2020 IEEE International Symposium
on Information Theory
21-26 June 2020 • Los Angeles, California, USA
L.6: Gradient-Based Distributed Learning | |
| Session Type: Lecture | |
| Track: Statistics and Learning Theory | |
| Virtual Session: View on Virtual Platform | |
| Session Chair: Chao Tian, Texas A&M University | |
| L.6.1: Hierarchical Coded Gradient Aggregation for Learning at the Edge | |
| Click here to download the manuscript | |
| Click here to view the Virtual Presentation | |
| Saurav Prakash; University of Southern California | |
| Amirhossein Reisizadeh; UC Santa Barbara | |
| Ramtin Pedarsani; UC Santa Barbara | |
| Amir Salman Avestimehr; University of Southern California | |
| L.6.2: Numerically Stable Binary Gradient Coding | |
| Click here to download the manuscript | |
| Click here to view the Virtual Presentation | |
| Neophytos Charalambides; University of Michigan | |
| Hessam Mahdavifar; University of Michigan | |
| Alfred Hero; University of Michigan | |
| L.6.3: On Byzantine-Resilient High-Dimensional Stochastic Gradient Descent | |
| Click here to download the manuscript | |
| Click here to view the Virtual Presentation | |
| Deepesh Data; University of California, Los Angeles | |
| Suhas Diggavi; University of California, Los Angeles | |
| L.6.4: Communication-Efficient Gradient Coding for Straggler Mitigation in Distributed Learning | |
| Click here to download the manuscript | |
| Click here to view the Virtual Presentation | |
| Swanand Kadhe; University of California Berkeley | |
| O. Ozan Koyluoglu; University of California Berkeley | |
| Kannan Ramchandran; University of California Berkeley | |
Plan Ahead
2021 IEEE International Symposium on Information Theory
11-16 July 2021 | Melbourne, Victoria, Australia
