{"list":"other","total":52,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"1904.09237","title":"On the Convergence of Adam and Beyond","created":"2019-04-19","cited_by_count":841},{"id":"1909.05207","title":"Introduction to Online Convex Optimization","created":"2019-09-07","cited_by_count":803},{"id":"1309.5549","title":"Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming","created":"2013-09-22","cited_by_count":724},{"id":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629},{"id":"1802.10026","title":"Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs","created":"2018-02-27","cited_by_count":588},{"id":"1405.4980","title":"Convex Optimization: Algorithms and Complexity","created":"2014-05-20","cited_by_count":575},{"id":"1407.7722","title":"OpenML: networked science in machine learning","created":"2014-07-29","cited_by_count":526},{"id":"2103.00065","title":"Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability","created":"2021-02-26","cited_by_count":427},{"id":"1802.09568","title":"Shampoo: Preconditioned Stochastic Tensor Optimization","created":"2018-02-26","cited_by_count":426},{"id":"1912.13213","title":"Online Learning: A Modern Introduction Using Convex Optimization","created":"2019-12-31","cited_by_count":417},{"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":"1805.11604","title":"How Does Batch Normalization Help Optimization?","created":"2018-05-29","cited_by_count":357},{"id":"1905.11881","title":"Why gradient clipping accelerates training: A theoretical justification for adaptivity","created":"2019-05-28","cited_by_count":341},{"id":"1905.10018","title":"Momentum-Based Variance Reduction in Non-Convex SGD","created":"2019-05-24","cited_by_count":306},{"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":"1412.0233","title":"The Loss Surfaces of Multilayer Networks","created":"2014-11-30","cited_by_count":280},{"id":"2305.14342","title":"Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training","created":"2023-05-23","cited_by_count":265},{"id":"2006.00719","title":"ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning","created":"2020-06-01","cited_by_count":202},{"id":"1412.6544","title":"Qualitatively characterizing neural network optimization problems","created":"2014-12-19","cited_by_count":188},{"id":"1806.01811","title":"AdaGrad stepsizes: Sharp convergence over nonconvex landscapes","created":"2018-06-05","cited_by_count":182},{"id":"1803.06523","title":"Stochastic model-based minimization of weakly convex functions","created":"2018-03-17","cited_by_count":159},{"id":"2002.03329","title":"Better Theory for SGD in the Nonconvex World","created":"2020-02-09","cited_by_count":158},{"id":"1805.08114","title":"On the Convergence of Stochastic Gradient Descent with Adaptive Stepsizes","created":"2018-05-21","cited_by_count":156},{"id":"1712.07897","title":"Non-convex Optimization for Machine Learning","created":"2017-12-21","cited_by_count":133},{"id":"2207.14484","title":"Adaptive Gradient Methods at the Edge of Stability","created":"2022-07-29","cited_by_count":101},{"id":"2206.04817","title":"The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon","created":"2022-06-10","cited_by_count":94},{"id":"2007.03479","title":"Dynamic Regret of Convex and Smooth Functions","created":"2020-07-07","cited_by_count":90},{"id":"1802.08770","title":"A Walk with SGD","created":"2018-02-24","cited_by_count":78},{"id":"1603.05643","title":"Variance Reduction for Faster Non-Convex Optimization","created":"2016-03-17","cited_by_count":72},{"id":"2202.05791","title":"The Power of Adaptivity in SGD: Self-Tuning Step Sizes with Unbounded Gradients and Affine Variance","created":"2022-02-11","cited_by_count":61},{"id":"2305.18471","title":"Convergence of AdaGrad for Non-convex Objectives: Simple Proofs and Relaxed Assumptions","created":"2023-05-29","cited_by_count":57},{"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":"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":"2306.01264","title":"Convex and Non-convex Optimization Under Generalized Smoothness","created":"2023-06-02","cited_by_count":44},{"id":"2006.13476","title":"Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations","created":"2020-06-24","cited_by_count":40},{"id":"2002.05466","title":"Convergence of a Stochastic Gradient Method with Momentum for Non-Smooth Non-Convex Optimization","created":"2020-02-13","cited_by_count":32},{"id":"2402.01567","title":"Understanding Adam Optimizer via Online Learning of Updates: Adam is FTRL in Disguise","created":"2024-02-02","cited_by_count":26},{"id":"1612.04010","title":"An empirical analysis of the optimization of deep network loss surfaces","created":"2016-12-13","cited_by_count":21},{"id":"2405.09742","title":"Random Scaling and Momentum for Non-smooth Non-convex Optimization","created":"2024-05-16","cited_by_count":19},{"id":"2103.03265","title":"Better SGD using Second-order Momentum","created":"2021-03-04","cited_by_count":15},{"id":"2002.04130","title":"Complexity of Finding Stationary Points of Nonsmooth Nonconvex Functions","created":"2020-02-10","cited_by_count":13},{"id":"2209.14827","title":"On the Convergence of AdaGrad(Norm) on $\\R^{d}$: Beyond Convexity, Non-Asymptotic Rate and Acceleration","created":"2022-09-29","cited_by_count":13},{"id":"2311.04163","title":"Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization","created":"2023-11-07","cited_by_count":13},{"id":"2210.06328","title":"Momentum Aggregation for Private Non-convex ERM","created":"2022-10-12","cited_by_count":10},{"id":"1903.00974","title":"Anytime Online-to-Batch Conversions, Optimism, and Acceleration","created":"2019-03-03","cited_by_count":3}],"next_cursor":null}