AI Paper Atlas

Research map / Optimization / Implicit bias and generalization

Symmetry Teleportation for Accelerated Optimization

Bo Zhao, Nima Dehmamy, Robin Walters, Rose Yu

NeurIPS 2022 · Optimization › Implicit bias and generalization · approach: Low-rank and single-index recovery · 3 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
add symmetry teleportation to gradient descentGradient descent · Rosenbrock functionsteps to reach targetImproved
add symmetry teleportation to gradient descentGradient descent · Booth functionconvergence rateImproved
add teleportation to GD and AdaGradGD, AdaGrad · 3-layer network regressionepochs and time to convergenceImproved
add teleportation to SGDSGD · MNISTtraining lossImproved
add teleportation to AdaGradAdaGrad · MNISTvalidation lossHurt
add teleportationSGD · MNISTvalidation accuracyHurt
teleport before training instead of after epoch 0 (ablation)SGD with teleportation · MNISTtraining lossHurt
teleport earlier (after epoch 0) (ablation)SGD with teleportation · MNISTtraining lossImproved
smaller intervals between teleportations (ablation)SGD with teleportation · MNISTconvergence speedImproved
teleport using more mini-batches (ablation)SGD with teleportation · MNISTtraining lossImproved

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