conftrace_

stochastic gradient estimation

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

quantized training (1) on-device training (1) fixed-point arithmetic (1) memory footprint (1) forward gradient (1) edge deployment (1) edge computing (1) memory efficiency (1) loss landscape (1) model compression (1)

Papers

Stepping Forward on the Last Mile NeurIPS 2024