{"total":112,"rows":[{"id":"2106.07594","title":"Graph Contrastive Learning Automated","created":"2021-06-10","cited_by_count":287,"area":null},{"id":"2304.04934","title":"Model Sparsity Can Simplify Machine Unlearning","created":"2023-04-11","cited_by_count":214,"area":"safety"},{"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":"2101.04562","title":"Hyperbolic Deep Neural Networks: A Survey","created":"2021-01-12","cited_by_count":139,"area":null},{"id":"2110.11773","title":"Sinkformers: Transformers with Doubly Stochastic Attention","created":"2021-10-22","cited_by_count":138,"area":null},{"id":"2307.13565","title":"Decision-Focused Learning: Foundations, State of the Art, Benchmark and Future Opportunities","created":"2023-07-25","cited_by_count":130,"area":null},{"id":"2106.02666","title":"Counterfactual Explanations Can Be Manipulated","created":"2021-06-04","cited_by_count":113,"area":null},{"id":"2211.06489","title":"Equivariance with Learned Canonicalization Functions","created":"2022-11-11","cited_by_count":109,"area":null},{"id":"2106.04692","title":"Provably Faster Algorithms for Bilevel Optimization","created":"2021-06-08","cited_by_count":106,"area":null},{"id":"2404.18239","title":"SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning","created":"2024-04-28","cited_by_count":104,"area":"safety"},{"id":"2202.00665","title":"Tutorial on amortized optimization","created":"2022-02-01","cited_by_count":83,"area":null},{"id":"2112.12376","title":"Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization","created":"2021-12-23","cited_by_count":76,"area":null},{"id":"2207.09442","title":"Theseus: A Library for Differentiable Nonlinear Optimization","created":"2022-07-19","cited_by_count":65,"area":null},{"id":"2111.14580","title":"Amortized Implicit Differentiation for Stochastic Bilevel Optimization","created":"2021-11-29","cited_by_count":63,"area":null},{"id":"2210.04092","title":"Advancing Model Pruning via Bi-level Optimization","created":"2022-10-08","cited_by_count":56,"area":null},{"id":"2105.02343","title":"CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints","created":"2021-05-05","cited_by_count":49,"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":"2201.04038","title":"DDG-DA: Data Distribution Generation for Predictable Concept Drift Adaptation","created":"2022-01-11","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":"2206.14234","title":"PyEPO: A PyTorch-based End-to-End Predict-then-Optimize Library for Linear and Integer Programming","created":"2022-06-28","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":"2112.11450","title":"Max-Margin Contrastive Learning","created":"2021-12-21","cited_by_count":27,"area":null},{"id":"2410.17509","title":"WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models","created":"2024-10-23","cited_by_count":26,"area":"safety"},{"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":"2210.01802","title":"Alternating Differentiation for Optimization Layers","created":"2022-10-03","cited_by_count":22,"area":null},{"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":"2307.08964","title":"Landscape Surrogate: Learning Decision Losses for Mathematical Optimization Under Partial Information","created":"2023-07-18","cited_by_count":18,"area":null},{"id":"2111.12193","title":"Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation","created":"2021-11-23","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":"2301.13197","title":"Unlocking Slot Attention by Changing Optimal Transport Costs","created":"2023-01-30","cited_by_count":16,"area":null},{"id":"2310.19007","title":"Behavior Alignment via Reward Function Optimization","created":"2023-10-29","cited_by_count":16,"area":null},{"id":"2406.07687","title":"Adversarial Machine Unlearning","created":"2024-06-11","cited_by_count":16,"area":"safety"},{"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":"2302.01970","title":"Efficient Gradient Approximation Method for Constrained Bilevel Optimization","created":"2023-02-03","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":"2305.19442","title":"SimFBO: Towards Simple, Flexible and Communication-efficient Federated Bilevel Learning","created":"2023-05-30","cited_by_count":14,"area":null},{"id":"2411.01248","title":"Guiding Neural Collapse: Optimising Towards the Nearest Simplex Equiangular Tight Frame","created":"2024-11-02","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":"2212.10048","title":"Asynchronous Distributed Bilevel Optimization","created":"2022-12-20","cited_by_count":13,"area":null},{"id":"2301.12047","title":"Backpropagation of Unrolled Solvers with Folded Optimization","created":"2023-01-28","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":"2106.01680","title":"Convergent Graph Solvers","created":"2021-06-03","cited_by_count":12,"area":null},{"id":"2107.10254","title":"Neural Fixed-Point Acceleration for Convex Optimization","created":"2021-07-21","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":"2303.02343","title":"What Is Missing in IRM Training and Evaluation? Challenges and Solutions","created":"2023-03-04","cited_by_count":10,"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":"2410.06324","title":"Differentiation Through Black-Box Quadratic Programming Solvers","created":"2024-10-08","cited_by_count":10,"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":"2506.07003","title":"End-to-End Probabilistic Framework for Learning with Hard Constraints","created":"2025-06-08","cited_by_count":9,"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":"2402.13984","title":"Stability-Aware Training of Machine Learning Force Fields with Differentiable Boltzmann Estimators","created":"2024-02-21","cited_by_count":8,"area":null},{"id":"2104.11455","title":"Birds of a Feather Flock Together: A Close Look at Cooperation Emergence via Multi-Agent RL","created":"2021-04-23","cited_by_count":7,"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":"2306.11023","title":"PINQI: An End-to-End Physics-Informed Approach to Learned Quantitative MRI Reconstruction","created":"2023-06-19","cited_by_count":7,"area":null},{"id":"2510.06179","title":"Differentiable Model Predictive Control on the GPU","created":"2025-10-07","cited_by_count":7,"area":"deeprl"},{"id":"2202.12404","title":"Exploiting Problem Structure in Deep Declarative Networks: Two Case Studies","created":"2022-02-24","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":"2407.05920","title":"LPGD: A General Framework for Backpropagation through Embedded Optimization Layers","created":"2024-07-08","cited_by_count":6,"area":null},{"id":"2202.10600","title":"Myriad: a real-world testbed to bridge trajectory optimization and deep learning","created":"2022-02-22","cited_by_count":5,"area":null},{"id":"2207.11486","title":"Time Series Prediction under Distribution Shift using Differentiable Forgetting","created":"2022-07-23","cited_by_count":5,"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":"2505.13564","title":"Online Decision-Focused Learning","created":"2025-05-19","cited_by_count":4,"area":null},{"id":"2106.02487","title":"Debiasing a First-order Heuristic for Approximate Bi-level Optimization","created":"2021-06-04","cited_by_count":3,"area":null},{"id":"2109.13662","title":"DeepPSL: End-to-end perception and reasoning","created":"2021-09-28","cited_by_count":3,"area":null},{"id":"2605.12754","title":"Constraint-Aware Flow Matching: Decision Aligned End-to-End Training for Constrained Sampling","created":"2026-05-12","cited_by_count":3,"area":"diffusion"},{"id":"2102.00927","title":"Total Least Squares Phase Retrieval","created":"2021-02-01","cited_by_count":2,"area":null},{"id":"2106.12563","title":"Feature Attributions and Counterfactual Explanations Can Be Manipulated","created":"2021-06-23","cited_by_count":2,"area":null},{"id":"2301.13812","title":"Learning Roles with Emergent Social Value Orientations","created":"2023-01-31","cited_by_count":2,"area":null},{"id":"2308.00311","title":"Doubly Robust Instance-Reweighted Adversarial Training","created":"2023-08-01","cited_by_count":2,"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":"2405.02372","title":"Triadic-OCD: Asynchronous Online Change Detection with Provable Robustness, Optimality, and Convergence","created":"2024-05-03","cited_by_count":2,"area":null},{"id":"2408.09976","title":"Preference-Optimized Pareto Set Learning for Blackbox Optimization","created":"2024-08-19","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":"2412.20679","title":"Differentiable Convex Optimization Layers in Neural Architectures: Foundations and Perspectives","created":"2024-12-30","cited_by_count":2,"area":null},{"id":"2606.24039","title":"TurboMPC: Fast, Scalable, and Differentiable Model Predictive Control on the GPU","created":"2026-06-23","cited_by_count":2,"area":null},{"id":"2608.23211","title":"SGHA: A Single-Loop Fully First-Order Algorithm for Nonconvex-Strongly-Convex Bilevel Optimization","created":"2026-08-24","cited_by_count":2,"area":null},{"id":"2205.02329","title":"Second-Order Sensitivity Analysis for Bilevel Optimization","created":"2022-05-04","cited_by_count":1,"area":null},{"id":"2312.17394","title":"Analyzing and Enhancing the Backward-Pass Convergence of Unrolled Optimization","created":"2023-12-28","cited_by_count":1,"area":null},{"id":"2408.04819","title":"Interventional Causal Structure Discovery over Graphical Models with Convergence and Optimality Guarantees","created":"2024-08-09","cited_by_count":1,"area":null},{"id":"2409.04407","title":"Exploiting Missing Data Remediation Strategies using Adversarial Missingness Attacks","created":"2024-09-06","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":"2511.12945","title":"APT: Affine Prototype-Timestamp For Time Series Forecasting Under Distribution Shift","created":"2025-11-17","cited_by_count":1,"area":null},{"id":"2601.16510","title":"Learning to Optimize by Differentiable Programming","created":"2026-01-23","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":"2603.05495","title":"Cheap Thrills: Effective Amortized Optimization Using Inexpensive Labels","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2606.05247","title":"DiffSlack: Learning under Nonlinear Inequality Constraints via Learnable Slack Variables","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2610.03945","title":"DePICT: Decision-Preserving Interface for Constrained Downstream Tasks","created":"2026-10-02","cited_by_count":1,"area":null},{"id":"2106.13272","title":"Generalized One-Class Learning Using Pairs of Complementary Classifiers","created":"2021-06-24","cited_by_count":0,"area":null},{"id":"2108.05531","title":"The Contextual Appointment Scheduling Problem","created":"2021-08-12","cited_by_count":0,"area":null},{"id":"2211.14448","title":"How to Backpropagate through Hungarian in Your DETR?","created":"2022-11-12","cited_by_count":0,"area":null},{"id":"2302.01421","title":"Follower Agnostic Methods for Stackelberg Games","created":"2023-02-02","cited_by_count":0,"area":null},{"id":"2306.14054","title":"Towards Understanding Gradient Approximation in Equality Constrained Deep Declarative Networks","created":"2023-06-24","cited_by_count":0,"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":"2410.11312","title":"Towards Differentiable Multilevel Optimization: A Gradient-Based Approach","created":"2024-10-15","cited_by_count":0,"area":null},{"id":"2410.17415","title":"End-to-End Optimization and Learning of Fair Court Schedules","created":"2024-10-22","cited_by_count":0,"area":null}],"next_cursor":"100"}