{"list":"other","total":62,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1603.00943","title":"CVXPY: A Python-Embedded Modeling Language for Convex Optimization","created":"2016-03-03","cited_by_count":641},{"id":"1909.01377","title":"Deep Equilibrium Models","created":"2019-09-03","cited_by_count":615},{"id":"1703.00443","title":"OptNet: Differentiable Optimization as a Layer in Neural Networks","created":"2017-03-01","cited_by_count":599},{"id":"1909.04630","title":"Meta-Learning with Implicit Gradients","created":"2019-09-10","cited_by_count":525},{"id":"1910.12430","title":"Differentiable Convex Optimization Layers","created":"2019-10-28","cited_by_count":465},{"id":"1904.03758","title":"Meta-Learning with Differentiable Convex Optimization","created":"2019-04-07","cited_by_count":461},{"id":"1806.04910","title":"Bilevel Programming for Hyperparameter Optimization and Meta-Learning","created":"2018-06-13","cited_by_count":405},{"id":"1805.08136","title":"Meta-learning with differentiable closed-form solvers","created":"2018-05-21","cited_by_count":397},{"id":"1502.03492","title":"Gradient-based Hyperparameter Optimization through Reversible Learning","created":"2015-02-11","cited_by_count":360},{"id":"1710.08005","title":"Smart \"Predict, then Optimize\"","created":"2017-10-22","cited_by_count":339},{"id":"1911.02590","title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","created":"2019-11-06","cited_by_count":304},{"id":"1802.02246","title":"Approximation Methods for Bilevel Programming","created":"2018-02-06","cited_by_count":236},{"id":"1703.01785","title":"Forward and Reverse Gradient-Based Hyperparameter Optimization","created":"2017-03-06","cited_by_count":234},{"id":"1602.02355","title":"Hyperparameter optimization with approximate gradient","created":"2016-02-07","cited_by_count":233},{"id":"1809.05504","title":"Melding the Data-Decisions Pipeline: Decision-Focused Learning for Combinatorial Optimization","created":"2018-09-14","cited_by_count":227},{"id":"2010.07962","title":"Bilevel Optimization: Convergence Analysis and Enhanced Design","created":"2020-10-15","cited_by_count":222},{"id":"1810.10667","title":"Truncated Back-propagation for Bilevel Optimization","created":"2018-10-25","cited_by_count":190},{"id":"2103.16378","title":"End-to-End Constrained Optimization Learning: A Survey","created":"2021-03-30","cited_by_count":157},{"id":"2006.16218","title":"On the Iteration Complexity of Hypergradient Computation","created":"2020-06-29","cited_by_count":155},{"id":"2007.05170","title":"A Two-Timescale Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Critic","created":"2020-07-10","cited_by_count":144},{"id":"1705.06270","title":"A Review on Bilevel Optimization: From Classical to Evolutionary Approaches and Applications","created":"2017-05-17","cited_by_count":129},{"id":"1607.05447","title":"On Differentiating Parameterized Argmin and Argmax Problems with Application to Bi-level Optimization","created":"2016-07-19","cited_by_count":112},{"id":"1507.08752","title":"An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback","created":"2015-07-31","cited_by_count":111},{"id":"2102.07367","title":"A Near-Optimal Algorithm for Stochastic Bilevel Optimization via Double-Momentum","created":"2021-02-15","cited_by_count":106},{"id":"2106.04692","title":"Provably Faster Algorithms for Bilevel Optimization","created":"2021-06-08","cited_by_count":106},{"id":"2209.08709","title":"BOME! Bilevel Optimization Made Easy: A Simple First-Order Approach","created":"2022-09-19","cited_by_count":105},{"id":"2301.10945","title":"A Fully First-Order Method for Stochastic Bilevel Optimization","created":"2023-01-26","cited_by_count":100},{"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},{"id":"1803.06396","title":"Reviving and Improving Recurrent Back-Propagation","created":"2018-03-16","cited_by_count":69},{"id":"2102.04671","title":"A Single-Timescale Method for Stochastic Bilevel Optimization","created":"2021-02-09","cited_by_count":69},{"id":"1702.03999","title":"A First Order Method for Solving Convex Bi-Level Optimization Problems","created":"2017-02-13","cited_by_count":67},{"id":"2006.09486","title":"Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters","created":"2020-06-16","cited_by_count":65},{"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},{"id":"2302.03775","title":"Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion","created":"2023-02-07","cited_by_count":45},{"id":"2301.01716","title":"First-order penalty methods for bilevel optimization","created":"2023-01-04","cited_by_count":41},{"id":"1909.03510","title":"Bi-level Actor-Critic for Multi-agent Coordination","created":"2019-09-08","cited_by_count":39},{"id":"2104.06763","title":"Oracle Complexity in Nonsmooth Nonconvex Optimization","created":"2021-04-14","cited_by_count":39},{"id":"2112.06969","title":"A gradient sampling method with complexity guarantees for Lipschitz functions in high and low dimensions","created":"2021-12-13","cited_by_count":39},{"id":"1911.03432","title":"Penalty Method for Inversion-Free Deep Bilevel Optimization","created":"2019-11-08","cited_by_count":33},{"id":"2105.02266","title":"Randomized Stochastic Variance-Reduced Methods for Multi-Task Stochastic Bilevel Optimization","created":"2021-05-05","cited_by_count":33},{"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},{"id":"1802.01504","title":"Linear Convergence of the Primal-Dual Gradient Method for Convex-Concave Saddle Point Problems without Strong Convexity","created":"2018-02-05","cited_by_count":29},{"id":"2302.08300","title":"Deterministic Nonsmooth Nonconvex Optimization","created":"2023-02-16","cited_by_count":26},{"id":"2307.04504","title":"An Algorithm with Optimal Dimension-Dependence for Zero-Order Nonsmooth Nonconvex Stochastic Optimization","created":"2023-07-10","cited_by_count":23},{"id":"2102.09006","title":"Difference of convex algorithms for bilevel programs with applications in hyperparameter selection","created":"2021-02-17","cited_by_count":17},{"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},{"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},{"id":"2302.01970","title":"Efficient Gradient Approximation Method for Constrained Bilevel Optimization","created":"2023-02-03","cited_by_count":15},{"id":"2008.01500","title":"A bilevel framework for decision-making under uncertainty with contextual information","created":"2020-08-04","cited_by_count":13},{"id":"2308.07536","title":"Projection-Free Methods for Stochastic Simple Bilevel Optimization with Convex Lower-level Problem","created":"2023-08-15","cited_by_count":13},{"id":"2106.03278","title":"Coordinating Followers to Reach Better Equilibria: End-to-End Gradient Descent for Stackelberg Games","created":"2021-06-06","cited_by_count":10},{"id":"2210.00652","title":"The cost of nonconvexity in deterministic nonsmooth optimization","created":"2022-10-02","cited_by_count":9},{"id":"2110.11721","title":"Projection-Free Algorithm for Stochastic Bi-level Optimization","created":"2021-10-22","cited_by_count":8},{"id":"2306.16761","title":"Moreau Envelope Based Difference-of-weakly-Convex Reformulation and Algorithm for Bilevel Programs","created":"2023-06-29","cited_by_count":8},{"id":"2307.08245","title":"Convex Bi-Level Optimization Problems with Non-smooth Outer Objective Function","created":"2023-07-17","cited_by_count":7},{"id":"1809.10050","title":"An Iterative Regularized Incremental Projected Subgradient Method for a Class of Bilevel Optimization Problems","created":"2018-09-26","cited_by_count":6},{"id":"2310.03690","title":"Goldstein Stationarity in Lipschitz Constrained Optimization","created":"2023-10-05","cited_by_count":6},{"id":"2306.02429","title":"An Inexact Conditional Gradient Method for Constrained Bilevel Optimization","created":"2023-06-04","cited_by_count":4},{"id":"1901.09506","title":"An iterative regularized mirror descent method for ill-posed nondifferentiable stochastic optimization","created":"2019-01-28","cited_by_count":3}],"next_cursor":null}