{"total":81,"rows":[{"id":"2309.01753","title":"On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation","created":"2023-09-04","cited_by_count":51,"area":null},{"id":"2308.00788","title":"An Introduction to Bi-level Optimization: Foundations and Applications in Signal Processing and Machine Learning","created":"2023-08-01","cited_by_count":41,"area":null},{"id":"2406.19976","title":"ScaleBiO: Scalable Bilevel Optimization for LLM Data Reweighting","created":"2024-06-28","cited_by_count":37,"area":null},{"id":"2306.12067","title":"Optimal Algorithms for Stochastic Bilevel Optimization under Relaxed Smoothness Conditions","created":"2023-06-21","cited_by_count":31,"area":null},{"id":"2306.14853","title":"Near-Optimal Nonconvex-Strongly-Convex Bilevel Optimization with Fully First-Order Oracles","created":"2023-06-26","cited_by_count":17,"area":null},{"id":"2310.05674","title":"Making Scalable Meta Learning Practical","created":"2023-10-09","cited_by_count":17,"area":null},{"id":"2302.08766","title":"A Lower Bound and a Near-Optimal Algorithm for Bilevel Empirical Risk Minimization","created":"2023-02-17","cited_by_count":16,"area":null},{"id":"2401.16164","title":"Constrained Bi-Level Optimization: Proximal Lagrangian Value function Approach and Hessian-free Algorithm","created":"2024-01-29","cited_by_count":16,"area":null},{"id":"2405.09927","title":"Moreau Envelope for Nonconvex Bi-Level Optimization: A Single-loop and Hessian-free Solution Strategy","created":"2024-05-16","cited_by_count":16,"area":null},{"id":"2401.09587","title":"Bilevel Optimization under Unbounded Smoothness: A New Algorithm and Convergence Analysis","created":"2024-01-17","cited_by_count":15,"area":null},{"id":"2303.03944","title":"On Momentum-Based Gradient Methods for Bilevel Optimization with Nonconvex Lower-Level","created":"2023-03-07","cited_by_count":14,"area":null},{"id":"2402.07101","title":"On the Complexity of First-Order Methods in Stochastic Bilevel Optimization","created":"2024-02-11","cited_by_count":12,"area":null},{"id":"2406.14095","title":"Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization","created":"2024-06-20","cited_by_count":11,"area":null},{"id":"2406.12771","title":"First-Order Methods for Linearly Constrained Bilevel Optimization","created":"2024-06-18","cited_by_count":10,"area":null},{"id":"2409.19212","title":"An Accelerated Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness","created":"2024-09-28","cited_by_count":9,"area":null},{"id":"2401.09257","title":"A First-Order Multi-Gradient Algorithm for Multi-Objective Bi-Level Optimization","created":"2024-01-17","cited_by_count":8,"area":null},{"id":"2506.06599","title":"Direct Prediction Set Minimization via Bilevel Conformal Classifier Training","created":"2025-06-07","cited_by_count":8,"area":null},{"id":"2306.13800","title":"A First Order Meta Stackelberg Method for Robust Federated Learning","created":"2023-06-23","cited_by_count":7,"area":null},{"id":"2311.08945","title":"A Single-Loop Algorithm for Decentralized Bilevel Optimization","created":"2023-11-15","cited_by_count":7,"area":null},{"id":"2406.10148","title":"A Primal-Dual-Assisted Penalty Approach to Bilevel Optimization with Coupled Constraints","created":"2024-06-14","cited_by_count":7,"area":null},{"id":"2412.20017","title":"A Nearly Optimal Single Loop Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness","created":"2024-12-28","cited_by_count":7,"area":null},{"id":"2502.08585","title":"LDC-MTL: Balancing Multi-Task Learning through Scalable Loss Discrepancy Control","created":"2025-02-12","cited_by_count":7,"area":null},{"id":"2503.03920","title":"Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA","created":"2025-03-05","cited_by_count":6,"area":null},{"id":"2410.05140","title":"Tuning-Free Bilevel Optimization: New Algorithms and Convergence Analysis","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2410.13067","title":"Two-Timescale Linear Stochastic Approximation: Constant Stepsizes Go a Long Way","created":"2024-10-16","cited_by_count":5,"area":null},{"id":"2502.03604","title":"Bilevel ZOFO: Efficient LLM Fine-Tuning and Meta-Training","created":"2025-02-05","cited_by_count":5,"area":null},{"id":"2308.10098","title":"An adaptively inexact first-order method for bilevel optimization with application to hyperparameter learning","created":"2023-08-19","cited_by_count":4,"area":null},{"id":"2402.02552","title":"Neur2BiLO: Neural Bilevel Optimization","created":"2024-02-04","cited_by_count":4,"area":null},{"id":"2404.03331","title":"LancBiO: dynamic Lanczos-aided bilevel optimization via Krylov subspace","created":"2024-04-04","cited_by_count":4,"area":null},{"id":"2409.03682","title":"A New First-Order Meta-Learning Algorithm with Convergence Guarantees","created":"2024-09-05","cited_by_count":4,"area":null},{"id":"2509.14952","title":"Stochastic Bilevel Optimization with Heavy-Tailed Noise","created":"2025-09-18","cited_by_count":4,"area":null},{"id":"2305.13153","title":"Effective Bilevel Optimization via Minimax Reformulation","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2402.03883","title":"A Framework for Bilevel Optimization on Riemannian Manifolds","created":"2024-02-06","cited_by_count":3,"area":null},{"id":"2505.02101","title":"Efficient Curvature-Aware Hypergradient Approximation for Bilevel Optimization","created":"2025-05-04","cited_by_count":3,"area":null},{"id":"2510.06048","title":"BLISS: A Lightweight Bilevel Influence Scoring Method for Data Selection in Language Model Pretraining","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2511.07398","title":"Solving bilevel optimization via sequential minimax optimization","created":"2025-11-10","cited_by_count":3,"area":null},{"id":"2511.19656","title":"Lower Complexity Bounds for Nonconvex-Strongly-Convex Bilevel Optimization with First-Order Oracles","created":"2025-11-24","cited_by_count":3,"area":null},{"id":"2511.22331","title":"On the Condition Number Dependency in Bilevel Optimization","created":"2025-11-27","cited_by_count":3,"area":null},{"id":"2512.02494","title":"A Fully First-Order Layer for Differentiable Optimization","created":"2025-12-02","cited_by_count":3,"area":null},{"id":"2606.04401","title":"TANDEM: Bi-Level Data Mixture Optimization with Twin Networks","created":"2026-06-03","cited_by_count":3,"area":null},{"id":"2312.03807","title":"Achieving ${O}(\\epsilon^{-1.5})$ Complexity in Hessian/Jacobian-free Stochastic Bilevel Optimization","created":"2023-12-06","cited_by_count":2,"area":null},{"id":"2409.19800","title":"Differentially Private Bilevel Optimization","created":"2024-09-29","cited_by_count":2,"area":null},{"id":"2412.06436","title":"An Adaptively Inexact Method for Bilevel Learning Using Primal-Dual Style Differentiation","created":"2024-12-09","cited_by_count":2,"area":null},{"id":"2412.12049","title":"Bilevel Learning with Inexact Stochastic Gradients","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2502.01076","title":"qNBO: quasi-Newton Meets Bilevel Optimization","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2507.23155","title":"On the Complexity of Finding Stationary Points in Nonconvex Simple Bilevel Optimization","created":"2025-07-30","cited_by_count":2,"area":null},{"id":"2509.15399","title":"Adaptive Algorithms with Sharp Convergence Rates for Stochastic Hierarchical Optimization","created":"2025-09-18","cited_by_count":2,"area":null},{"id":"2510.16806","title":"Computational Budget Should Be Considered in Data Selection","created":"2025-10-19","cited_by_count":2,"area":null},{"id":"2511.07824","title":"Multi-Objective Bilevel Learning","created":"2025-11-11","cited_by_count":2,"area":null},{"id":"2511.21056","title":"Bilevel Data Curation for LLM Fine-tuning: Offline Selection and Online Self-Refining Generation","created":"2025-11-26","cited_by_count":2,"area":null},{"id":"2606.00571","title":"On the Difficulty of Learning a Meta-network for Training Data Selection","created":"2026-05-30","cited_by_count":2,"area":null},{"id":"2606.18650","title":"BLADE: Scalable Bi-level Adaptive Data Selection for LLM Training","created":"2026-06-17","cited_by_count":2,"area":null},{"id":"2401.09651","title":"Convex and Bilevel Optimization for Neuro-Symbolic Inference and Learning","created":"2024-01-17","cited_by_count":1,"area":null},{"id":"2410.15923","title":"Automatic Differentiation of Optimization Algorithms with Time-Varying Updates","created":"2024-10-21","cited_by_count":1,"area":null},{"id":"2410.19319","title":"Fully First-Order Methods for Decentralized Bilevel Optimization","created":"2024-10-25","cited_by_count":1,"area":null},{"id":"2503.03908","title":"On the Convergence of Adam-Type Algorithm for Bilevel Optimization under Unbounded Smoothness","created":"2025-03-05","cited_by_count":1,"area":null},{"id":"2506.12994","title":"Differentially Private Bilevel Optimization: Efficient Algorithms with Near-Optimal Rates","created":"2025-06-15","cited_by_count":1,"area":null},{"id":"2509.02937","title":"Faster Gradient Methods for Highly-Smooth Stochastic Bilevel Optimization","created":"2025-09-03","cited_by_count":1,"area":null},{"id":"2509.15543","title":"Nonconvex Decentralized Stochastic Bilevel Optimization under Heavy-Tailed Noise","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2511.09845","title":"Bridging Constraints and Stochasticity: A Fully First-Order Method for Stochastic Bilevel Optimization with Linear Constraints","created":"2025-11-13","cited_by_count":1,"area":null},{"id":"2602.06457","title":"Achieving Better Local Regret Bound for Online Non-Convex Bilevel Optimization","created":"2026-02-06","cited_by_count":1,"area":null},{"id":"2603.29108","title":"Efficient Bilevel Optimization with KFAC-Based Hypergradients","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2605.08006","title":"Penalty-Based First-Order Methods for Bilevel Optimization with Minimax and Constrained Lower-Level Problems","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2605.15530","title":"Rethinking Neural Network Learning Rates: A Stackelberg Perspective","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2405.00914","title":"Accelerated Fully First-Order Methods for Bilevel and Minimax Optimization","created":"2024-05-01","cited_by_count":0,"area":null},{"id":"2405.15816","title":"Riemannian Bilevel Optimization","created":"2024-05-22","cited_by_count":0,"area":null},{"id":"2408.13323","title":"On Stability in Optimistic Bilevel Optimization","created":"2024-08-23","cited_by_count":0,"area":null},{"id":"2505.01258","title":"A Provably Convergent Plug-and-Play Framework for Stochastic Bilevel Optimization","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2505.14647","title":"Sequential QCQP for Bilevel Optimization with Line Search","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2510.24710","title":"A Single-Loop First-Order Algorithm for Linearly Constrained Bilevel Optimization","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2602.11665","title":"Fully First-Order Algorithms for Online Bilevel Optimization","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2603.00027","title":"Bilevel Optimization with Lower-Level Uniform Convexity: Theory and Algorithm","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2605.10288","title":"BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.24743","title":"Bilevel Optimization of Synthetic Trajectories for Multi-Turn LLM Fine-Tuning","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2607.13414","title":"Non-Expansive Two-Time-Scale Stochastic Approximation: A Fixed-Schedule One-Quarter Barrier and Bias-Corrected Acceleration","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2608.12704","title":"Efficient Hessian-Free Methods for Multi-Objective Bilevel Optimization with Nonconvex Lower Level","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2609.02286","title":"From topology learning to graph generation: A unifying perspective","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.16350","title":"Federated stochastic bilevel optimization with fully first-order gradients","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.33176","title":"ABO-Med: Accelerated Bilevel Optimization for Few-Shot Medical Image Classification","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.01843","title":"Optimal Stochastic Bilevel Optimization with First-Order Oracles","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.13693","title":"Calibration in One Go: Jointly Learning Accurate and Calibrated Neural Networks","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}