{"total":32,"rows":[{"id":"2204.01050","title":"Understanding the unstable convergence of gradient descent","created":"2022-04-03","cited_by_count":86,"area":null},{"id":"2206.07085","title":"Understanding the Generalization Benefit of Normalization Layers: Sharpness Reduction","created":"2022-06-14","cited_by_count":86,"area":null},{"id":"2106.14289","title":"Global Convergence of Gradient Descent for Asymmetric Low-Rank Matrix Factorization","created":"2021-06-27","cited_by_count":45,"area":null},{"id":"2208.13614","title":"Neural Tangent Kernel: A Survey","created":"2022-08-29","cited_by_count":23,"area":null},{"id":"2402.08508","title":"A PAC-Bayesian Link Between Generalisation and Flat Minima","created":"2024-02-13","cited_by_count":13,"area":null},{"id":"2103.10922","title":"Landscape analysis for shallow neural networks: complete classification of critical points for affine target functions","created":"2021-03-19","cited_by_count":11,"area":null},{"id":"2108.04620","title":"A proof of convergence for the gradient descent optimization method with random initializations in the training of neural networks with ReLU activation for piecewise linear target functions","created":"2021-08-10","cited_by_count":10,"area":null},{"id":"2104.00277","title":"A proof of convergence for stochastic gradient descent in the training of artificial neural networks with ReLU activation for constant target functions","created":"2021-04-01","cited_by_count":9,"area":null},{"id":"2112.07369","title":"Convergence proof for stochastic gradient descent in the training of deep neural networks with ReLU activation for constant target functions","created":"2021-12-13","cited_by_count":9,"area":null},{"id":"2101.05248","title":"Solving Min-Max Optimization with Hidden Structure via Gradient Descent Ascent","created":"2021-01-13","cited_by_count":8,"area":null},{"id":"2208.02083","title":"Gradient descent provably escapes saddle points in the training of shallow ReLU networks","created":"2022-08-03","cited_by_count":5,"area":null},{"id":"2507.15264","title":"On exploration of an interior mirror descent flow for stochastic nonconvex constrained problem","created":"2025-07-21","cited_by_count":3,"area":null},{"id":"2111.04596","title":"Inertial Newton Algorithms Avoiding Strict Saddle Points","created":"2021-11-08","cited_by_count":2,"area":null},{"id":"2209.03705","title":"Losing momentum in continuous-time stochastic optimisation","created":"2022-09-08","cited_by_count":2,"area":null},{"id":"2507.06367","title":"The Riemannian Geometry Associated to Gradient Flows of Linear Convolutional Networks","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2108.10249","title":"New Q-Newton's method meets Backtracking line search: good convergence guarantee, saddle points avoidance, quadratic rate of convergence, and easy implementation","created":"2021-08-23","cited_by_count":1,"area":null},{"id":"2112.13269","title":"Over-Parametrized Matrix Factorization in the Presence of Spurious Stationary Points","created":"2021-12-25","cited_by_count":1,"area":null},{"id":"2302.07862","title":"Almost Sure Saddle Avoidance of Stochastic Gradient Methods without the Bounded Gradient Assumption","created":"2023-02-15","cited_by_count":1,"area":null},{"id":"2305.09904","title":"On the ISS Property of the Gradient Flow for Single Hidden-Layer Neural Networks with Linear Activations","created":"2023-05-17","cited_by_count":1,"area":null},{"id":"2406.05666","title":"Probability Distribution Learning and Its Application in Deep Learning","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2104.01730","title":"Training Deep Neural Networks via Branch-and-Bound","created":"2021-04-05","cited_by_count":0,"area":null},{"id":"2107.09207","title":"Asymptotic Escape of Spurious Critical Points on the Low-rank Matrix Manifold","created":"2021-07-20","cited_by_count":0,"area":null},{"id":"2109.03974","title":"Constants of Motion: The Antidote to Chaos in Optimization and Game Dynamics","created":"2021-09-08","cited_by_count":0,"area":null},{"id":"2204.11407","title":"Accelerated Multiplicative Weights Update Avoids Saddle Points almost always","created":"2022-04-25","cited_by_count":0,"area":null},{"id":"2402.18830","title":"Training-set-free two-stage deep learning for spectroscopic data de-noising","created":"2024-02-29","cited_by_count":0,"area":null},{"id":"2502.19210","title":"Langevin Multiplicative Weights Update with Applications in Polynomial Portfolio Management","created":"2025-02-26","cited_by_count":0,"area":null},{"id":"2506.08428","title":"Sharper Convergence Rates for Nonconvex Optimisation via Reduction Mappings","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2510.09034","title":"Convergence of optimizers implies eigenvalues filtering at equilibrium","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2510.09923","title":"AutoGD: Automatic Learning Rate Selection for Gradient Descent","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2510.24466","title":"Non-Singularity of the Gradient Descent map for Neural Networks with Piecewise Analytic Activations","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2605.18315","title":"Attention-based PCA","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2607.11752","title":"Paradoxes of Game Theoretic Equilibria and Price of Anarchy","created":"2026-07-13","cited_by_count":0,"area":null}],"next_cursor":null}