{"list":"other","total":55,"rows":[{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1503.05671","title":"Optimizing Neural Networks with Kronecker-factored Approximate Curvature","created":"2015-03-19","cited_by_count":796},{"id":"2008.08186","title":"Prevalence of Neural Collapse during the terminal phase of deep learning training","created":"2020-08-18","cited_by_count":719},{"id":"1810.02054","title":"Gradient Descent Provably Optimizes Over-parameterized Neural Networks","created":"2018-10-04","cited_by_count":659},{"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":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"1802.09568","title":"Shampoo: Preconditioned Stochastic Tensor Optimization","created":"2018-02-26","cited_by_count":426},{"id":"1805.11604","title":"How Does Batch Normalization Help Optimization?","created":"2018-05-29","cited_by_count":357},{"id":"1901.10159","title":"An Investigation into Neural Net Optimization via Hessian Eigenvalue Density","created":"2019-01-29","cited_by_count":292},{"id":"2110.06296","title":"The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks","created":"2021-10-12","cited_by_count":291},{"id":"1706.04454","title":"Empirical Analysis of the Hessian of Over-Parametrized Neural Networks","created":"2017-06-14","cited_by_count":290},{"id":"1412.0233","title":"The Loss Surfaces of Multilayer Networks","created":"2014-11-30","cited_by_count":280},{"id":"1503.02101","title":"Escaping From Saddle Points --- Online Stochastic Gradient for Tensor Decomposition","created":"2015-03-06","cited_by_count":243},{"id":"1605.07110","title":"Deep Learning without Poor Local Minima","created":"2016-05-23","cited_by_count":234},{"id":"2003.00307","title":"Loss landscapes and optimization in over-parameterized non-linear systems and neural networks","created":"2020-02-29","cited_by_count":233},{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227},{"id":"2409.20325","title":"Old Optimizer, New Norm: An Anthology","created":"2024-09-30","cited_by_count":193},{"id":"1809.09573","title":"Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview","created":"2018-09-25","cited_by_count":160},{"id":"1611.07476","title":"Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond","created":"2016-11-22","cited_by_count":159},{"id":"1704.00708","title":"No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis","created":"2017-04-03","cited_by_count":129},{"id":"1407.1065","title":"Phase Retrieval via Wirtinger Flow: Theory and Algorithms","created":"2014-07-03","cited_by_count":125},{"id":"1605.07272","title":"Matrix Completion has No Spurious Local Minimum","created":"2016-05-24","cited_by_count":125},{"id":"1506.02617","title":"Path-SGD: Path-Normalized Optimization in Deep Neural Networks","created":"2015-06-08","cited_by_count":120},{"id":"1907.04164","title":"Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model","created":"2019-07-09","cited_by_count":117},{"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":"2202.08087","title":"Extended Unconstrained Features Model for Exploring Deep Neural Collapse","created":"2022-02-16","cited_by_count":102},{"id":"2008.11865","title":"Traces of Class/Cross-Class Structure Pervade Deep Learning Spectra","created":"2020-08-27","cited_by_count":94},{"id":"1602.06664","title":"A Geometric Analysis of Phase Retrieval","created":"2016-02-22","cited_by_count":92},{"id":"1905.10961","title":"Fast Convergence of Natural Gradient Descent for Overparameterized Neural Networks","created":"2019-05-27","cited_by_count":76},{"id":"2005.08898","title":"Accelerating Ill-Conditioned Low-Rank Matrix Estimation via Scaled Gradient Descent","created":"2020-05-18","cited_by_count":71},{"id":"1901.08244","title":"Measurements of Three-Level Hierarchical Structure in the Outliers in the Spectrum of Deepnet Hessians","created":"2019-01-24","cited_by_count":68},{"id":"1602.06661","title":"Error bounds, quadratic growth, and linear convergence of proximal methods","created":"2016-02-22","cited_by_count":60},{"id":"1511.03607","title":"Complete Dictionary Recovery over the Sphere I: Overview and the Geometric Picture","created":"2015-11-11","cited_by_count":49},{"id":"2305.13165","title":"Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model","created":"2023-05-22","cited_by_count":43},{"id":"1905.11675","title":"Gram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems","created":"2019-05-28","cited_by_count":40},{"id":"1605.00405","title":"Gradient Descent Only Converges to Minimizers: Non-Isolated Critical Points and Invariant Regions","created":"2016-05-02","cited_by_count":34},{"id":"1811.02564","title":"On exponential convergence of SGD in non-convex over-parametrized learning","created":"2018-11-06","cited_by_count":33},{"id":"2302.01186","title":"The Power of Preconditioning in Overparameterized Low-Rank Matrix Sensing","created":"2023-02-02","cited_by_count":33},{"id":"2007.06753","title":"From Symmetry to Geometry: Tractable Nonconvex Problems","created":"2020-07-14","cited_by_count":29},{"id":"1511.04777","title":"Complete Dictionary Recovery over the Sphere II: Recovery by Riemannian Trust-region Method","created":"2015-11-15","cited_by_count":24},{"id":"1403.3862","title":"Asynchronous Stochastic Coordinate Descent: Parallelism and Convergence Properties","created":"2014-03-15","cited_by_count":21},{"id":"1706.05598","title":"On the Optimization Landscape of Tensor Decompositions","created":"2017-06-18","cited_by_count":21},{"id":"2004.05788","title":"The Numerics of Phase Retrieval","created":"2020-04-13","cited_by_count":21},{"id":"2207.03512","title":"The effect of smooth parametrizations on nonconvex optimization landscapes","created":"2022-07-07","cited_by_count":21},{"id":"2409.04180","title":"The Prevalence of Neural Collapse in Neural Multivariate Regression","created":"2024-09-06","cited_by_count":21},{"id":"2302.07384","title":"The Geometry of Neural Nets' Parameter Spaces Under Reparametrization","created":"2023-02-14","cited_by_count":16},{"id":"1806.00338","title":"Structured Local Optima in Sparse Blind Deconvolution","created":"2018-06-01","cited_by_count":15},{"id":"2411.01248","title":"Guiding Neural Collapse: Optimising Towards the Nearest Simplex Equiangular Tight Frame","created":"2024-11-02","cited_by_count":14},{"id":"2410.23169","title":"The Persistence of Neural Collapse Despite Low-Rank Bias","created":"2024-10-30","cited_by_count":13},{"id":"1901.00256","title":"Geometry and Symmetry in Short-and-Sparse Deconvolution","created":"2019-01-02","cited_by_count":11},{"id":"1809.10313","title":"Efficient Dictionary Learning with Gradient Descent","created":"2018-09-27","cited_by_count":10},{"id":"1908.10959","title":"Short-and-Sparse Deconvolution -- A Geometric Approach","created":"2019-08-28","cited_by_count":9},{"id":"1912.02427","title":"Analysis of the Optimization Landscapes for Overcomplete Representation Learning","created":"2019-12-05","cited_by_count":7},{"id":"1908.10776","title":"A Nonconvex Approach for Exact and Efficient Multichannel Sparse Blind Deconvolution","created":"2019-08-28","cited_by_count":5}],"next_cursor":null}