Jedrzej Jablonski, Andrew Tulloch

* 11 pages, 7 figures 

  Access Model/Code and Paper
Bandana: Using Non-volatile Memory for Storing Deep Learning Models

Nov 15, 2018
Assaf Eisenman, Maxim Naumov, Darryl Gardner, Misha Smelyanskiy, Sergey Pupyrev, Kim Hazelwood, Asaf Cidon, Sachin Katti


  Access Model/Code and Paper
AdaBatch: Adaptive Batch Sizes for Training Deep Neural Networks

Feb 14, 2018
Aditya Devarakonda, Maxim Naumov, Michael Garland

* 14 pages 

  Access Model/Code and Paper
Parallel Complexity of Forward and Backward Propagation

Dec 18, 2017
Maxim Naumov

* 18 pages 

  Access Model/Code and Paper
Feedforward and Recurrent Neural Networks Backward Propagation and Hessian in Matrix Form

Sep 16, 2017
Maxim Naumov

* 23 pages, 4 figures 

  Access Model/Code and Paper