From the 1 of 1.7k papers with an AI index.
24.4k citations
- University of California, BerkeleyUS97 papers
- Stanford UniversityUS80 papers
- Massachusetts Institute of TechnologyUS73 papers
- Google DeepMind (United Kingdom)GB59 papers
- Carnegie Mellon UniversityUS54 papers
- University of TorontoCA52 papers
- Princeton UniversityUS49 papers
- Cornell UniversityUS46 papers
- University of Illinois Urbana-ChampaignUS38 papers
- Columbia UniversityUS35 papers
- University of California, Santa BarbaraUS33 papers
- University of WashingtonUS33 papers
348 papers · 1 filter
Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies
Paul Vicol, Luke Metz, Jascha Sohl-Dickstein
Unrolled computation graphs arise in many scenarios, including training RNNs, tuning hyperparameters through unrolled optimization, and training learned optimizers. Current approac…
Energy-Proportional Data Center Network Architecture Through OS, Switch and Laser Co-design
Haiyang Han, Nikos Terzenidis, Dimitris Syrivelis +8
Optical interconnects are already the dominant technology in large-scale data center networks. However, the high optical loss of many optical components coupled with the low effici…
Privacy Guarantees of BLE Contact Tracing: A Case Study on COVIDWISE
Salman Ahmed, Ya Xiao, Taejoong +5
Google and Apple jointly introduced a digital contact tracing technology and an API called "exposure notification," to help health organizations and governments with contact tracin…
Information is Power: Intrinsic Control via Information Capture
Nicholas Rhinehart, Jenny Wang, Glen Berseth +4
Humans and animals explore their environment and acquire useful skills even in the absence of clear goals, exhibiting intrinsic motivation. The study of intrinsic motivation in art…
Noether Networks: Meta-Learning Useful Conserved Quantities
Ferran Alet, Dylan Doblar, Allan Zhou +3
Progress in machine learning (ML) stems from a combination of data availability, computational resources, and an appropriate encoding of inductive biases. Useful biases often explo…
Revisiting dequantization and quantum advantage in learning tasks
Jordan Cotler, Hsin-Yuan Huang, Jarrod R. McClean
It has been shown that the apparent advantage of some quantum machine learning algorithms may be efficiently replicated using classical algorithms with suitable data access -- a pr…