AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Learning Discretized Neural Networks under Ricci Flow

Jun Chen, Hanwen Chen, Mengmeng Wang, Guang Dai, Ivor W. Tsang, Yong Liu

JMLR 2024 · Optimization › Implicit bias and generalization · approach: Neural tangent kernel analysis · 5 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
replace Dorefa gradient with RF-DNN Ricci-flow gradient (ResNet20) (ablation)binarized ResNet training with straight-through estimators · CIFAR-10 (1-bit weights, from scratch)test accuracy (%): 88.28 -> 89.83Improved
replace MultiFCG gradient with RF-DNN (ResNet32) (ablation)binarized ResNet training with straight-through estimators · CIFAR-10 (1-bit weights, from scratch)test accuracy (%): 89.63 -> 90.75Improved
replace Dorefa gradient with RF-DNN (ResNet44) (ablation)binarized ResNet training with straight-through estimators · CIFAR-10 (1-bit weights, from scratch)test accuracy (%): 90.71 -> 91.63Improved
replace FCGrad gradient with RF-DNN (ResNet56) (ablation)binarized ResNet training with straight-through estimators · CIFAR-100 (1-bit weights, from scratch)test accuracy (%): 66.56 -> 68.56Improved
replace FCGrad gradient with RF-DNN (ResNet110) (ablation)binarized ResNet training with straight-through estimators · CIFAR-100 (1-bit weights, from scratch)test accuracy (%): 68.74 -> 69.20Improved
replace Dorefa gradient with RF-DNN (ResNet18) (ablation)binarized ResNet training with straight-through estimators · ImageNet (1-bit weights, from scratch)top-1 accuracy (%): 58.34 -> 60.83Improved
replace FCGrad gradient with RF-DNN (ResNet18) (ablation)binarized ResNet training with straight-through estimators · ImageNet (1-bit weights, from scratch)top-5 accuracy (%): 82.67 -> 83.54Improved
replace MultiFCG gradient with RF-DNN (ResNet44) (ablation)binarized ResNet training with straight-through estimators · CIFAR-10 (1-bit weights, from scratch)test accuracy (%): 90.54 -> 91.63Improved

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