Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Dynamic Network Adaptation at Inference


Apr 18, 2022
Daniel Mendoza, Caroline Trippel


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

RecShard: Statistical Feature-Based Memory Optimization for Industry-Scale Neural Recommendation


Jan 25, 2022
Geet Sethi, Bilge Acun, Niket Agarwal, Christos Kozyrakis, Caroline Trippel, Carole-Jean Wu


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Analysis and Mitigations of Reverse Engineering Attacks on Local Feature Descriptors


May 09, 2021
Deeksha Dangwal, Vincent T. Lee, Hyo Jin Kim, Tianwei Shen, Meghan Cowan, Rajvi Shah, Caroline Trippel, Brandon Reagen, Timothy Sherwood, Vasileios Balntas, Armin Alaghi, Eddy Ilg

* 13 pages 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

RecSSD: Near Data Processing for Solid State Drive Based Recommendation Inference


Jan 29, 2021
Mark Wilkening, Udit Gupta, Samuel Hsia, Caroline Trippel, Carole-Jean Wu, David Brooks, Gu-Yeon Wei


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

CPR: Understanding and Improving Failure Tolerant Training for Deep Learning Recommendation with Partial Recovery


Nov 05, 2020
Kiwan Maeng, Shivam Bharuka, Isabel Gao, Mark C. Jeffrey, Vikram Saraph, Bor-Yiing Su, Caroline Trippel, Jiyan Yang, Mike Rabbat, Brandon Lucia, Carole-Jean Wu


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email