AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

LCA: Loss Change Allocation for Neural Network Training

Janice Lan, Rosanne Liu, Hattie Zhou, Jason Yosinski

NeurIPS 2019 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width · 17 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
Freeze the last layer at initialization (ablation)CIFAR-ResNet with SGD · CIFAR-10train lossImproved
Freeze the last layer at initialization (ablation)CIFAR-ResNet with SGD · CIFAR-10test lossImproved
Reduce the last layer learning rate by 10x (ablation)CIFAR-ResNet with SGD · CIFAR-10layer LCA: 0.01 as opposed to 0.1Mixed
Freeze the first layer at initialization (ablation)CIFAR-ResNet with SGD · CIFAR-10overall performanceNo clear effect
Reduce the first layer learning rate by 10x (ablation)CIFAR-ResNet with SGD · CIFAR-10layer LCANo clear effect
Freeze the last layer at initialization (ablation)CIFAR-AllCNN with SGD · CIFAR-10overall lossHurt
Use RK4 rather than first-order Taylor approximation (ablation)LCA estimation · CIFAR-ResNet, SGDtotal loss error: -1189.71\% (first-order) versus 0.0345\% (RK4)Improved
Vary learning rate, momentum, or batch size within ranges where training remains effective (ablation)CIFAR-ResNet with SGD · CIFAR-10helping parameters (%): 50.3\% to 51.6\%No clear effect
Increase mini-batch size to 5000 (ablation)CIFAR-ResNet with SGD · CIFAR-10test performance: 56.2\%Hurt
Increase momentum to 0.99 (ablation)CIFAR-ResNet with SGD · CIFAR-10train and test performance: 53.5\%Hurt
Give the last layer a fresher-information advantage by reducing its momentum delay (ablation)CIFAR-ResNet with SGD · CIFAR-10last-layer LCAImproved

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