{"total":105,"rows":[{"id":"2103.04628","title":"Personalized Federated Learning using Hypernetworks","created":"2021-03-08","cited_by_count":212,"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":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139,"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":"2306.07349","title":"ATT3D: Amortized Text-to-3D Object Synthesis","created":"2023-06-06","cited_by_count":87,"area":null},{"id":"2101.01035","title":"HyperMorph: Amortized Hyperparameter Learning for Image Registration","created":"2021-01-04","cited_by_count":85,"area":null},{"id":"2312.04528","title":"Using Large Language Models for Hyperparameter Optimization","created":"2023-12-07","cited_by_count":71,"area":null},{"id":"2110.00455","title":"Towards Gradient-based Bilevel Optimization with Non-convex Followers and Beyond","created":"2021-10-01","cited_by_count":63,"area":null},{"id":"2106.07991","title":"A Value-Function-based Interior-point Method for Non-convex Bi-level Optimization","created":"2021-06-15","cited_by_count":60,"area":null},{"id":"2112.13835","title":"Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies","created":"2021-12-27","cited_by_count":52,"area":null},{"id":"2106.10784","title":"iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients","created":"2021-06-21","cited_by_count":51,"area":null},{"id":"2205.12679","title":"Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning","created":"2022-05-25","cited_by_count":50,"area":null},{"id":"2201.01212","title":"AutoBalance: Optimized Loss Functions for Imbalanced Data","created":"2022-01-04","cited_by_count":49,"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":"2302.06755","title":"Dataset Distillation with Convexified Implicit Gradients","created":"2023-02-13","cited_by_count":46,"area":null},{"id":"2301.09819","title":"Model Agnostic Sample Reweighting for Out-of-Distribution Learning","created":"2023-01-24","cited_by_count":44,"area":null},{"id":"2403.15385","title":"LATTE3D: Large-scale Amortized Text-To-Enhanced3D Synthesis","created":"2024-03-22","cited_by_count":39,"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":"2203.16680","title":"Learning the Effect of Registration Hyperparameters with HyperMorph","created":"2022-03-30","cited_by_count":35,"area":null},{"id":"2306.08107","title":"AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Risks","created":"2023-06-13","cited_by_count":35,"area":null},{"id":"2106.04188","title":"Stability and Generalization of Bilevel Programming in Hyperparameter Optimization","created":"2021-06-08","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":"2102.07976","title":"A General Descent Aggregation Framework for Gradient-based Bi-level Optimization","created":"2021-02-16","cited_by_count":28,"area":null},{"id":"2111.01754","title":"Meta-Learning to Improve Pre-Training","created":"2021-11-02","cited_by_count":27,"area":null},{"id":"2301.09880","title":"Probabilistic Bilevel Coreset Selection","created":"2023-01-24","cited_by_count":27,"area":null},{"id":"2205.03076","title":"Beyond backpropagation: bilevel optimization through implicit differentiation and equilibrium propagation","created":"2022-05-06","cited_by_count":26,"area":null},{"id":"2207.11719","title":"Gradient-based Bi-level Optimization for Deep Learning: A Survey","created":"2022-07-24","cited_by_count":26,"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":"2110.04974","title":"Value-Function-based Sequential Minimization for Bi-level Optimization","created":"2021-10-11","cited_by_count":24,"area":null},{"id":"2403.20233","title":"Functional Bilevel Optimization for Machine Learning","created":"2024-03-29","cited_by_count":20,"area":null},{"id":"2501.06773","title":"Pareto Set Learning for Multi-Objective Reinforcement Learning","created":"2025-01-12","cited_by_count":20,"area":"deeprl"},{"id":"2212.03905","title":"Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve","created":"2022-12-07","cited_by_count":18,"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":"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":"2304.07645","title":"Magnitude Invariant Parametrizations Improve Hypernetwork Learning","created":"2023-04-15","cited_by_count":14,"area":null},{"id":"2112.09245","title":"Automated Deep Learning: Neural Architecture Search Is Not the End","created":"2021-12-16","cited_by_count":13,"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":"2301.13501","title":"Auxiliary Learning as an Asymmetric Bargaining Game","created":"2023-01-31","cited_by_count":12,"area":null},{"id":"2102.08431","title":"Complex Momentum for Optimization in Games","created":"2021-02-16","cited_by_count":11,"area":null},{"id":"2109.11410","title":"Learning to Robustly Aggregate Labeling Functions for Semi-supervised Data Programming","created":"2021-09-23","cited_by_count":11,"area":null},{"id":"2208.07734","title":"Data Augmentation is a Hyperparameter: Cherry-picked Self-Supervision for Unsupervised Anomaly Detection is Creating the Illusion of Success","created":"2022-08-16","cited_by_count":11,"area":null},{"id":"2308.08497","title":"HyperBandit: Contextual Bandit with Hypernewtork for Time-Varying User Preferences in Streaming Recommendation","created":"2023-08-14","cited_by_count":10,"area":null},{"id":"2504.13112","title":"Hadamard product in deep learning: Introduction, Advances and Challenges","created":"2025-04-17","cited_by_count":9,"area":null},{"id":"2109.04684","title":"Enhancing Unsupervised Anomaly Detection with Score-Guided Network","created":"2021-09-10","cited_by_count":8,"area":null},{"id":"2112.14570","title":"Lyapunov Exponents for Diversity in Differentiable Games","created":"2021-12-24","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":"2308.03811","title":"Non-Convex Bilevel Optimization with Time-Varying Objective Functions","created":"2023-08-07","cited_by_count":8,"area":null},{"id":"2110.10461","title":"Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiation","created":"2021-10-20","cited_by_count":7,"area":null},{"id":"2208.12754","title":"Task Selection for AutoML System Evaluation","created":"2022-08-26","cited_by_count":7,"area":null},{"id":"2304.11153","title":"Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single","created":"2023-04-21","cited_by_count":7,"area":null},{"id":"2408.13237","title":"JacNet: Learning Functions with Structured Jacobians","created":"2024-08-23","cited_by_count":7,"area":null},{"id":"2109.05765","title":"DHA: End-to-End Joint Optimization of Data Augmentation Policy, Hyper-parameter and Architecture","created":"2021-09-13","cited_by_count":6,"area":null},{"id":"2111.06961","title":"Adversarially Robust Learning for Security-Constrained Optimal Power Flow","created":"2021-11-12","cited_by_count":6,"area":null},{"id":"2307.06534","title":"DSV: An Alignment Validation Loss for Self-supervised Outlier Model Selection","created":"2023-07-13","cited_by_count":6,"area":null},{"id":"2307.10529","title":"Fast Unsupervised Deep Outlier Model Selection with Hypernetworks","created":"2023-07-20","cited_by_count":6,"area":null},{"id":"2404.00158","title":"Fully Zeroth-Order Bilevel Programming via Gaussian Smoothing","created":"2024-03-29","cited_by_count":6,"area":null},{"id":"2505.04621","title":"Score Distillation Sampling for Audio: Source Separation, Synthesis, and Beyond","created":"2025-05-07","cited_by_count":6,"area":"diffusion"},{"id":"2107.04713","title":"Automated Graph Learning via Population Based Self-Tuning GCN","created":"2021-07-09","cited_by_count":5,"area":null},{"id":"2406.18630","title":"Improving Hyperparameter Optimization with Checkpointed Model Weights","created":"2024-06-26","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":"2112.15362","title":"Modeling Mask Uncertainty in Hyperspectral Image Reconstruction","created":"2021-12-31","cited_by_count":4,"area":null},{"id":"2404.14642","title":"Uncertainty Quantification on Graph Learning: A Survey","created":"2024-04-23","cited_by_count":4,"area":null},{"id":"2407.12993","title":"Improving SAM Requires Rethinking its Optimization Formulation","created":"2024-07-17","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":"2105.13695","title":"AutoSampling: Search for Effective Data Sampling Schedules","created":"2021-05-28","cited_by_count":3,"area":null},{"id":"2209.05093","title":"Bilevel Optimization for Feature Selection in the Data-Driven Newsvendor Problem","created":"2022-09-12","cited_by_count":3,"area":null},{"id":"2305.13153","title":"Effective Bilevel Optimization via Minimax Reformulation","created":"2023-05-22","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":"2101.06590","title":"Cost-Efficient Online Hyperparameter Optimization","created":"2021-01-17","cited_by_count":2,"area":null},{"id":"2205.10054","title":"Towards Extremely Fast Bilevel Optimization with Self-governed Convergence Guarantees","created":"2022-05-20","cited_by_count":2,"area":null},{"id":"2209.04683","title":"Simple and Effective Gradient-Based Tuning of Sequence-to-Sequence Models","created":"2022-09-10","cited_by_count":2,"area":null},{"id":"2210.08452","title":"Efficient Cross-Modal Video Retrieval with Meta-Optimized Frames","created":"2022-10-16","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":"2302.14473","title":"Implicit Bilevel Optimization: Differentiating through Bilevel Optimization Programming","created":"2023-02-28","cited_by_count":2,"area":null},{"id":"2308.14380","title":"Self-Supervision for Tackling Unsupervised Anomaly Detection: Pitfalls and Opportunities","created":"2023-08-28","cited_by_count":2,"area":null},{"id":"2410.13853","title":"AutoAL: Automated Active Learning with Differentiable Query Strategy Search","created":"2024-10-17","cited_by_count":2,"area":null},{"id":"2504.10735","title":"Frozen Layers: Memory-efficient Many-fidelity Hyperparameter Optimization","created":"2025-04-14","cited_by_count":2,"area":null},{"id":"2606.18697","title":"Stealthy World Model Manipulation via Data Poisoning","created":"2026-06-17","cited_by_count":2,"area":"wm"},{"id":"2606.29582","title":"Bilevel Optimization for Neural Architecture Search","created":"2026-06-28","cited_by_count":2,"area":null},{"id":"2301.08830","title":"ApproxED: Approximate exploitability descent via learned best responses","created":"2023-01-20","cited_by_count":1,"area":null},{"id":"2307.11808","title":"Automatic Data Augmentation Learning using Bilevel Optimization for Histopathological Images","created":"2023-07-21","cited_by_count":1,"area":null},{"id":"2307.13750","title":"Solution Path of Time-varying Markov Random Fields with Discrete Regularization","created":"2023-07-25","cited_by_count":1,"area":null},{"id":"2410.10006","title":"TapWeight: Reweighting Pretraining Objectives for Task-Adaptive Pretraining","created":"2024-10-13","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":"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":"2602.08067","title":"Enhancing Bandit Algorithms with LLMs for Time-varying User Preferences in Streaming Recommendations","created":"2026-02-08","cited_by_count":1,"area":"alignment"},{"id":"2205.08231","title":"Hyper-Learning for Gradient-Based Batch Size Adaptation","created":"2022-05-17","cited_by_count":0,"area":null},{"id":"2208.12118","title":"A Globally Convergent Gradient-based Bilevel Hyperparameter Optimization Method","created":"2022-08-25","cited_by_count":0,"area":null},{"id":"2212.06150","title":"CPMLHO:Hyperparameter Tuning via Cutting Plane and Mixed-Level Optimization","created":"2022-12-11","cited_by_count":0,"area":null},{"id":"2304.05448","title":"Scale-Space Hypernetworks for Efficient Biomedical Imaging","created":"2023-04-11","cited_by_count":0,"area":null},{"id":"2308.01207","title":"BiERL: A Meta Evolutionary Reinforcement Learning Framework via Bilevel Optimization","created":"2023-08-01","cited_by_count":0,"area":"synth"},{"id":"2406.11769","title":"Solving Vision Tasks with Simple Photoreceptors Instead of Cameras","created":"2024-06-17","cited_by_count":0,"area":null},{"id":"2407.00613","title":"A Linear Programming Enhanced Genetic Algorithm for Hyperparameter Tuning in Machine Learning","created":"2024-06-30","cited_by_count":0,"area":null},{"id":"2410.11312","title":"Towards Differentiable Multilevel Optimization: A Gradient-Based Approach","created":"2024-10-15","cited_by_count":0,"area":null},{"id":"2504.20501","title":"SAM-Guided Robust Representation Learning for One-Shot 3D Medical Image Segmentation","created":"2025-04-29","cited_by_count":0,"area":null},{"id":"2510.07624","title":"From Data to Rewards: a Bilevel Optimization Perspective on Maximum Likelihood Estimation","created":"2025-10-08","cited_by_count":0,"area":"deeprl"},{"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":"2510.25121","title":"Bilevel Models for Adversarial Learning and A Case Study","created":"2025-10-29","cited_by_count":0,"area":null}],"next_cursor":"100"}