{"url":"/task/bilevel-optimization","name":"Bilevel Optimization","slug":"bilevel-optimization","description_markdown":"**Bilevel Optimization** is a branch of optimization, which contains a nested optimization problem within the constraints of the outer optimization problem. The outer optimization task is usually referred as the upper level task, and the nested inner optimization task is referred as the lower level task. The lower level problem appears as a constraint, such that only an optimal solution to the lower level optimization problem is a possible feasible candidate to the upper level optimization problem.\r\n\r\n\r\n<span class=\"description-source\">Source: [Efficient Evolutionary Algorithm for Single-Objective Bilevel Optimization ](https://arxiv.org/abs/1303.3901)</span>","categories":[{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":423,"papers_with_code":143,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/bilevel-optimization-on-equilibrium-traffic","slug":"bilevel-optimization-on-equilibrium-traffic","dataset":"Equilibrium-Traffic-Networks/Eastern Massachusetts","dataset_url":null,"rows_in_archive":1,"metrics":["Optimality Gap"],"first_row_in_archive_order":{"model":"GIN-GA","paper_title":"A hybrid deep-learning-metaheuristic framework for bi-level network design problems","paper_url":"/paper/a-hybrid-deep-learning-metaheuristic","paper_date":"2023-03-10","arxiv_id":"2303.06024","code_links":[{"title":"bahmanmdd/HDLMF_GIN-GA","url":"https://github.com/bahmanmdd/HDLMF_GIN-GA"}],"syntology":null}},{"leaderboard":"/sota/bilevel-optimization-on-equilibrium-traffic-1","slug":"bilevel-optimization-on-equilibrium-traffic-1","dataset":"Equilibrium-Traffic-Networks/Anaheim","dataset_url":null,"rows_in_archive":1,"metrics":["Optimality Gap"],"first_row_in_archive_order":{"model":"GIN-GA","paper_title":"A hybrid deep-learning-metaheuristic framework for bi-level network design problems","paper_url":"/paper/a-hybrid-deep-learning-metaheuristic","paper_date":"2023-03-10","arxiv_id":"2303.06024","code_links":[{"title":"bahmanmdd/HDLMF_GIN-GA","url":"https://github.com/bahmanmdd/HDLMF_GIN-GA"}],"syntology":null}},{"leaderboard":"/sota/bilevel-optimization-on-equilibrium-traffic-2","slug":"bilevel-optimization-on-equilibrium-traffic-2","dataset":"Equilibrium-Traffic-Networks/Sioux Falls","dataset_url":null,"rows_in_archive":1,"metrics":["Optimality Gap"],"first_row_in_archive_order":{"model":"GIN-GA","paper_title":"A hybrid deep-learning-metaheuristic framework for bi-level network design problems","paper_url":"/paper/a-hybrid-deep-learning-metaheuristic","paper_date":"2023-03-10","arxiv_id":"2303.06024","code_links":[{"title":"bahmanmdd/HDLMF_GIN-GA","url":"https://github.com/bahmanmdd/HDLMF_GIN-GA"}],"syntology":null}}],"datasets":[],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":143,"tagged_in_all":423,"items":[{"url":"/paper/adaptive-personalized-federated-learning","title":"Adaptive Personalized Federated Learning","date":"2020-03-30","arxiv_id":"2003.13461","repositories_listed":11,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/optnet-differentiable-optimization-as-a-layer","title":"OptNet: Differentiable Optimization as a Layer in Neural Networks","date":"2017-03-01","arxiv_id":"1703.00443","repositories_listed":8,"syntology":{"n":16,"n_ran":0,"n_unverified":16,"n_pointer_only":0}},{"url":"/paper/nystrom-method-for-accurate-and-scalable","title":"Nystrom Method for Accurate and Scalable Implicit Differentiation","date":"2023-02-20","arxiv_id":"2302.09726","repositories_listed":4,"syntology":null},{"url":"/paper/convex-and-bilevel-optimization-for-neuro","title":"Convex and Bilevel Optimization for Neuro-Symbolic Inference and Learning","date":"2024-01-17","arxiv_id":"2401.09651","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/second-order-sensitivity-analysis-for-bilevel","title":"Second-Order Sensitivity Analysis for Bilevel Optimization","date":"2022-05-04","arxiv_id":"2205.02329","repositories_listed":3,"syntology":null},{"url":"/paper/self-tuning-networks-bilevel-optimization-of","title":"Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions","date":"2019-03-07","arxiv_id":"1903.03088","repositories_listed":3,"syntology":null},{"url":"/paper/scalable-bilevel-loss-balancing-for-multi","title":"LDC-MTL: Balancing Multi-Task Learning through Scalable Loss Discrepancy Control","date":"2025-02-12","arxiv_id":"2502.08585","repositories_listed":2,"syntology":null},{"url":"/paper/fair-bilevel-neural-network-fairbinn-on","title":"Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via Stackelberg Equilibrium","date":"2024-10-21","arxiv_id":"2410.16432","repositories_listed":2,"syntology":{"n":20,"n_ran":6,"n_unverified":14,"n_pointer_only":3}},{"url":"/paper/embarassingly-simple-dataset-distillation","title":"Embarassingly Simple Dataset Distillation","date":"2023-11-13","arxiv_id":"2311.07025","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/self-supervised-set-representation-learning","title":"Self-Supervised Dataset Distillation for Transfer Learning","date":"2023-10-10","arxiv_id":"2310.06511","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/squeeze-recover-and-relabel-dataset","title":"Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective","date":"2023-06-22","arxiv_id":"2306.13092","repositories_listed":2,"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":6}},{"url":"/paper/generative-adversarial-method-based-on-neural","title":"Single-level Adversarial Data Synthesis based on Neural Tangent Kernels","date":"2022-04-08","arxiv_id":"2204.04090","repositories_listed":2,"syntology":null},{"url":"/paper/target-aware-dual-adversarial-learning-and-a","title":"Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection","date":"2022-03-30","arxiv_id":"2203.16220","repositories_listed":2,"syntology":null},{"url":"/paper/bilevel-optimization-with-a-lower-level","title":"Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-start","date":"2022-02-07","arxiv_id":"2202.03397","repositories_listed":2,"syntology":{"n":8,"n_ran":8,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/bobcat-bilevel-optimization-based","title":"BOBCAT: Bilevel Optimization-Based Computerized Adaptive Testing","date":"2021-08-17","arxiv_id":"2108.07386","repositories_listed":2,"syntology":{"n":10,"n_ran":10,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/provably-faster-algorithms-for-bilevel-1","title":"Bilevel Optimization: Convergence Analysis and Enhanced Design","date":"2020-10-15","arxiv_id":"2010.07962","repositories_listed":2,"syntology":{"n":18,"n_ran":9,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/adversarial-immunization-for-improving","title":"Adversarial Immunization for Certifiable Robustness on Graphs","date":"2020-07-19","arxiv_id":"2007.09647","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/learning-data-augmentation-with-online","title":"Learning Data Augmentation with Online Bilevel Optimization for Image Classification","date":"2020-06-25","arxiv_id":"2006.14699","repositories_listed":2,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/metapoison-practical-general-purpose-clean","title":"MetaPoison: Practical General-purpose Clean-label Data Poisoning","date":"2020-04-01","arxiv_id":"2004.00225","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/penalty-method-for-inversion-free-deep","title":"Penalty Method for Inversion-Free Deep Bilevel Optimization","date":"2019-11-08","arxiv_id":"1911.03432","repositories_listed":2,"syntology":null},{"url":"/paper/truncated-back-propagation-for-bilevel","title":"Truncated Back-propagation for Bilevel Optimization","date":"2018-10-25","arxiv_id":"1810.10667","repositories_listed":2,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/spectral-inference-networks-unifying-spectral","title":"Spectral Inference Networks: Unifying Deep and Spectral Learning","date":"2018-06-06","arxiv_id":"1806.02215","repositories_listed":2,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/guilomo-allocating-expert-number-and-rank-for","title":"GuiLoMo: Allocating Expert Number and Rank for LoRA-MoE via Bilevel Optimization with GuidedSelection Vectors","date":"2025-06-17","arxiv_id":"2506.14646","repositories_listed":1,"syntology":null},{"url":"/paper/misleader-defending-against-model-extraction","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","date":"2025-06-03","arxiv_id":"2506.02362","repositories_listed":1,"syntology":null},{"url":"/paper/learning-where-to-learn-training-distribution","title":"Learning Where to Learn: Training Distribution Selection for Provable OOD Performance","date":"2025-05-27","arxiv_id":"2505.21626","repositories_listed":1,"syntology":null},{"url":"/paper/gcal-adapting-graph-models-to-evolving-domain","title":"GCAL: Adapting Graph Models to Evolving Domain Shifts","date":"2025-05-22","arxiv_id":"2505.16860","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_unverified":3,"n_pointer_only":10}},{"url":"/paper/hbo-hierarchical-balancing-optimization-for","title":"HBO: Hierarchical Balancing Optimization for Fine-Tuning Large Language Models","date":"2025-05-18","arxiv_id":"2505.12300","repositories_listed":1,"syntology":null},{"url":"/paper/optimizing-decomposition-for-optimal-claim","title":"Optimizing Decomposition for Optimal Claim Verification","date":"2025-03-19","arxiv_id":"2503.15354","repositories_listed":1,"syntology":null},{"url":"/paper/prdp-progressively-refined-differentiable","title":"PRDP: Progressively Refined Differentiable Physics","date":"2025-02-26","arxiv_id":"2502.19611","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/adversarial-training-for-defense-against","title":"Adversarial Training for Defense Against Label Poisoning Attacks","date":"2025-02-24","arxiv_id":"2502.17121","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}],"syntology_records":18,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}