{"total":234,"rows":[{"id":"2106.07594","title":"Graph Contrastive Learning Automated","created":"2021-06-10","cited_by_count":287,"area":null},{"id":"2105.15183","title":"Efficient and Modular Implicit Differentiation","created":"2021-05-31","cited_by_count":203,"area":null},{"id":"2101.06861","title":"Discrete Graph Structure Learning for Forecasting Multiple Time Series","created":"2021-01-18","cited_by_count":171,"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":"2107.05847","title":"Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challenges","created":"2021-07-13","cited_by_count":145,"area":null},{"id":"2301.07014","title":"Dataset Distillation: A Comprehensive Review","created":"2023-01-17","cited_by_count":127,"area":null},{"id":"2102.07367","title":"A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum","created":"2021-02-15","cited_by_count":106,"area":null},{"id":"2106.04692","title":"Provably Faster Algorithms for Bilevel Optimization","created":"2021-06-08","cited_by_count":106,"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":"2206.02916","title":"Remember the Past: Distilling Datasets into Addressable Memories for Neural Networks","created":"2022-06-06","cited_by_count":104,"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":"2302.05185","title":"On Penalty-based Bilevel Gradient Descent Method","created":"2023-02-10","cited_by_count":87,"area":null},{"id":"2202.00665","title":"Tutorial on amortized optimization","created":"2022-02-01","cited_by_count":83,"area":null},{"id":"2111.05177","title":"On Training Implicit Models","created":"2021-11-09","cited_by_count":75,"area":null},{"id":"2312.04528","title":"Using Large Language Models for Hyperparameter Optimization","created":"2023-12-07","cited_by_count":71,"area":null},{"id":"2410.07471","title":"SEAL: Safety-enhanced Aligned LLM Fine-tuning via Bilevel Data Selection","created":"2024-10-09","cited_by_count":64,"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":"2111.14580","title":"Amortized Implicit Differentiation for Stochastic Bilevel Optimization","created":"2021-11-29","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":"2205.02215","title":"FedNest: Federated Bilevel, Minimax, and Compositional Optimization","created":"2022-05-04","cited_by_count":60,"area":null},{"id":"2105.07246","title":"An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming","created":"2021-05-15","cited_by_count":59,"area":null},{"id":"2302.10911","title":"Revisiting Weighted Aggregation in Federated Learning with Neural Networks","created":"2023-02-14","cited_by_count":58,"area":null},{"id":"2210.04092","title":"Advancing Model Pruning via Bi-level Optimization","created":"2022-10-08","cited_by_count":56,"area":null},{"id":"2112.04660","title":"A Fully Single Loop Algorithm for Bilevel Optimization without Hessian Inverse","created":"2021-12-09","cited_by_count":53,"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":"2102.03926","title":"Lower Bounds and Accelerated Algorithms for Bilevel Optimization","created":"2021-02-07","cited_by_count":46,"area":null},{"id":"2310.07831","title":"Optimal Linear Decay Learning Rate Schedules and Further Refinements","created":"2023-10-11","cited_by_count":43,"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":"2402.06886","title":"Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF","created":"2024-02-10","cited_by_count":41,"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":"2102.02515","title":"HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks","created":"2021-02-04","cited_by_count":38,"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":"2207.11518","title":"Online Knowledge Distillation via Mutual Contrastive Learning for Visual Recognition","created":"2022-07-23","cited_by_count":36,"area":"distill"},{"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":"2208.10494","title":"Dataset Condensation with Latent Space Knowledge Factorization and Sharing","created":"2022-08-21","cited_by_count":34,"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":"2306.12067","title":"Optimal Algorithms for Stochastic Bilevel Optimization under Relaxed Smoothness Conditions","created":"2023-06-21","cited_by_count":31,"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":"2207.02849","title":"Betty: An Automatic Differentiation Library for Multilevel Optimization","created":"2022-07-05","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":"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":"2402.17457","title":"Super Consistency of Neural Network Landscapes and Learning Rate Transfer","created":"2024-02-27","cited_by_count":23,"area":null},{"id":"2105.01637","title":"Implicit differentiation for fast hyperparameter selection in non-smooth convex learning","created":"2021-05-04","cited_by_count":22,"area":null},{"id":"2504.16430","title":"MAGIC: Near-Optimal Data Attribution for Deep Learning","created":"2025-04-23","cited_by_count":22,"area":null},{"id":"2105.09384","title":"Graph Sanitation with Application to Node Classification","created":"2021-05-19","cited_by_count":20,"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":"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":"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":"2209.13271","title":"The Curse of Unrolling: Rate of Differentiating Through Optimization","created":"2022-09-27","cited_by_count":16,"area":null},{"id":"2302.00441","title":"Scaling Laws for Hyperparameter Optimization","created":"2023-02-01","cited_by_count":16,"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":"2306.06634","title":"Adaptive Multi-Teacher Knowledge Distillation with Meta-Learning","created":"2023-06-11","cited_by_count":16,"area":"distill"},{"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":"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":"2106.00058","title":"Stable and Interpretable Unrolled Dictionary Learning","created":"2021-05-31","cited_by_count":15,"area":null},{"id":"2202.09774","title":"Supervising the Multi-Fidelity Race of Hyperparameter Configurations","created":"2022-02-20","cited_by_count":15,"area":null},{"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":"2209.12086","title":"One-Shot Learning of Stochastic Differential Equations with Data Adapted Kernels","created":"2022-09-24","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":"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":"2105.10762","title":"AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly","created":"2021-05-22","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":"2305.19442","title":"SimFBO: Towards Simple, Flexible and Communication-efficient Federated Bilevel Learning","created":"2023-05-30","cited_by_count":14,"area":null},{"id":"2102.09026","title":"Optimizing Large-Scale Hyperparameters via Automated Learning Algorithm","created":"2021-02-17","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":"2302.04969","title":"Communication-Efficient Federated Hypergradient Computation via Aggregated Iterative Differentiation","created":"2023-02-09","cited_by_count":13,"area":null},{"id":"2408.10774","title":"Flexora: Flexible Low Rank Adaptation for Large Language Models","created":"2024-08-20","cited_by_count":13,"area":null},{"id":"2105.13954","title":"A Gradient Method for Multilevel Optimization","created":"2021-05-28","cited_by_count":12,"area":null},{"id":"2112.15400","title":"A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning","created":"2021-12-31","cited_by_count":12,"area":null},{"id":"2203.01443","title":"Continuous-Time Meta-Learning with Forward Mode Differentiation","created":"2022-03-02","cited_by_count":12,"area":null},{"id":"2206.06544","title":"A Survey of Automated Data Augmentation Algorithms for Deep Learning-based Image Classification Tasks","created":"2022-06-14","cited_by_count":12,"area":null},{"id":"2210.12936","title":"Selecting and Composing Learning Rate Policies for Deep Neural Networks","created":"2022-10-24","cited_by_count":12,"area":null},{"id":"2201.06314","title":"Efficient Hyperparameter Tuning for Large Scale Kernel Ridge Regression","created":"2022-01-17","cited_by_count":11,"area":null},{"id":"2206.05558","title":"Communication-Efficient Robust Federated Learning with Noisy Labels","created":"2022-06-11","cited_by_count":11,"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":"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":"2305.14851","title":"Sharpness-Aware Data Poisoning Attack","created":"2023-05-24","cited_by_count":10,"area":"safety"},{"id":"2404.01206","title":"Machine Unlearning for Traditional Models and Large Language Models: A Short Survey","created":"2024-04-01","cited_by_count":10,"area":"safety"},{"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":"2203.00089","title":"Amortized Proximal Optimization","created":"2022-02-28","cited_by_count":9,"area":null},{"id":"2209.08907","title":"Learning Symbolic Model-Agnostic Loss Functions via Meta-Learning","created":"2022-09-19","cited_by_count":9,"area":null},{"id":"2304.13339","title":"OpenBox: A Python Toolkit for Generalized Black-box Optimization","created":"2023-04-26","cited_by_count":9,"area":null},{"id":"2308.10915","title":"DiffPrep: Differentiable Data Preprocessing Pipeline Search for Learning over Tabular Data","created":"2023-08-20","cited_by_count":9,"area":null},{"id":"2102.00252","title":"Synthetic Dataset Generation of Driver Telematics","created":"2021-01-30","cited_by_count":8,"area":null}],"next_cursor":"100"}