{"total":144,"rows":[{"id":"2404.04057","title":"Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation","created":"2024-04-05","cited_by_count":214,"area":"diffusion"},{"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":"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":"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":"2205.14224","title":"Will Bilevel Optimizers Benefit from Loops","created":"2022-05-27","cited_by_count":36,"area":null},{"id":"2106.11396","title":"BiAdam: Fast Adaptive Bilevel Optimization Methods","created":"2021-06-21","cited_by_count":33,"area":null},{"id":"2210.09921","title":"Finite-time analysis of single-timescale actor-critic","created":"2022-10-18","cited_by_count":32,"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":"2207.02849","title":"Betty: An Automatic Differentiation Library for Multilevel Optimization","created":"2022-07-05","cited_by_count":27,"area":null},{"id":"2302.07457","title":"When Demonstrations Meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning","created":"2023-02-15","cited_by_count":26,"area":"wm"},{"id":"2112.13521","title":"Can Reinforcement Learning Find Stackelberg-Nash Equilibria in General-Sum Markov Games with Myopic Followers?","created":"2021-12-27","cited_by_count":24,"area":null},{"id":"2203.02591","title":"A Small Gain Analysis of Single Timescale Actor Critic","created":"2022-03-04","cited_by_count":24,"area":null},{"id":"2402.05468","title":"Implicit Diffusion: Efficient Optimization through Stochastic Sampling","created":"2024-02-08","cited_by_count":24,"area":null},{"id":"2409.11219","title":"Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Models","created":"2024-09-17","cited_by_count":23,"area":"diffusion"},{"id":"2210.12839","title":"Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexity","created":"2022-10-23","cited_by_count":21,"area":null},{"id":"2205.01608","title":"Local Stochastic Bilevel Optimization with Momentum-Based Variance Reduction","created":"2022-05-03","cited_by_count":20,"area":null},{"id":"2403.20233","title":"Functional Bilevel Optimization for Machine Learning","created":"2024-03-29","cited_by_count":20,"area":null},{"id":"2109.12286","title":"Stackelberg Actor-Critic: Game-Theoretic Reinforcement Learning Algorithms","created":"2021-09-25","cited_by_count":19,"area":null},{"id":"2304.09576","title":"Leveraging the two timescale regime to demonstrate convergence of neural networks","created":"2023-04-19","cited_by_count":19,"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":"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":"2410.01537","title":"Attention layers provably solve single-location regression","created":"2024-10-02","cited_by_count":17,"area":null},{"id":"2206.03383","title":"On the Role of Discount Factor in Offline Reinforcement Learning","created":"2022-06-07","cited_by_count":16,"area":"offlinerl"},{"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":"2207.02829","title":"Online Bilevel Optimization: Regret Analysis of Online Alternating Gradient Methods","created":"2022-07-06","cited_by_count":15,"area":null},{"id":"2302.01667","title":"Mind the Gap: Offline Policy Optimization for Imperfect Rewards","created":"2023-02-03","cited_by_count":15,"area":"offlinerl"},{"id":"2306.07894","title":"iSLAM: Imperative SLAM","created":"2023-06-13","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":"2106.07472","title":"Analysis of a Target-Based Actor-Critic Algorithm with Linear Function Approximation","created":"2021-06-14","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":"2310.18535","title":"Contextual Stochastic Bilevel Optimization","created":"2023-10-27","cited_by_count":14,"area":null},{"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":"2302.04969","title":"Communication-Efficient Federated Hypergradient Computation via Aggregated Iterative Differentiation","created":"2023-02-09","cited_by_count":13,"area":null},{"id":"2410.11826","title":"Bayesian Experimental Design via Contrastive Diffusions","created":"2024-10-15","cited_by_count":11,"area":null},{"id":"2104.01627","title":"Finite-Time Convergence Rates of Nonlinear Two-Time-Scale Stochastic Approximation under Markovian Noise","created":"2021-04-04","cited_by_count":10,"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":"2405.09660","title":"Fast Two-Time-Scale Stochastic Gradient Method with Applications in Reinforcement Learning","created":"2024-05-15","cited_by_count":10,"area":"deeprl"},{"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":"2505.20659","title":"An Optimisation Framework for Unsupervised Environment Design","created":"2025-05-27","cited_by_count":10,"area":"deeprl"},{"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":"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":"2311.08945","title":"A Single-Loop Algorithm for Decentralized Bilevel Optimization","created":"2023-11-15","cited_by_count":7,"area":null},{"id":"2401.09339","title":"Central Limit Theorem for Two-Timescale Stochastic Approximation with Markovian Noise: Theory and Applications","created":"2024-01-17","cited_by_count":7,"area":null},{"id":"2401.12764","title":"Fast Nonlinear Two-Time-Scale Stochastic Approximation: Achieving $O(1/k)$ Finite-Sample Complexity","created":"2024-01-23","cited_by_count":7,"area":null},{"id":"2403.04236","title":"Regularized DeepIV with Model Selection","created":"2024-03-07","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":"2207.10751","title":"Federated Learning on Adaptively Weighted Nodes by Bilevel Optimization","created":"2022-07-21","cited_by_count":6,"area":null},{"id":"2106.00993","title":"On the Convergence Rate of Off-Policy Policy Optimization Methods with Density-Ratio Correction","created":"2021-06-02","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":"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":"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},{"id":"2406.06874","title":"Learning Reward and Policy Jointly from Demonstration and Preference Improves Alignment","created":"2024-06-11","cited_by_count":4,"area":"alignment"},{"id":"2410.13743","title":"Single-Timescale Multi-Sequence Stochastic Approximation Without Fixed Point Smoothness: Theories and Applications","created":"2024-10-17","cited_by_count":4,"area":null},{"id":"2501.09429","title":"ADAGE: A generic two-layer framework for adaptive agent based modelling","created":"2025-01-16","cited_by_count":4,"area":null},{"id":"2502.08808","title":"A First-order Generative Bilevel Optimization Framework for Diffusion Models","created":"2025-02-12","cited_by_count":4,"area":"diffusion"},{"id":"2508.17448","title":"Rectified Robust Policy Optimization for Model-Uncertain Constrained Reinforcement Learning without Strong Duality","created":"2025-08-24","cited_by_count":4,"area":"deeprl"},{"id":"2509.14952","title":"Stochastic Bilevel Optimization with Heavy-Tailed Noise","created":"2025-09-18","cited_by_count":4,"area":null},{"id":"2305.15249","title":"Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees","created":"2023-05-24","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":"2505.11714","title":"Bi-Level Policy Optimization with Nystr\\\"om Hypergradients","created":"2025-05-16","cited_by_count":3,"area":"deeprl"},{"id":"2509.18822","title":"On the Convergence of Policy Mirror Descent with Temporal Difference Evaluation","created":"2025-09-23","cited_by_count":3,"area":"deeprl"},{"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":"2511.22331","title":"On the Condition Number Dependency in Bilevel Optimization","created":"2025-11-27","cited_by_count":3,"area":null},{"id":"2604.04090","title":"Fine-grained Analysis of Stability and Generalization for Stochastic Bilevel Optimization","created":"2026-04-05","cited_by_count":3,"area":"deeprl"},{"id":"2606.04401","title":"TANDEM: Bi-Level Data Mixture Optimization with Twin Networks","created":"2026-06-03","cited_by_count":3,"area":null},{"id":"2206.06995","title":"Two-Timescale Stochastic Approximation for Bilevel Optimisation Problems in Continuous-Time Models","created":"2022-06-14","cited_by_count":2,"area":null},{"id":"2211.04088","title":"A Penalty-Based Method for Communication-Efficient Decentralized Bilevel Programming","created":"2022-11-08","cited_by_count":2,"area":null},{"id":"2401.09665","title":"Accelerating Distributed Stochastic Optimization via Self-Repellent Random Walks","created":"2024-01-18","cited_by_count":2,"area":null},{"id":"2401.15196","title":"Regularized Q-Learning with Linear Function Approximation","created":"2024-01-26","cited_by_count":2,"area":"deeprl"},{"id":"2409.19800","title":"Differentially Private Bilevel Optimization","created":"2024-09-29","cited_by_count":2,"area":null},{"id":"2410.09728","title":"Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator","created":"2024-10-13","cited_by_count":2,"area":"deeprl"},{"id":"2412.00797","title":"Online Poisoning Attack Against Reinforcement Learning under Black-box Environments","created":"2024-12-01","cited_by_count":2,"area":"deeprl"},{"id":"2502.01076","title":"qNBO: quasi-Newton Meets Bilevel Optimization","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2502.08457","title":"Learning Theory for Kernel Bilevel Optimization","created":"2025-02-12","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":"2510.12334","title":"Finite-time Convergence Analysis of Actor-Critic with Evolving Reward","created":"2025-10-14","cited_by_count":2,"area":"deeprl"},{"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":"2601.15363","title":"Non-Stationary Functional Bilevel Optimization","created":"2026-01-21","cited_by_count":2,"area":null},{"id":"2605.06593","title":"ReActor: Reinforcement Learning for Physics-Aware Motion Retargeting","created":"2026-05-07","cited_by_count":2,"area":"offlinerl"},{"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":"2307.05384","title":"Stochastic Nested Compositional Bi-level Optimization for Robust Feature Learning","created":"2023-07-11","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":"2411.16081","title":"Exploring the Generalization Capabilities of AID-based Bi-level Optimization","created":"2024-11-25","cited_by_count":1,"area":null},{"id":"2501.16520","title":"Safe Gradient Flow for Bilevel Optimization","created":"2025-01-27","cited_by_count":1,"area":null}],"next_cursor":"100"}