Skip to content
conftrace_

layer replacement

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

activation checkpointing (1) binary decision (1) neural network (1) transformer model (1) backpropagation algorithm (1) convolution layer (1) gradient accumulation (1) transformer training (1) memory optimization (1) decision tree (1)

Papers

Tempo: Accelerating Transformer-Based Model Training through Memory Footprint Reduction NeurIPS 2022 Training Decision Trees as Replacement for Convolution Layers AAAI 2020