AI Paper Atlas

Research map / Optimization / Optimizers

Stability and Generalization of Bilevel Programming in Hyperparameter Optimization

Fan Bao, Guoqiang Wu, Chongxuan Li, Jun Zhu, Bo Zhang

NeurIPS 2021 · Optimization › Optimizers · approach: Hypergradient bilevel optimization · 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
Use large inner-loop K and outer-loop T in unrolled differentiationUnrolled differentiation · Omniglot feature learning and MNIST data reweightingtesting lossHurt
Use small inner-loop K and outer-loop T in unrolled differentiationUnrolled differentiation · Omniglot feature learning and MNIST data reweightingvalidation fitHurt
Reduce the inner-loop learning rate and increase KUnrolled differentiation · Feature learning and data reweightingtesting lossHurt
Use random-search cross-validation instead of unrolled differentiation in a high-dimensional hyperparameter spaceCross-validation versus unrolled differentiation · Omniglot feature learningtesting lossHurt
Use cross-validation instead of unrolled differentiation when the hyperparameter space is smallerCross-validation versus unrolled differentiation · Feature learning and data reweighting with fewer hyperparameterstesting lossImproved
Add weight decay to the outer level (ablation)Unrolled differentiation · Omniglot feature learning and MNIST data reweightingtesting lossImproved
Add weight decay to the inner level (ablation)Unrolled differentiation · Omniglot feature learning and MNIST data reweightingtesting lossImproved
Add weight decay to both levels instead of using the better single-level regularizer (ablation)Unrolled differentiation · Omniglot feature learning and MNIST data reweightingtesting lossHurt
Use very heavy inner-level weight decay (ablation)Unrolled differentiation · MNIST data reweightingoptimization stabilityHurt

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