Research map / Optimization / Nonconvex and smooth optimization
Enhanced Bilevel Optimization via Bregman Distance
Feihu Huang, Junyi Li, Shangqian Gao, Heng Huang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| ASBiO-BreD versus best baseline AID_BiO at 60s | ASBiO-BreD · Omniglot 5-way-1-shot (L1) | validation accuracy: 0.7762 -> 0.7830 | Improved |
| ASBiO-BreD versus best baseline AID_BiO at 60s | ASBiO-BreD · Omniglot 5-way-5-shot (L1) | validation accuracy: 0.9032 -> 0.9313 | Improved |
| ASBiO-BreD versus VR-saBiAdam at 20s | ASBiO-BreD · Omniglot 5-way-1-shot (L1) | validation accuracy: 0.6812 -> 0.6653 | Hurt |
| ASBiO-BreD versus FSLA at 20s | ASBiO-BreD · Omniglot 5-way-1-shot (L1) | validation accuracy: 0.6539 -> 0.6653 | Improved |
| ASBiO-BreD versus AID_BiO at 40s | ASBiO-BreD · Omniglot 5-way-1-shot (L1) | validation accuracy: 0.7365 -> 0.7403 | Improved |
| ASBiO-BreD versus AID_BiO at 20s | ASBiO-BreD · Omniglot 5-way-5-shot (L1) | validation accuracy: 0.8316 -> 0.8529 | Improved |
| ASBiO-BreD versus AID_BiO at 40s | ASBiO-BreD · Omniglot 5-way-5-shot (L1) | validation accuracy: 0.8779 -> 0.8967 | Improved |
| Longer running time (20s to 60s) | ASBiO-BreD · Omniglot 5-way-1-shot (L1) | validation accuracy: 0.6653 -> 0.7830 | Improved |
| Longer running time (20s to 60s) | ASBiO-BreD · Omniglot 5-way-5-shot (L1) | validation accuracy: 0.8529 -> 0.9313 | Improved |
| ASBiO-BreD versus MRBO (SPIDER-based) at 60s | ASBiO-BreD · Omniglot 5-way-1-shot (L1) | validation accuracy: 0.7519 -> 0.7830 | Improved |
| ASBiO-BreD versus VRBO at 60s | ASBiO-BreD · Omniglot 5-way-5-shot (L1) | validation accuracy: 0.8745 -> 0.9313 | Improved |
| ASBiO-BreD versus ITD_BiO at 60s | ASBiO-BreD · Omniglot 5-way-5-shot (L1) | validation accuracy: 0.8968 -> 0.9313 | Improved |
Closest papers by meaning
- TSP: A Two-Sided Smoothed Primal-Dual Method for Nonconvex Bilevel Optimization (ICML 2025 · similarity 0.90)
- Efficient Curvature-Aware Hypergradient Approximation for Bilevel Optimization (ICML 2025 · similarity 0.90)
- Tuning-Free Bilevel Optimization: New Algorithms and Convergence Analysis (ICLR 2025 · similarity 0.89)
- Provably Faster Algorithms for Bilevel Optimization via Without-Replacement Sampling (NeurIPS 2024 · similarity 0.89)
- Bilevel Optimization under Unbounded Smoothness: A New Algorithm and Convergence Analysis (ICLR 2024 · similarity 0.89)
- Optimal Hessian/Jacobian-Free Nonconvex-PL Bilevel Optimization (ICML 2024 · similarity 0.89)
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.
