Pith. sign in

REVIEW 3 cited by

CB$^2$O: Consensus-Based Bi-Level Optimization

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2411.13394 v2 pith:3PRAAASY submitted 2024-11-20 math.OC math.AP

classification math.OCmath.AP
keywords optimizationbi-levelsolutionobjectivegloballearningconsensusconsensus-based
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Bi-level optimization problems, where one wishes to find the global minimizer of an upper-level objective function over the globally optimal solution set of a lower-level objective, arise in a variety of scenarios throughout science and engineering, machine learning, and artificial intelligence. In this paper, we propose and investigate, analytically and experimentally, consensus-based bi-level optimization (CB$^2$O), a multi-particle metaheuristic derivative-free optimization method designed to solve bi-level optimization problems when both objectives may be nonconvex. Our method leverages within the computation of the consensus point a carefully designed particle selection principle implemented through a suitable choice of a quantile on the level of the lower-level objective, together with a Laplace principle-type approximation w.r.t. the upper-level objective function, to ensure that the bi-level optimization problem is solved in an intrinsic manner. We give an existence proof of solutions to a corresponding mean-field dynamics, for which we first establish the stability of our consensus point w.r.t. a combination of Wasserstein and $L^2$ perturbations, and consecutively resort to PDE considerations extending the classical Picard iteration to construct a solution. For such solution, we provide a global convergence analysis in mean-field law showing that the solution of the associated nonlinear nonlocal Fokker-Planck equation converges exponentially fast to the unique solution of the bi-level optimization problem provided suitable choices of the hyperparameters. The practicability and efficiency of our CB$^2$O algorithm is demonstrated through extensive numerical experiments in the settings of constrained global optimization, sparse representation learning, and robust (clustered) federated learning.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Regularity and positivity of solutions of the Consensus-Based Optimization equation: unconditional global convergence

    math.AP 2025-02 conditional novelty 7.0 of 10

    For d>1, smooth solutions of the CBO Fokker-Planck equation are positive away from the consensus point, so the usual initial-support condition for global convergence can be dropped.

  2. Exploiting Structure with Anisotropic Consensus-Based Optimization

    math.OC 2026-07 accept novelty 6.0 of 10

    Anisotropic CBO's computational complexity depends exponentially only on the intrinsic dimension of an additively separable objective, not the ambient dimension, under aligned anisotropic noise.

  3. Consensus-based optimization for closed-box adversarial attacks and a connection to evolution strategies

    math.OC 2025-06 conditional novelty 5.0 of 10

    Consensus-based optimization matches or beats natural evolution strategies as a closed-box adversarial attack method in easier attack scenarios, and consensus hopping is shown to be a gradient-descent-like limit of CBO.

Pith tools