Bilevel Optimization
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
96 papers10 papers in the last four weeks, down 23% on the four weeks before. 0.1% of all new papers.
Your Hypergradient is Skewed: Antithetic Neumann Estimation for Bilevel Optimization
On Generalization in Bilevel Least Squares with Overparameterized Neural Networks
Lower-Level Agnostic Bilevel Optimization
A Theoretical Analysis of a Bilevel Optimization Formulation for Combined Local-Global Optical Flow Models
A Bilevel Neurodynamic Approach for Distributed SCAD-Regularized Sparse Least Squares
Differentiable Iterative Learning Control for Black-Box Position-Commanded Manipulators
Structure-Actuation Co-Design of All-Electric Heavy-Duty Robotic Manipulators
Decentralized Bi-Level Optimization for Cooperative Orbital Transportation of a Rigid Payload
Newton-Based Methods for Bilevel Optimization Beyond Lower-Level Strong Convexity
Accelerating Finite-Sum Bilevel Optimization with Fully First-Order Oracles
Probabilistic Multi-Source Data Selection via Learnable Categorical Priors: Variance Reduction and Guaranteed Derandomization
A Single-Loop, Constant-Batch First-Order Penalty Method for Stochastic Bilevel Optimization
Smoothed Gradient Method for Nonconvex Federated Stochastic Bilevel Optimization
Optimal Stochastic Bilevel Optimization with First-Order Oracles
Anchoring Adversarial Trajectories to Data Manifolds: A Bilevel Transfer Optimization Framework
Dr. OPD: Learning What to Follow for Optimal On-Policy Distillation of Large Language Models
BRIDGE: Bilevel Retrieval-Credit-Aware Agentic Reinforcement Learning
Learning the Robustness Mechanism with Bilevel Optimization
Learning to Re-Draft: A Variational Stackelberg Game for Discrete Diffusion
A Light Bilevel Refinement Aligns Self-Supervised Representations for Stronger Task-Specific Learning
ABO-Med: Accelerated Bilevel Optimization for Few-Shot Medical Image Classification
To Solve Bilevel Optimization with Nonconvex Lower Levels, We Need Second-Order Stationarity
Bilevel Optimization of Topology and Hyperparameters (BOTH)
magic numbers''---hyperparameters whose tuning significantly affects the outcome. Finding the right values typically requires not only deep problem-specific knowledge but also extensive trial-and-error. While practitioners can use surrogate-assisted hyperparameter optimization as an alternative, this approach requires strictly limiting the number of hyperparameters through careful problem formulation. Here, we propose differentiating TO itself using automatic differentiation. This yields hypergradients'' that allow us to tune these hyperparameters in tandem with the primary optimization. We show that evaluating just one or two steps of TO is sufficiently informative and that the method scales favorably to thousands of hyperparameters at an expense comparable to only a few standard TO runs. We demonstrate this approach on stress-constrained and compliance problems, with the latter utilizing a neural parameterization of the density field.