{"list":"other","total":98,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"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":"1907.02189","title":"On the Convergence of FedAvg on Non-IID Data","created":"2019-07-04","cited_by_count":1229},{"id":"1803.02999","title":"On First-Order Meta-Learning Algorithms","created":"2018-03-08","cited_by_count":1018},{"id":"1309.5549","title":"Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming","created":"2013-09-22","cited_by_count":724},{"id":"1803.09050","title":"Learning to Reweight Examples for Robust Deep Learning","created":"2018-03-24","cited_by_count":675},{"id":"1606.04474","title":"Learning to learn by gradient descent by gradient descent","created":"2016-06-14","cited_by_count":620},{"id":"1405.4980","title":"Convex Optimization: Algorithms and Complexity","created":"2014-05-20","cited_by_count":575},{"id":"1802.04434","title":"signSGD: Compressed Optimisation for Non-Convex Problems","created":"2018-02-13","cited_by_count":571},{"id":"1909.04630","title":"Meta-Learning with Implicit Gradients","created":"2019-09-10","cited_by_count":525},{"id":"1705.09056","title":"Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent","created":"2017-05-25","cited_by_count":502},{"id":"1806.04910","title":"Bilevel Programming for Hyperparameter Optimization and Meta-Learning","created":"2018-06-13","cited_by_count":405},{"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":"1911.02590","title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","created":"2019-11-06","cited_by_count":304},{"id":"1406.2572","title":"Identifying and attacking the saddle point problem in high-dimensional non-convex optimization","created":"2014-06-10","cited_by_count":289},{"id":"1807.01695","title":"SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path Integrated Differential Estimator","created":"2018-07-04","cited_by_count":287},{"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":"1503.02101","title":"Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decomposition","created":"2015-03-06","cited_by_count":243},{"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":"1904.12760","title":"Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation","created":"2019-04-29","cited_by_count":230},{"id":"1809.10505","title":"The Convergence of Sparsified Gradient Methods","created":"2018-09-27","cited_by_count":229},{"id":"2010.07962","title":"Bilevel Optimization: Convergence Analysis and Enhanced Design","created":"2020-10-15","cited_by_count":222},{"id":"1808.07217","title":"Don't Use Large Mini-Batches, Use Local SGD","created":"2018-08-22","cited_by_count":202},{"id":"1312.2139","title":"Optimal rates for zero-order convex optimization: the power of two function evaluations","created":"2013-12-07","cited_by_count":198},{"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":"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":"2202.09357","title":"ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!","created":"2022-02-18","cited_by_count":134},{"id":"1312.7853","title":"Communication Efficient Distributed Optimization using an Approximate Newton-type Method","created":"2013-12-30","cited_by_count":132},{"id":"1908.10400","title":"On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithms","created":"2019-08-27","cited_by_count":132},{"id":"1710.11606","title":"Lower Bounds for Finding Stationary Points I","created":"2017-10-31","cited_by_count":126},{"id":"1605.07272","title":"Matrix Completion has No Spurious Local Minimum","created":"2016-05-24","cited_by_count":125},{"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":"1903.03088","title":"Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions","created":"2019-03-07","cited_by_count":105},{"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":"2206.01288","title":"Decentralized Training of Foundation Models in Heterogeneous Environments","created":"2022-06-02","cited_by_count":87},{"id":"2302.05185","title":"On Penalty-based Bilevel Gradient Descent Method","created":"2023-02-10","cited_by_count":87},{"id":"1702.08704","title":"Optimal algorithms for smooth and strongly convex distributed optimization in networks","created":"2017-02-28","cited_by_count":83},{"id":"1803.08917","title":"Byzantine Stochastic Gradient Descent","created":"2018-03-23","cited_by_count":81},{"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":"2112.03806","title":"OOD-GNN: Out-of-Distribution Generalized Graph Neural Network","created":"2021-12-07","cited_by_count":78},{"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},{"id":"1803.06396","title":"Reviving and Improving Recurrent Back-Propagation","created":"2018-03-16","cited_by_count":69},{"id":"1711.10456","title":"Accelerated Gradient Descent Escapes Saddle Points Faster than Gradient Descent","created":"2017-11-28","cited_by_count":66},{"id":"1806.07811","title":"Stochastic Nested Variance Reduction for Nonconvex Optimization","created":"2018-06-20","cited_by_count":63},{"id":"2110.00455","title":"Towards Gradient-based Bilevel Optimization with Non-convex Followers and Beyond","created":"2021-10-01","cited_by_count":63},{"id":"2006.08085","title":"Optimal Complexity in Decentralized Training","created":"2020-06-15","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":"2205.02215","title":"FedNest: Federated Bilevel, Minimax, and Compositional Optimization","created":"2022-05-04","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":"1801.02982","title":"How To Make the Gradients Small Stochastically: Even Faster Convex and Nonconvex SGD","created":"2018-01-08","cited_by_count":57},{"id":"1910.01215","title":"ES-MAML: Simple Hessian-Free Meta Learning","created":"2019-09-25","cited_by_count":57},{"id":"1711.02838","title":"Stochastic Cubic Regularization for Fast Nonconvex Optimization","created":"2017-11-08","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":"2205.12679","title":"Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning","created":"2022-05-25","cited_by_count":50},{"id":"1708.08694","title":"Natasha 2: Faster Non-Convex Optimization Than SGD","created":"2017-08-29","cited_by_count":49},{"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":"1709.03528","title":"GIANT: Globally Improved Approximate Newton Method for Distributed Optimization","created":"2017-09-11","cited_by_count":44},{"id":"2301.09819","title":"Model Agnostic Sample Reweighting for Out-of-Distribution Learning","created":"2023-01-24","cited_by_count":44},{"id":"2301.01716","title":"First-order penalty methods for bilevel optimization","created":"2023-01-04","cited_by_count":41},{"id":"1902.00247","title":"Sharp Analysis for Nonconvex SGD Escaping from Saddle Points","created":"2019-02-01","cited_by_count":40},{"id":"2006.13476","title":"Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations","created":"2020-06-24","cited_by_count":40},{"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},{"id":"1711.06673","title":"Neon2: Finding Local Minima via First-Order Oracles","created":"2017-11-17","cited_by_count":36},{"id":"2205.14224","title":"Will Bilevel Optimizers Benefit from Loops","created":"2022-05-27","cited_by_count":36},{"id":"2110.07004","title":"On the Convergence Theory for Hessian-Free Bilevel Algorithms","created":"2021-10-13","cited_by_count":35},{"id":"2206.10870","title":"Decentralized Gossip-Based Stochastic Bilevel Optimization over Communication Networks","created":"2022-06-22","cited_by_count":32},{"id":"2306.12067","title":"Optimal Algorithms for Stochastic Bilevel Optimization under Relaxed Smoothness Conditions","created":"2023-06-21","cited_by_count":31},{"id":"2206.01299","title":"Fine-tuning Language Models over Slow Networks using Activation Compression with Guarantees","created":"2022-06-02","cited_by_count":30},{"id":"1711.01944","title":"First-order Stochastic Algorithms for Escaping From Saddle Points in Almost Linear Time","created":"2017-11-03","cited_by_count":29},{"id":"1802.03475","title":"Communication-Computation Efficient Gradient Coding","created":"2018-02-09","cited_by_count":27},{"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":"2110.04743","title":"ZARTS: On Zero-order Optimization for Neural Architecture Search","created":"2021-10-10","cited_by_count":18},{"id":"2302.05412","title":"Achieving Linear Speedup in Non-IID Federated Bilevel Learning","created":"2023-02-10","cited_by_count":18},{"id":"2010.13514","title":"Delta-STN: Efficient Bilevel Optimization for Neural Networks using Structured Response Jacobians","created":"2020-10-26","cited_by_count":17},{"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":"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":"2206.05976","title":"Value Function Based Difference-of-Convex Algorithm for Bilevel Hyperparameter Selection Problems","created":"2022-06-13","cited_by_count":15},{"id":"2302.04969","title":"Communication-Efficient Federated Hypergradient Computation via Aggregated Iterative Differentiation","created":"2023-02-09","cited_by_count":13},{"id":"2306.11035","title":"Adversarial Training Should Be Cast as a Non-Zero-Sum Game","created":"2023-06-19","cited_by_count":13},{"id":"2111.14069","title":"Escape saddle points by a simple gradient-descent based algorithm","created":"2021-11-28","cited_by_count":11},{"id":"2301.06806","title":"Convergence of First-Order Algorithms for Meta-Learning with Moreau Envelopes","created":"2023-01-17","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":"2304.12453","title":"Efficient First Order Method for Saddle Point Problems with Higher Order Smoothness","created":"2023-04-24","cited_by_count":4},{"id":"2305.17945","title":"Communication Efficient Distributed Newton Method with Fast Convergence Rates","created":"2023-05-29","cited_by_count":4},{"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":"2306.11211","title":"A New Simple Stochastic Gradient Descent Type Algorithm With Lower Computational Complexity for Bilevel Optimization","created":"2023-06-20","cited_by_count":1}],"next_cursor":null}