BIU Learning Club 9.5.2021 — Brain Chmiel — NEURAL GRADIENTS ARE NEAR-LOGNORMAL: IMPROVED QUANTIZED AND SPARSE TRAINING

The recording of Brian's talk is available here: https://us02web.zoom.us/rec/play/q1MhnoNJqMOBCBpADGABiGx7BUErjRyRe61hIsrWZeVwn5h0Jewn9JtO2z5BzYtFUrMB7dKckS2Us0RK.tsVtRh_-0qN13UJI Zoom: https://us02web.zoom.us/j/84467714967?pwd=MW5pR216eUlvMXRFK0g2WHpNbjBVQT09 Meeting ID: 844 6771 4967 Passcode: 149008 Title: NEURAL GRADIENTS ARE NEAR-LOGNORMAL: IMPROVED  QUANTIZED AND SPARSE TRAINING Abstract: While training can mostly be accelerated by reducing the time needed to propagate neural gradients (loss gradients with respect to the intermediate neural layer outputs) back ... Read more