AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Achieving $\mathcal{O}(\epsilon^{-1.5})$ Complexity in Hessian/Jacobian-free Stochastic Bilevel Optimization

Yifan Yang, Peiyao Xiao, Kaiyi Ji

NeurIPS 2023 · Optimization › Nonconvex and smooth optimization · approach: Penalty and implicit-gradient bilevel methods · 0 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
use FdeHBO instead of PZOBO-S, F2SA and F3SA7-layer LeNet hyper-representation · MNIST hyper-representationouter loss and accuracy vs running timeImproved
use FMBO instead of stocBiO and AID-FPdata hyper-cleaning, linear classifier · MNIST, noise p = 0.1, 20000 train / 5000 valtraining lossImproved
use FMBO instead of single-loop FSLA and SOBAdata hyper-cleaning · MNISTconvergence speed and training lossImproved
compare AmIGO with stocBiOdata hyper-cleaning · MNISTperformanceNo clear effect
add auxiliary projection on v updates (ablation)FdeHBO · theoryboundedness of LS error and varianceImproved

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