AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

An Efficient Training Framework for Reversible Neural Architectures

Zixuan Jiang, Keren Zhu, Mingjie Liu, Jiaqi Gu, David Z. Pan

ECCV 2020 · Architectures and efficiency › RNNs and normalization · approach: Efficient network compression and training · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
choose per-layer M/C modes by knapsack DP instead of all-reversible (baseline-M)Reformer on enwik8 · enwik8, batch size 1relative speedup: 1.321 -> 0.949 s per sample; speedup 1.392Improved
choose per-layer M/C modes by knapsack DP instead of all-reversible (baseline-M)Reformer on enwik8 · enwik8, batch size 3training time per sample (s): 1.201 -> 0.917Improved
choose per-layer M/C modes by knapsack DP instead of all-reversible (baseline-M)Reformer on enwik8 · enwik8, batch size 10training time per sample (s): 1.187 -> 1.129Improved
choose per-layer M/C modes by knapsack DP instead of all-reversible (baseline-M)RevNet-104 · ImageNet (mini-batch sweep)relative speedup: up to 1.15xImproved
choose per-layer M/C modes by knapsack DP instead of all-reversible (baseline-M)ResNeXt-101 with Inplace ABN · ImageNet (mini-batch sweep)relative speedup: baseline-C only 0.8-2% faster than baseline-MImproved
increase mini-batch size when baseline-C is feasibleReformer on enwik8 · enwik8training time per sample (s): 0.869 at batch size 2 is lowestHurt
enable reversibility (M-Mode) to allow larger batches than baseline-CReformer on enwik8 · enwik8max feasible batch size: 2 -> 10Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy