AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

On the Equivalence between Neural Network and Support Vector Machine

Yilan Chen, Wei Huang, Lam M. Nguyen, Tsui-Wei Weng

NeurIPS 2021 · Optimization › Implicit bias and generalization · approach: Neural tangent kernel analysis · 2 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
increase NN hidden width from 10^3 to 10^6 (ablation)two-layer ReLU NN · MNIST 0/1 (100 test)robustness certificate (x1e-3): 7.4485 -> 0.31539Hurt
increase NN hidden width from 10^3 to 10^6 (ablation)two-layer ReLU NN · MNIST 0/1 (full test)robustness certificate (x1e-3): 7.2708 -> 0.30997Hurt
replace finite-width NN (10^6) with equivalent infinite-width SVM certificateNN robustness certification · MNIST 0/1 (100 test)robustness certificate (x1e-3): 0.31539 -> 8.0541Improved
use KRR with l2 regularization lambda=1000 instead of lambda=0 (ablation)KRR with NTK · MNIST 0/1robustness certificate: 790.06XImproved
use KRR with l2 regularization lambda=100 instead of lambda=0 (ablation)KRR with NTK · MNIST 0/1robustness certificate: 619.50XImproved
use KRR with l2 regularization lambda=10 instead of lambda=0 (ablation)KRR with NTK · MNIST 0/1robustness certificate: 156.90XImproved
use KRR with l2 regularization lambda=0.001 instead of lambda=0 (ablation)KRR with NTK · MNIST 0/1robustness certificate: 1.14XImproved
increase KRR lambda from 0 to 1000 (ablation)KRR with NTK · MNIST 0/1test accuracy: 99.95 -> 99.76Hurt
use soft margin SVM (lambda 0.064) instead of lambda=0 KRRSVM with NTK · MNIST 0/1robustness certificate: 243.91XImproved
use wider NN (10K vs narrower) when comparing training dynamics to SVM (ablation)NN trained with soft margin loss · MNIST 0/1agreement of output dynamics with SVMImproved

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