# Geometric and computational hardness of bilevel programming

arXiv: https://arxiv.org/abs/2407.12372 · HTML: https://mlsanity.com/paper/2407.12372/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2024.

## Built on by (most cited first, 4 of 4)

- [Optimizing Pre-Training Data Mixtures with Mixtures of Data Expert Models](https://mlsanity.com/paper/2502.15950/) (2025)
- [Differentially Private Bilevel Optimization](https://mlsanity.com/paper/2409.19800/) (2024)
- [Learning Theory for Kernel Bilevel Optimization](https://mlsanity.com/paper/2502.08457/) (2025)
- [Prediction-Intervention Games and Invariant Sets](https://mlsanity.com/paper/2605.16828/) (2026)

## Abstract (arXiv)

We first show a simple but striking result in bilevel optimization: unconstrained C^∞ smooth bilevel programming is as hard as general extended-real-valued lower semicontinuous minimization. We then proceed to a worst-case analysis of box-constrained bilevel polynomial optimization. We show in particular that any extended-real-valued semi-algebraic function, possibly non-continuous, can be expressed as the value function of a polynomial bilevel program. Secondly, from a computational complexity perspective, the decision version of polynomial bilevel programming is one level above NP in the polynomial hierarchy (Sigmap2-hard). Both types of difficulties are uncommon in non-linear programs for which objective functions are typically continuous and belong to the class NP. These results highlight the irremediable hardness attached to general bilevel optimization and the necessity of imposing some form of regularity on the lower level.