We study optimistic bilevel optimization when the lower-level problem has a non-isolated manifold of minimizers. In this setting, the hyper-objective may be non-differentiable because the upper-level criterion must choose among multiple lower-level solutions. Under a local Polyak--Łojasiewicz (PŁ) condition, we show that differentiability does not require the lower-level solution set to be a singleton: uniqueness of the optimistic selection is sufficient. This yields an explicit pseudoinverse-based hyper-gradient formula extending the classical singleton-minimizer result. We further characterize the regularity of the hyper-objective: non-degeneracy of the selected minimizer along the solution manifold yields local smoothness, while failure of uniqueness can create many non-differentiable points and failure of non-degeneracy can destroy all positive Hölder regularity of the hyper-gradient. Motivated by this theory, we propose HG-MS, a select-then-differentiate method combining explicit optimistic selection with efficient pseudoinverse-based hyper-gradient computation. Despite the nonconvex nature of optimistic selection over the lower-level solution manifold, we show that HG-MS converges to a stationary point of the optimistic objective with complexity governed by the intrinsic dimension of the solution manifold rather than its ambient dimension. Empirically, we test a practical variant of HG-MS for matched-budget LLM source reweighting. This variant preserves the select-then-differentiate principle and obtains the best GSM8K/MATH scores across the tested backbones, along with competitive or best MT-Bench instruction-following results.
Bilevel Optimization of Agent Skills via Monte Carlo Tree Search
Department of Mathematics(数学系);National University of Singapore(国立新加坡大学);Department of Industrial Engineering and Operations Research(工业工程与运营管理系);University of California at Berkeley(加州大学伯克利分校);Department of Decision, Operation and Technology(决策、运营与技术系);The Chinese University of Hong Kong(香港中文大学)
Alternating Gradient-Type Algorithm for Bilevel Optimization with Inexact Lower-Level Solutions via Moreau Envelope-based Reformulation
Southern University of Science and Technology(南方科技大学);National Center for Applied Mathematics Shenzhen(深圳应用数学国家研究中心);City University of Hong Kong(香港城市大学)
Bilevel Optimization for Feature Selection in the Data-Driven Newsvendor Problem
Technical University of Munich(慕尼黑工业大学);Munich Data Science Institute(慕尼黑数据科学研究所);Polytechnique Montréal(蒙特利尔理工大学);Pontifical Catholic University of Rio de Janeiro(里约热内卢天主教大学)
Bilevel Optimization over Saddle Points of Zero-Sum Markov Games
Shun Hing Institute of Advanced Engineering, The Chinese University of Hong Kong(香港中文大学先进工程学院);Department of Computer Science and Engineering, The Chinese University of Hong Kong(香港中文大学计算机科学与工程系)
An adaptively inexact first-order method for bilevel optimization with application to hyperparameter learning
EPSRC Centre for Doctoral Training in Statistical Applied Mathematics at Bath (SAMBa)(EPSRC统计应用数学博士培训中心(SAMBa));Department of Mathematical Sciences, University of Bath(巴斯大学数学科学系);Department of Electronics & Electrical Communication Engineering, Indian Institute of Technology (IIT), Kharagpur(印度理工学院(Kharagpur)电子与电气通信工程系);School of Mathematics and Statistics, University of Sydney(悉尼大学数学与统计学学院)
Moreau Envelope Based Difference-of-weakly-Convex Reformulation and Algorithm for Bilevel Programs
University of British Columbia(不列颠哥伦比亚大学);University of Victoria(维多利亚大学);Southern University of Science and Technology(南方科技大学);National Center for Applied Mathematics Shenzhen(深圳国家应用数学中心);Peng Cheng Laboratory(鹏城实验室)
S$^3$LDBO: A Snapshot Single-Loop Algorithm for Decentralized Bilevel Optimization
School of Mathematics, Hohai University(河海大学数学学院);School of Mathematics, Nanjing University(南京大学数学学院);Department of Computational Applied Mathematics and Operations Research, Rice University(理海大学计算应用数学与运筹学系)
On the role of semismoothness in the implicit programming approach to selected nonsmooth optimization problems
Institute of Information Theory and Automation, Czech Academy of Sciences(捷克科学院信息论与自动化研究所);Johann Radon Institute for Computational and Applied Mathematics (RICAM), Austrian Academy of Sciences(奥地利科学院约翰·拉登计算与应用数学研究所);School of Mathematics, University of Birmingham(伯明翰大学数学学院)
An Efficient Smoothing Damped Newton Method for Large-Scale Mathematical Programs with Equilibrium Constraints
School of Mathematics and Statistics, Beijing Institute of Technology(北京理工大学数学与统计学院);National Frontiers Science center for Industrial Intelligence and Systems Optimization, Northeastern University(东北大学工业智能与系统优化前沿科学中心)
Implicit differentiation for fast hyperparameter selection in non-smooth convex learning
Université Paris-Saclay(巴黎萨克雷大学);Inria(法国国家信息与自动化研究所);CEA(法国原子能和替代能源委员会);Université de Bourgogne(勃艮第大学);Institut Mathématique de Bourgogne(勃艮第数学研究所);Università degli Studi di Genova(热那亚大学);Google Research(谷歌研究院);CNRS(法国国家科学研究中心);Université de Montpellier(蒙彼利埃大学)