{"total":222,"rows":[{"id":"2105.15183","title":"Efficient and Modular Implicit Differentiation","created":"2021-05-31","cited_by_count":203,"area":null},{"id":"2101.11517","title":"Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyond","created":"2021-01-27","cited_by_count":153,"area":null},{"id":"2209.08709","title":"BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach","created":"2022-09-19","cited_by_count":105,"area":null},{"id":"2301.10945","title":"A Fully First-Order Method for Stochastic Bilevel Optimization","created":"2023-01-26","cited_by_count":100,"area":null},{"id":"2201.13409","title":"A framework for bilevel optimization that enables stochastic and global variance reduction algorithms","created":"2022-01-31","cited_by_count":99,"area":null},{"id":"2111.14580","title":"Amortized Implicit Differentiation for Stochastic Bilevel Optimization","created":"2021-11-29","cited_by_count":63,"area":null},{"id":"2205.02215","title":"FedNest: Federated Bilevel, Minimax, and Compositional Optimization","created":"2022-05-04","cited_by_count":60,"area":null},{"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":"2102.03926","title":"Lower Bounds and Accelerated Algorithms for Bilevel Optimization","created":"2021-02-07","cited_by_count":46,"area":null},{"id":"2210.01808","title":"Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees","created":"2022-10-04","cited_by_count":42,"area":"offlinerl"},{"id":"2301.01716","title":"First-order penalty methods for bilevel optimization","created":"2023-01-04","cited_by_count":41,"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":"2402.06886","title":"Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF","created":"2024-02-10","cited_by_count":41,"area":"alignment"},{"id":"2308.02585","title":"PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback","created":"2023-08-03","cited_by_count":40,"area":"alignment"},{"id":"2301.00712","title":"On Finding Small Hyper-Gradients in Bilevel Optimization: Hardness Results and Improved Analysis","created":"2023-01-02","cited_by_count":39,"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":"2205.14224","title":"Will Bilevel Optimizers Benefit from Loops","created":"2022-05-27","cited_by_count":36,"area":null},{"id":"2110.07004","title":"On the Convergence Theory for Hessian-Free Bilevel Algorithms","created":"2021-10-13","cited_by_count":35,"area":null},{"id":"2106.11396","title":"BiAdam: Fast Adaptive Bilevel Optimization Methods","created":"2021-06-21","cited_by_count":33,"area":null},{"id":"2206.10870","title":"Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networks","created":"2022-06-22","cited_by_count":32,"area":null},{"id":"2504.07717","title":"PR-Attack: Coordinated Prompt-RAG Attacks on Retrieval-Augmented Generation in Large Language Models via Bilevel Optimization","created":"2025-04-10","cited_by_count":32,"area":"rag"},{"id":"2106.04188","title":"Stability and Generalization of Bilevel Programming in Hyperparameter Optimization","created":"2021-06-08","cited_by_count":31,"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":"2212.14032","title":"On Implicit Bias in Overparameterized Bilevel Optimization","created":"2022-12-28","cited_by_count":30,"area":null},{"id":"2107.12301","title":"Enhanced Bilevel Optimization via Bregman Distance","created":"2021-07-26","cited_by_count":28,"area":null},{"id":"2207.02849","title":"Betty: An Automatic Differentiation Library for Multilevel Optimization","created":"2022-07-05","cited_by_count":27,"area":null},{"id":"2302.03407","title":"Averaged Method of Multipliers for Bi-Level Optimization without Lower-Level Strong Convexity","created":"2023-02-07","cited_by_count":26,"area":null},{"id":"2506.08164","title":"BLUR: A Bi-Level Optimization Approach for LLM Unlearning","created":"2025-06-09","cited_by_count":23,"area":"safety"},{"id":"2210.12839","title":"Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexity","created":"2022-10-23","cited_by_count":21,"area":null},{"id":"2403.20233","title":"Functional Bilevel Optimization for Machine Learning","created":"2024-03-29","cited_by_count":20,"area":null},{"id":"2202.03684","title":"Efficiently Escaping Saddle Points in Bilevel Optimization","created":"2022-02-08","cited_by_count":19,"area":null},{"id":"2302.05412","title":"Achieving Linear Speedup in Non-IID Federated Bilevel Learning","created":"2023-02-10","cited_by_count":18,"area":null},{"id":"2202.03397","title":"Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-start","created":"2022-02-07","cited_by_count":17,"area":null},{"id":"2206.08868","title":"A Conditional Gradient-based Method for Simple Bilevel Optimization with Convex Lower-level Problem","created":"2022-06-17","cited_by_count":17,"area":null},{"id":"2209.07075","title":"Bi-level Physics-Informed Neural Networks for PDE Constrained Optimization using Broyden's Hypergradients","created":"2022-09-15","cited_by_count":17,"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":"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":"2406.16087","title":"Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomy","created":"2024-06-23","cited_by_count":16,"area":"offlinerl"},{"id":"2206.05976","title":"Value Function Based Difference-of-Convex Algorithm for Bilevel Hyperparameter Selection Problems","created":"2022-06-13","cited_by_count":15,"area":null},{"id":"2207.02829","title":"Online Bilevel Optimization: Regret Analysis of Online Alternating Gradient Methods","created":"2022-07-06","cited_by_count":15,"area":null},{"id":"2302.01970","title":"Efficient Gradient Approximation Method for Constrained Bilevel Optimization","created":"2023-02-03","cited_by_count":15,"area":null},{"id":"2303.13009","title":"MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models","created":"2023-03-23","cited_by_count":15,"area":null},{"id":"2306.07894","title":"iSLAM: Imperative SLAM","created":"2023-06-13","cited_by_count":15,"area":null},{"id":"2307.00126","title":"Accelerating Inexact HyperGradient Descent for Bilevel Optimization","created":"2023-06-30","cited_by_count":15,"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":"2510.01755","title":"Learning Regularization Functionals for Inverse Problems: A Comparative Study","created":"2025-10-02","cited_by_count":15,"area":null},{"id":"2109.07497","title":"Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGD","created":"2021-09-15","cited_by_count":14,"area":null},{"id":"2206.15025","title":"On the Convergence of Distributed Stochastic Bilevel Optimization Algorithms over a Network","created":"2022-06-30","cited_by_count":14,"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":"2305.19442","title":"SimFBO: Towards Simple, Flexible and Communication-efficient Federated Bilevel Learning","created":"2023-05-30","cited_by_count":14,"area":null},{"id":"2310.18535","title":"Contextual Stochastic Bilevel Optimization","created":"2023-10-27","cited_by_count":14,"area":null},{"id":"2406.07236","title":"Let Go of Your Labels with Unsupervised Transfer","created":"2024-06-11","cited_by_count":14,"area":"mllm"},{"id":"2203.01123","title":"A Primal-Dual Approach to Bilevel Optimization with Multiple Inner Minima","created":"2022-03-01","cited_by_count":13,"area":null},{"id":"2212.10048","title":"Asynchronous Distributed Bilevel Optimization","created":"2022-12-20","cited_by_count":13,"area":null},{"id":"2302.04969","title":"Communication-Efficient Federated Hypergradient Computation via Aggregated Iterative Differentiation","created":"2023-02-09","cited_by_count":13,"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":"2410.07018","title":"Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalization","created":"2024-10-09","cited_by_count":12,"area":null},{"id":"2110.00604","title":"Inexact bilevel stochastic gradient methods for constrained and unconstrained lower-level problems","created":"2021-10-01","cited_by_count":11,"area":null},{"id":"2407.17823","title":"Optimal Hessian/Jacobian-Free Nonconvex-PL Bilevel Optimization","created":"2024-07-25","cited_by_count":11,"area":null},{"id":"2502.10510","title":"MixMin: Finding Data Mixtures via Convex Minimization","created":"2025-02-14","cited_by_count":11,"area":null},{"id":"2211.07096","title":"Alternating Implicit Projected SGD and Its Efficient Variants for Equality-constrained Bilevel Optimization","created":"2022-11-14","cited_by_count":10,"area":null},{"id":"2405.19697","title":"Bilevel reinforcement learning via the development of hyper-gradient without lower-level convexity","created":"2024-05-30","cited_by_count":10,"area":"deeprl"},{"id":"2406.12771","title":"First-Order Methods for Linearly Constrained Bilevel Optimization","created":"2024-06-18","cited_by_count":10,"area":null},{"id":"2503.17644","title":"On The Sample Complexity Bounds In Bilevel Reinforcement Learning","created":"2025-03-22","cited_by_count":10,"area":"deeprl"},{"id":"2107.02378","title":"Learning an Explicit Hyperparameter Prediction Function Conditioned on Tasks","created":"2021-07-06","cited_by_count":9,"area":null},{"id":"2203.01924","title":"Min-Max Bilevel Multi-objective Optimization with Applications in Machine Learning","created":"2022-03-03","cited_by_count":9,"area":null},{"id":"2203.13663","title":"FedGradNorm: Personalized Federated Gradient-Normalized Multi-Task Learning","created":"2022-03-24","cited_by_count":9,"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":"2410.17431","title":"Meta Stackelberg Game: Robust Federated Learning against Adaptive and Mixed Poisoning Attacks","created":"2024-10-22","cited_by_count":9,"area":"deeprl"},{"id":"2507.16302","title":"Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning","created":"2025-07-22","cited_by_count":9,"area":"diffusion"},{"id":"2110.11721","title":"Projection-Free Algorithm for Stochastic Bi-level Optimization","created":"2021-10-22","cited_by_count":8,"area":null},{"id":"2207.13283","title":"INTERACT: Achieving Low Sample and Communication Complexities in Decentralized Bilevel Learning over Networks","created":"2022-07-27","cited_by_count":8,"area":null},{"id":"2302.06701","title":"Communication-Efficient Federated Bilevel Optimization with Local and Global Lower Level Problems","created":"2023-02-13","cited_by_count":8,"area":null},{"id":"2305.18730","title":"Blockwise Stochastic Variance-Reduced Methods with Parallel Speedup for Multi-Block Bilevel Optimization","created":"2023-05-30","cited_by_count":8,"area":null},{"id":"2308.03811","title":"Non-Convex Bilevel Optimization with Time-Varying Objective Functions","created":"2023-08-07","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":"2203.16615","title":"A Fast and Convergent Proximal Algorithm for Regularized Nonconvex and Nonsmooth Bi-level Optimization","created":"2022-03-30","cited_by_count":7,"area":null},{"id":"2212.02376","title":"DIAMOND: Taming Sample and Communication Complexities in Decentralized Bilevel Optimization","created":"2022-12-05","cited_by_count":7,"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":"2211.00915","title":"Passage-Mask: A Learnable Regularization Strategy for Retriever-Reader Models","created":"2022-11-02","cited_by_count":6,"area":null},{"id":"2312.11835","title":"Provably Convergent Federated Trilevel Learning","created":"2023-12-19","cited_by_count":6,"area":null},{"id":"2402.14760","title":"Generalizing Reward Modeling for Out-of-Distribution Preference Learning","created":"2024-02-22","cited_by_count":6,"area":"alignment"},{"id":"2404.00158","title":"Fully Zeroth-Order Bilevel Programming via Gaussian Smoothing","created":"2024-03-29","cited_by_count":6,"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":"2301.01801","title":"Network Utility Maximization with Unknown Utility Functions: A Distributed, Data-Driven Bilevel Optimization Approach","created":"2023-01-04","cited_by_count":5,"area":null},{"id":"2306.02422","title":"A Generalized Alternating Method for Bilevel Learning under the Polyak-{\\L}ojasiewicz Condition","created":"2023-06-04","cited_by_count":5,"area":null},{"id":"2402.02857","title":"Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation","created":"2024-02-05","cited_by_count":5,"area":null},{"id":"2408.05885","title":"GFlowNet Training by Policy Gradients","created":"2024-08-12","cited_by_count":5,"area":"deeprl"},{"id":"2410.05140","title":"Tuning-Free Bilevel Optimization: New Algorithms and Convergence Analysis","created":"2024-10-07","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":"2510.08962","title":"Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigation","created":"2025-10-10","cited_by_count":5,"area":null},{"id":"2303.00039","title":"M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-Adaptation","created":"2023-02-28","cited_by_count":4,"area":null},{"id":"2305.18666","title":"BiSLS/SPS: Auto-tune Step Sizes for Stable Bi-level Optimization","created":"2023-05-30","cited_by_count":4,"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":"2404.03331","title":"LancBiO: dynamic Lanczos-aided bilevel optimization via Krylov subspace","created":"2024-04-04","cited_by_count":4,"area":null}],"next_cursor":"100"}