{"list":"other","total":80,"rows":[{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"1405.4980","title":"Convex Optimization: Algorithms and Complexity","created":"2014-05-20","cited_by_count":575},{"id":"1608.04636","title":"Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-\\L{}ojasiewicz Condition","created":"2016-08-16","cited_by_count":539},{"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":"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":"1710.10571","title":"Certifying Some Distributional Robustness with Principled Adversarial Training","created":"2017-10-29","cited_by_count":337},{"id":"1703.00887","title":"How to Escape Saddle Points Efficiently","created":"2017-03-02","cited_by_count":285},{"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":"1810.10667","title":"Truncated Back-propagation for Bilevel Optimization","created":"2018-10-25","cited_by_count":190},{"id":"2006.16218","title":"On the Iteration Complexity of Hypergradient Computation","created":"2020-06-29","cited_by_count":155},{"id":"1902.08297","title":"Solving a Class of Non-Convex Min-Max Games Using Iterative First Order Methods","created":"2019-02-21","cited_by_count":148},{"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":"1710.11606","title":"Lower Bounds for Finding Stationary Points I","created":"2017-10-31","cited_by_count":126},{"id":"2002.02417","title":"Near-Optimal Algorithms for Minimax Optimization","created":"2020-02-05","cited_by_count":119},{"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":"2205.12934","title":"Amortized Inference for Causal Structure Learning","created":"2022-05-25","cited_by_count":90},{"id":"2302.05185","title":"On Penalty-based Bilevel Gradient Descent Method","created":"2023-02-10","cited_by_count":87},{"id":"2006.04045","title":"A Generic First-Order Algorithmic Framework for Bi-Level Programming Beyond Lower-Level Singleton","created":"2020-06-07","cited_by_count":79},{"id":"2001.03724","title":"Stochastic Recursive Gradient Descent Ascent for Stochastic Nonconvex-Strongly-Concave Minimax Problems","created":"2020-01-11","cited_by_count":77},{"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":"1711.10456","title":"Accelerated Gradient Descent Escapes Saddle Points Faster than Gradient Descent","created":"2017-11-28","cited_by_count":66},{"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":"1602.06661","title":"Error bounds, quadratic growth, and linear convergence of proximal methods","created":"2016-02-22","cited_by_count":60},{"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":"1711.00841","title":"Lower Bounds for Finding Stationary Points II: First-Order Methods","created":"2017-11-02","cited_by_count":58},{"id":"1711.02838","title":"Stochastic Cubic Regularization for Fast Nonconvex Optimization","created":"2017-11-08","cited_by_count":55},{"id":"1902.08294","title":"Hybrid Block Successive Approximation for One-Sided Non-Convex Min-Max Problems: Algorithms and Applications","created":"2019-02-21","cited_by_count":55},{"id":"2106.10784","title":"iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients","created":"2021-06-21","cited_by_count":51},{"id":"1705.02766","title":"\"Convex Until Proven Guilty\": Dimension-Free Acceleration of Gradient Descent on Non-Convex Functions","created":"2017-05-08","cited_by_count":46},{"id":"2102.03926","title":"Lower Bounds and Accelerated Algorithms for Bilevel Optimization","created":"2021-02-07","cited_by_count":46},{"id":"2006.07458","title":"Projection Robust Wasserstein Distance and Riemannian Optimization","created":"2020-06-12","cited_by_count":45},{"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":"2301.09819","title":"Model Agnostic Sample Reweighting for Out-of-Distribution Learning","created":"2023-01-24","cited_by_count":44},{"id":"2106.04350","title":"Nonsmooth Implicit Differentiation for Machine Learning and Optimization","created":"2021-06-08","cited_by_count":43},{"id":"2209.05045","title":"Gradient-Free Methods for Deterministic and Stochastic Nonsmooth Nonconvex Optimization","created":"2022-09-12","cited_by_count":43},{"id":"2301.01716","title":"First-order penalty methods for bilevel optimization","created":"2023-01-04","cited_by_count":41},{"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":"2207.01603","title":"Invariant and Transportable Representations for Anti-Causal Domain Shifts","created":"2022-07-04","cited_by_count":37},{"id":"2205.14224","title":"Will Bilevel Optimizers Benefit from Loops","created":"2022-05-27","cited_by_count":36},{"id":"2006.06359","title":"Improved Algorithms for Convex-Concave Minimax Optimization","created":"2020-06-11","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":"2112.09002","title":"On the Finite-Time Complexity and Practical Computation of Approximate Stationarity Concepts of Lipschitz Functions","created":"2021-12-16","cited_by_count":31},{"id":"2012.06188","title":"Recent Theoretical Advances in Non-Convex Optimization","created":"2020-12-11","cited_by_count":30},{"id":"2012.05199","title":"A Riemannian Block Coordinate Descent Method for Computing the Projection Robust Wasserstein Distance","created":"2020-12-09","cited_by_count":27},{"id":"2302.08300","title":"Deterministic Nonsmooth Nonconvex Optimization","created":"2023-02-16","cited_by_count":26},{"id":"2207.04888","title":"Non-Convex Bilevel Games with Critical Point Selection Maps","created":"2022-07-11","cited_by_count":25},{"id":"2205.01608","title":"Local Stochastic Bilevel Optimization with Momentum-Based Variance Reduction","created":"2022-05-03","cited_by_count":20},{"id":"2202.03684","title":"Efficiently Escaping Saddle Points in Bilevel Optimization","created":"2022-02-08","cited_by_count":19},{"id":"2110.04743","title":"ZARTS: On Zero-order Optimization for Neural Architecture Search","created":"2021-10-10","cited_by_count":18},{"id":"2201.11411","title":"Restarted Nonconvex Accelerated Gradient Descent: No More Polylogarithmic Factor in the $O(\\epsilon^{-7/4})$ Complexity","created":"2022-01-27","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":"2307.00126","title":"Accelerating Inexact HyperGradient Descent for Bilevel Optimization","created":"2023-06-30","cited_by_count":15},{"id":"2203.01123","title":"A Primal-Dual Approach to Bilevel Optimization with Multiple Inner Minima","created":"2022-03-01","cited_by_count":13},{"id":"2110.04814","title":"Finding Second-Order Stationary Points in Nonconvex-Strongly-Concave Minimax Optimization","created":"2021-10-10","cited_by_count":12},{"id":"2007.15845","title":"A Method with Convergence Rates for Optimization Problems with Variational Inequality Constraints","created":"2020-07-31","cited_by_count":8},{"id":"2301.02060","title":"A first-order augmented Lagrangian method for constrained minimax optimization","created":"2023-01-05","cited_by_count":8},{"id":"2105.05531","title":"Fast Algorithms for Stackelberg Prediction Game with Least Squares Loss","created":"2021-05-12","cited_by_count":7},{"id":"1708.04180","title":"Nonsmooth Analysis and Optimization","created":"2017-08-14","cited_by_count":5},{"id":"2110.07098","title":"A Cubic Regularization Approach for Finding Local Minimax Points in Nonconvex Minimax Optimization","created":"2021-10-14","cited_by_count":5},{"id":"2206.02991","title":"Solving Stackelberg Prediction Game with Least Squares Loss via Spherically Constrained Least Squares Reformulation","created":"2022-06-07","cited_by_count":3},{"id":"2205.02329","title":"Second-Order Sensitivity Analysis for Bilevel Optimization","created":"2022-05-04","cited_by_count":1}],"next_cursor":null}