{"list":"other","total":75,"rows":[{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"2006.09661","title":"Implicit Neural Representations with Periodic Activation Functions","created":"2020-06-17","cited_by_count":2238},{"id":"2006.10739","title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","created":"2020-06-18","cited_by_count":2200},{"id":"1806.08734","title":"On the Spectral Bias of Neural Networks","created":"2018-06-22","cited_by_count":1341},{"id":"2002.10099","title":"Implicit Geometric Regularization for Learning Shapes","created":"2020-02-24","cited_by_count":710},{"id":"1901.10159","title":"An Investigation into Neural Net Optimization via Hessian Eigenvalue Density","created":"2019-01-29","cited_by_count":292},{"id":"1706.04454","title":"Empirical Analysis of the Hessian of Over-Parametrized Neural Networks","created":"2017-06-14","cited_by_count":290},{"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":"2301.05187","title":"WIRE: Wavelet Implicit Neural Representations","created":"2023-01-05","cited_by_count":220},{"id":"1812.04754","title":"Gradient Descent Happens in a Tiny Subspace","created":"2018-12-12","cited_by_count":217},{"id":"2409.11321","title":"SOAP: Improving and Stabilizing Shampoo using Adam","created":"2024-09-17","cited_by_count":192},{"id":"1710.11606","title":"Lower Bounds for Finding Stationary Points I","created":"2017-10-31","cited_by_count":126},{"id":"2402.16788","title":"Why Transformers Need Adam: A Hessian Perspective","created":"2024-02-26","cited_by_count":124},{"id":"2207.14484","title":"Adaptive Gradient Methods at the Edge of Stability","created":"2022-07-29","cited_by_count":101},{"id":"2312.02434","title":"FINER: Flexible spectral-bias tuning in Implicit NEural Representation by Variable-periodic Activation Functions","created":"2023-12-05","cited_by_count":78},{"id":"1705.05933","title":"Sub-sampled Cubic Regularization for Non-convex Optimization","created":"2017-05-16","cited_by_count":63},{"id":"1711.02838","title":"Stochastic Cubic Regularization for Fast Nonconvex Optimization","created":"2017-11-08","cited_by_count":55},{"id":"2101.09545","title":"Acceleration Methods","created":"2021-01-23","cited_by_count":48},{"id":"1708.07164","title":"Newton-Type Methods for Non-Convex Optimization Under Inexact Hessian Information","created":"2017-08-23","cited_by_count":41},{"id":"2211.02254","title":"How Does Adaptive Optimization Impact Local Neural Network Geometry?","created":"2022-11-04","cited_by_count":24},{"id":"2410.08198","title":"Adam Exploits $\\ell_\\infty$-geometry of Loss Landscape via Coordinate-wise Adaptivity","created":"2024-10-10","cited_by_count":23},{"id":"2112.02089","title":"Regularized Newton Method with Global $O(1/k^2)$ Convergence","created":"2021-12-03","cited_by_count":22},{"id":"2205.12856","title":"Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Function","created":"2022-05-25","cited_by_count":20},{"id":"2402.07114","title":"Towards Quantifying the Preconditioning Effect of Adam","created":"2024-02-11","cited_by_count":19},{"id":"1612.00547","title":"Gradient Descent Finds the Cubic-Regularized Non-Convex Newton Step","created":"2016-12-02","cited_by_count":18},{"id":"2510.09378","title":"The Potential of Second-Order Optimization for LLMs: A Study with Full Gauss-Newton","created":"2025-10-10","cited_by_count":17},{"id":"2212.00781","title":"Second-order optimization with lazy Hessians","created":"2022-12-01","cited_by_count":15},{"id":"1802.04084","title":"Randomized Block Cubic Newton Method","created":"2018-02-12","cited_by_count":14},{"id":"2410.05050","title":"FreSh: Frequency Shifting for Accelerated Neural Representation Learning","created":"2024-10-07","cited_by_count":14},{"id":"2505.02809","title":"Towards Quantifying the Hessian Structure of Neural Networks","created":"2025-05-05","cited_by_count":13},{"id":"2302.11962","title":"Unified Convergence Theory of Stochastic and Variance-Reduced Cubic Newton Methods","created":"2023-02-23","cited_by_count":12},{"id":"2407.19434","title":"FINER++: Building a Family of Variable-periodic Functions for Activating Implicit Neural Representation","created":"2024-07-28","cited_by_count":11},{"id":"2410.19964","title":"Understanding Adam Requires Better Rotation Dependent Assumptions","created":"2024-10-25","cited_by_count":11},{"id":"1806.09222","title":"Analysis of Krylov Subspace Solutions of Regularized Nonconvex Quadratic Problems","created":"2018-06-24","cited_by_count":9},{"id":"2410.13271","title":"Inductive Gradient Adjustment For Spectral Bias In Implicit Neural Representations","created":"2024-10-17","cited_by_count":8},{"id":"2505.20473","title":"Stochastic Preconditioning for Neural Field Optimization","created":"2025-05-26","cited_by_count":8},{"id":"2012.15636","title":"Inexact Tensor Methods and Their Application to Stochastic Convex Optimization","created":"2020-12-31","cited_by_count":6},{"id":"2309.02412","title":"First and zeroth-order implementations of the regularized Newton method with lazy approximated Hessians","created":"2023-09-05","cited_by_count":6},{"id":"2402.04843","title":"Spectral Preconditioning for Gradient Methods on Graded Non-convex Functions","created":"2024-02-07","cited_by_count":6},{"id":"2410.19644","title":"Improving Stochastic Cubic Newton with Momentum","created":"2024-10-25","cited_by_count":6},{"id":"2209.04170","title":"Theoretical analysis of the randomized subspace regularized Newton method for non-convex optimization","created":"2022-09-09","cited_by_count":5},{"id":"2402.08784","title":"Preconditioners for the Stochastic Training of Neural Fields","created":"2024-02-13","cited_by_count":5},{"id":"2401.03058","title":"Krylov Cubic Regularized Newton: A Subspace Second-Order Method with Dimension-Free Convergence Rate","created":"2024-01-05","cited_by_count":3},{"id":"2406.16666","title":"Cubic regularized subspace Newton for non-convex optimization","created":"2024-06-24","cited_by_count":3},{"id":"2407.03571","title":"A Fully Parameter-Free Second-Order Algorithm for Convex-Concave Minimax Problems","created":"2024-07-04","cited_by_count":3},{"id":"2504.20096","title":"Towards Practical Second-Order Optimizers in Deep Learning: Insights from Fisher Information Analysis","created":"2025-04-26","cited_by_count":3},{"id":"2506.13710","title":"Gradient-Normalized Smoothness for Optimization with Approximate Hessians","created":"2025-06-16","cited_by_count":3},{"id":"2103.16659","title":"Scalable adaptive cubic regularization methods","created":"2021-03-30","cited_by_count":2},{"id":"2301.13194","title":"Polynomial Preconditioning for Gradient Methods","created":"2023-01-30","cited_by_count":2},{"id":"2309.04052","title":"Riemannian Adaptive Regularized Newton Methods with H\\\"older Continuous Hessians","created":"2023-09-08","cited_by_count":2},{"id":"2502.12298","title":"Symmetric Rank-One Quasi-Newton Methods for Deep Learning Using Cubic Regularization","created":"2025-02-17","cited_by_count":2},{"id":"2204.09116","title":"A Novel Fast Exact Subproblem Solver for Stochastic Quasi-Newton Cubic Regularized Optimization","created":"2022-04-19","cited_by_count":1},{"id":"2306.14290","title":"Regularized methods via cubic model subspace minimization for nonconvex optimization","created":"2023-06-25","cited_by_count":1},{"id":"2308.13161","title":"First- and Second-Order Stochastic Adaptive Regularization with Cubics: High Probability Iteration and Sample Complexity","created":"2023-08-25","cited_by_count":1},{"id":"2312.03885","title":"Gathering and Exploiting Higher-Order Information when Training Large Structured Models","created":"2023-12-06","cited_by_count":1},{"id":"2406.14337","title":"Improving Convergence Guarantees of Random Subspace Second-order Algorithm for Nonconvex Optimization","created":"2024-06-20","cited_by_count":1},{"id":"2407.18150","title":"Block cubic Newton with greedy selection","created":"2024-07-25","cited_by_count":1},{"id":"2408.04315","title":"Federated Cubic Regularized Newton Learning with Sparsification-amplified Differential Privacy","created":"2024-08-08","cited_by_count":1},{"id":"2412.02079","title":"A simple and practical adaptive trust-region method","created":"2024-12-03","cited_by_count":1},{"id":"2501.03718","title":"Scalable Second-Order Optimization Algorithms for Minimizing Low-rank Functions","created":"2025-01-07","cited_by_count":1},{"id":"2501.09734","title":"Random Subspace Cubic-Regularization Methods, with Applications to Low-Rank Functions","created":"2025-01-16","cited_by_count":1},{"id":"2503.11254","title":"A scalable sequential adaptive cubic regularization algorithm for optimization with general equality constraints","created":"2025-03-14","cited_by_count":1},{"id":"2509.07580","title":"On Global Rates for Regularization Methods based on Secant Derivative Approximations","created":"2025-09-09","cited_by_count":1},{"id":"2510.08714","title":"Cubic Regularized Newton Method with Variance Reduction for Finite-sum Non-convex Problems","created":"2025-10-09","cited_by_count":1},{"id":"2511.07341","title":"Universal Reduced-Operator Method and High-Order Global Curvature Bounds","created":"2025-11-10","cited_by_count":1},{"id":"2511.11135","title":"Extended-Krylov-subspace methods for trust-region and norm-regularization subproblems","created":"2025-11-14","cited_by_count":1},{"id":"2512.08775","title":"Adaptive Regularized Newton Method with Inexact Hessian","created":"2025-12-09","cited_by_count":1},{"id":"2601.01575","title":"A MINRES-based Linesearch Algorithm for Nonconvex Optimization with Non-positive Curvature Detection","created":"2026-01-04","cited_by_count":1},{"id":"2604.02763","title":"Adaptive Newton-CG methods with global and local analysis for unconstrained optimization with H\\\"older continuous Hessian","created":"2026-04-03","cited_by_count":1},{"id":"2604.09437","title":"AdaCubic: An Adaptive Cubic Regularization Optimizer for Deep Learning","created":"2026-04-10","cited_by_count":1},{"id":"2604.15457","title":"Adaptive Regularization within Trust Region Methods for Stochastic Nonconvex Optimization","created":"2026-04-16","cited_by_count":1},{"id":"2605.30891","title":"A General Recipe for Parameter-Free Nonconvex Optimization via Higher-Order Regularization","created":"2026-05-29","cited_by_count":1},{"id":"2606.16671","title":"Chebyshev-Exact Acceleration under Hessian Variation, I: Sine-Jacobi Method","created":"2026-06-15","cited_by_count":1},{"id":"2607.10741","title":"Parameter-Free Cubic-Regularized Newton Method: Sharp Complexity and Generalized Smoothness","created":"2026-07-12","cited_by_count":1}],"next_cursor":null}