{"list":"other","total":56,"rows":[{"id":"1708.07747","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","created":"2017-08-25","cited_by_count":4349},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1909.04630","title":"Meta-Learning with Implicit Gradients","created":"2019-09-10","cited_by_count":525},{"id":"1806.04910","title":"Bilevel Programming for Hyperparameter Optimization and Meta-Learning","created":"2018-06-13","cited_by_count":405},{"id":"1407.0202","title":"SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives","created":"2014-07-01","cited_by_count":402},{"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":"1912.02365","title":"Lower Bounds for Non-Convex Stochastic Optimization","created":"2019-12-05","cited_by_count":307},{"id":"1905.10018","title":"Momentum-Based Variance Reduction in Non-Convex SGD","created":"2019-05-24","cited_by_count":306},{"id":"1906.00331","title":"On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems","created":"2019-06-02","cited_by_count":270},{"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":"2010.07962","title":"Bilevel Optimization: Convergence Analysis and Enhanced Design","created":"2020-10-15","cited_by_count":222},{"id":"1703.00102","title":"SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient","created":"2017-03-01","cited_by_count":220},{"id":"2006.16218","title":"On the Iteration Complexity of Hypergradient Computation","created":"2020-06-29","cited_by_count":155},{"id":"1603.06160","title":"Stochastic Variance Reduction for Nonconvex Optimization","created":"2016-03-19","cited_by_count":145},{"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":"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":"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":"1411.3803","title":"Stochastic Compositional Gradient Descent: Algorithms for Minimizing Compositions of Expected-Value Functions","created":"2014-11-14","cited_by_count":95},{"id":"2302.05185","title":"On Penalty-based Bilevel Gradient Descent Method","created":"2023-02-10","cited_by_count":87},{"id":"2102.04671","title":"A Single-Timescale Method for Stochastic Bilevel Optimization","created":"2021-02-09","cited_by_count":69},{"id":"2006.09486","title":"Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters","created":"2020-06-16","cited_by_count":65},{"id":"2110.00455","title":"Towards Gradient-based Bilevel Optimization with Non-convex Followers and Beyond","created":"2021-10-01","cited_by_count":63},{"id":"2111.14580","title":"Amortized Implicit Differentiation for Stochastic Bilevel Optimization","created":"2021-11-29","cited_by_count":63},{"id":"1812.01094","title":"A Single Time-Scale Stochastic Approximation Method for Nested Stochastic Optimization","created":"2018-12-03","cited_by_count":53},{"id":"2112.04660","title":"A Fully Single Loop Algorithm for Bilevel Optimization without Hessian Inverse","created":"2021-12-09","cited_by_count":53},{"id":"2008.10847","title":"Solving Stochastic Compositional Optimization is Nearly as Easy as Solving Stochastic Optimization","created":"2020-08-25","cited_by_count":51},{"id":"2110.07004","title":"On the Convergence Theory for Hessian-Free Bilevel Algorithms","created":"2021-10-13","cited_by_count":35},{"id":"1805.07588","title":"Robust Optimization over Multiple Domains","created":"2018-05-19","cited_by_count":34},{"id":"2002.08943","title":"Implicit differentiation of Lasso-type models for hyperparameter optimization","created":"2020-02-20","cited_by_count":34},{"id":"2105.02266","title":"Randomized Stochastic Variance-Reduced Methods for Multi-Task Stochastic Bilevel Optimization","created":"2021-05-05","cited_by_count":33},{"id":"1906.03563","title":"Adversarial Attack Generation Empowered by Min-Max Optimization","created":"2019-06-09","cited_by_count":32},{"id":"2206.13424","title":"Benchopt: Reproducible, efficient and collaborative optimization benchmarks","created":"2022-06-27","cited_by_count":27},{"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},{"id":"2008.10526","title":"Stochastic Multi-level Composition Optimization Algorithms with Level-Independent Convergence Rates","created":"2020-08-24","cited_by_count":25},{"id":"1801.03600","title":"Multi-Level Stochastic Gradient Methods for Nested Composition Optimization","created":"2018-01-11","cited_by_count":24},{"id":"2008.10103","title":"Single-Timescale Stochastic Nonconvex-Concave Optimization for Smooth Nonlinear TD Learning","created":"2020-08-23","cited_by_count":24},{"id":"2106.13695","title":"CADDA: Class-wise Automatic Differentiable Data Augmentation for EEG Signals","created":"2021-06-25","cited_by_count":22},{"id":"2210.12839","title":"Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexity","created":"2022-10-23","cited_by_count":21},{"id":"2202.03684","title":"Efficiently Escaping Saddle Points in Bilevel Optimization","created":"2022-02-08","cited_by_count":19},{"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":"2302.08766","title":"A Lower Bound and a Near-Optimal Algorithm for Bilevel Empirical Risk Minimization","created":"2023-02-17","cited_by_count":16},{"id":"2303.03944","title":"On Momentum-Based Gradient Methods for Bilevel Optimization with Nonconvex Lower-Level","created":"2023-03-07","cited_by_count":14},{"id":"2104.14840","title":"Unified Convergence Analysis for Adaptive Optimization with Moving Average Estimator","created":"2021-04-30","cited_by_count":13},{"id":"2110.00604","title":"Inexact bilevel stochastic gradient methods for constrained and unconstrained lower-level problems","created":"2021-10-01","cited_by_count":11},{"id":"2206.00260","title":"Multi-block Min-max Bilevel Optimization with Applications in Multi-task Deep AUC Maximization","created":"2022-06-01","cited_by_count":11},{"id":"2203.01924","title":"Min-Max Bilevel Multi-objective Optimization with Applications in Machine Learning","created":"2022-03-03","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":"2202.04296","title":"A Projection-free Algorithm for Constrained Stochastic Multi-level Composition Optimization","created":"2022-02-09","cited_by_count":8},{"id":"2302.05540","title":"Bilevel optimization with a multi-objective lower-level problem: Risk-neutral and risk-averse formulations","created":"2023-02-10","cited_by_count":5}],"next_cursor":null}