AI Paper Atlas

Research map / Optimization / Optimizers

Will Bilevel Optimizers Benefit from Loops

Kaiyi Ji, Mingrui Liu, Yingbin Liang, Lei Ying

NeurIPS 2022 · Optimization › Optimizers · approach: Hypergradient bilevel optimization · 4 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 a large inner loop (N-loop) instead of using small N (ablation)AID-BiO · Bilevel optimization, epsilon-accurate stationary pointMV(epsilon): \mathcal{\widetilde O}(\kappa^6\epsilon^{-1}) -> \mathcal{\widetilde O}(\kappa^4\epsilon^{-1})Improved
Add a large inner loop (N-loop) instead of using small N (ablation)AID-BiO · Bilevel optimization, epsilon-accurate stationary pointGc(epsilon): \mathcal{\widetilde O}(\kappa^6\epsilon^{-1}) -> \mathcal{\widetilde O}(\kappa^5\epsilon^{-1})Improved
Add a large Q loop for the Hessian-inverse-vector approximation (ablation)AID-BiO with N=1 · Bilevel optimization, epsilon-accurate stationary pointGc(epsilon): \mathcal{\widetilde O}(\kappa^6\epsilon^{-1}) -> \mathcal{\widetilde O}(\kappa^5\epsilon^{-1})Improved
Add a large Q loop for the Hessian-inverse-vector approximation (ablation)AID-BiO with N=1 · Bilevel optimization, epsilon-accurate stationary pointMV(epsilon): \mathcal{\widetilde O}(\kappa^6\epsilon^{-1}) -> \mathcal{\widetilde O}(\kappa^6\epsilon^{-1})No clear effect
Use N=20 rather than N=1 (ablation)ITD-BiO · Hyper-representation validation loss at k=500validation loss: 0.04 -> 0.004Improved
Use N=20 rather than N=1 (ablation)ITD-BiO · Hyper-representation validation loss at k=1000validation loss: 0.04 -> 0.004Improved
Use N=20 rather than N=1 (ablation)AID-BiO · MNIST hyperparameter optimizationtraining and test loss versus running timeImproved
Increase Q while keeping N fixed (ablation)AID-BiO · MNIST hyperparameter optimizationconvergence performanceNo clear effect

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