Overview

Bilevel optimization models decisions in two levels: an outer problem evaluates choices using the solution of an inner problem, as in hyperparameter tuning, data selection, meta-learning, and neural architecture search. Common approaches differentiate through inner optimization using unrolling or implicit hypergradients, while single-loop stochastic, penalty-based, and derivative-free methods aim to reduce computation and handle larger or black-box problems. Applications also use the framework for decision-focused learning, reinforcement learning, and strategic settings where one agent responds to another. A central challenge is making these methods efficient and reliable when the inner problem is nonconvex or has multiple solutions, while establishing useful convergence and generalization guarantees without restrictive assumptions.

Latest papers

CardsList

96 papers10 papers in the last four weeks, down 23% on the four weeks before. 0.1% of all new papers.

  1. Non-Stationary Functional Bilevel Optimization

    Jan 21, 2026Jason Bohne, Ieva Petrulionyte, Michael Arbel +2Bilevel OptimizationHyperparameter Optimization

  2. OFMU: Optimization-Driven Framework for Machine Unlearning

    Sep 26, 2025Sadia Asif, Mohammad Mohammadi AmiriBilevel OptimizationMachine Unlearning

  3. A Provably Convergent Plug-and-Play Framework for Stochastic Bilevel Optimization

    May 2, 2025Tianshu Chu, Dachuan Xu, Wei Yao +2Stochastic Bilevel OptimizationBilevel Optimization

  4. Bilevel ZOFO: Efficient LLM Fine-Tuning and Meta-Training

    Feb 5, 2025Reza Shirkavand, Peiran Yu, Qi He +1LLM Fine-TuningZeroth-Order Optimization