{"total":274,"rows":[{"id":"2202.06709","title":"How Do Vision Transformers Work?","created":"2022-02-14","cited_by_count":307,"area":null},{"id":"2102.01356","title":"Recent Advances in Adversarial Training for Adversarial Robustness","created":"2021-02-02","cited_by_count":279,"area":null},{"id":"2105.12221","title":"Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances","created":"2021-05-25","cited_by_count":127,"area":null},{"id":"2402.01868","title":"Challenges in Training PINNs: A Loss Landscape Perspective","created":"2024-02-02","cited_by_count":113,"area":null},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"area":null},{"id":"2102.10472","title":"Learning Neural Network Subspaces","created":"2021-02-20","cited_by_count":82,"area":null},{"id":"2202.00661","title":"When Do Flat Minima Optimizers Work?","created":"2022-02-01","cited_by_count":78,"area":null},{"id":"2206.00939","title":"Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs","created":"2022-06-02","cited_by_count":76,"area":null},{"id":"2211.13609","title":"PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization","created":"2022-11-24","cited_by_count":76,"area":null},{"id":"2201.08025","title":"Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape","created":"2022-01-20","cited_by_count":39,"area":null},{"id":"2209.14764","title":"Model Zoos: A Dataset of Diverse Populations of Neural Network Models","created":"2022-09-29","cited_by_count":39,"area":null},{"id":"2306.06179","title":"Hidden symmetries of ReLU networks","created":"2023-06-09","cited_by_count":39,"area":null},{"id":"2102.04396","title":"SGD in the Large: Average-case Analysis, Asymptotics, and Stepsize Criticality","created":"2021-02-08","cited_by_count":35,"area":null},{"id":"2106.03273","title":"Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation","created":"2021-06-06","cited_by_count":35,"area":null},{"id":"2107.11228","title":"Taxonomizing local versus global structure in neural network loss landscapes","created":"2021-07-23","cited_by_count":34,"area":null},{"id":"2103.01519","title":"Hessian Eigenspectra of More Realistic Nonlinear Models","created":"2021-03-02","cited_by_count":33,"area":null},{"id":"2210.12153","title":"On amortizing convex conjugates for optimal transport","created":"2022-10-21","cited_by_count":31,"area":null},{"id":"2310.10195","title":"AdaLomo: Low-memory Optimization with Adaptive Learning Rate","created":"2023-10-16","cited_by_count":31,"area":null},{"id":"2201.12250","title":"Gradient Descent on Neurons and its Link to Approximate Second-Order Optimization","created":"2022-01-28","cited_by_count":30,"area":null},{"id":"2208.12590","title":"Ab-initio quantum chemistry with neural-network wavefunctions","created":"2022-08-26","cited_by_count":29,"area":null},{"id":"2305.16971","title":"Theoretical and Practical Perspectives on what Influence Functions Do","created":"2023-05-26","cited_by_count":29,"area":null},{"id":"2305.18246","title":"Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo","created":"2023-05-29","cited_by_count":29,"area":null},{"id":"2107.05802","title":"How many degrees of freedom do we need to train deep networks: a loss landscape perspective","created":"2021-07-13","cited_by_count":28,"area":null},{"id":"2212.13827","title":"Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data","created":"2022-12-28","cited_by_count":28,"area":null},{"id":"2203.14661","title":"Random matrix analysis of deep neural network weight matrices","created":"2022-03-28","cited_by_count":21,"area":null},{"id":"2305.04684","title":"ASDL: A Unified Interface for Gradient Preconditioning in PyTorch","created":"2023-05-08","cited_by_count":21,"area":null},{"id":"2106.00669","title":"Discovering Diverse Nearly Optimal Policies with Successor Features","created":"2021-06-01","cited_by_count":20,"area":null},{"id":"2202.03684","title":"Efficiently Escaping Saddle Points in Bilevel Optimization","created":"2022-02-08","cited_by_count":19,"area":null},{"id":"2203.06498","title":"The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learning","created":"2022-03-12","cited_by_count":17,"area":null},{"id":"2303.09728","title":"The Cascaded Forward Algorithm for Neural Network Training","created":"2023-03-17","cited_by_count":17,"area":null},{"id":"2306.14853","title":"Near-Optimal Nonconvex-Strongly-Convex Bilevel Optimization with Fully First-Order Oracles","created":"2023-06-26","cited_by_count":17,"area":null},{"id":"2507.12224","title":"Optimizers Qualitatively Alter Solutions And We Should Leverage This","created":"2025-07-16","cited_by_count":17,"area":null},{"id":"2106.03696","title":"Dynamics of Stochastic Momentum Methods on Large-scale, Quadratic Models","created":"2021-06-07","cited_by_count":16,"area":null},{"id":"2201.13011","title":"On the Power-Law Hessian Spectrums in Deep Learning","created":"2022-01-31","cited_by_count":16,"area":null},{"id":"2208.13219","title":"Visualizing high-dimensional loss landscapes with Hessian directions","created":"2022-08-28","cited_by_count":16,"area":null},{"id":"2305.19440","title":"Machine learning with tree tensor networks, CP rank constraints, and tensor dropout","created":"2023-05-30","cited_by_count":15,"area":null},{"id":"2307.00126","title":"Accelerating Inexact HyperGradient Descent for Bilevel Optimization","created":"2023-06-30","cited_by_count":15,"area":null},{"id":"2107.04228","title":"Activated Gradients for Deep Neural Networks","created":"2021-07-09","cited_by_count":14,"area":null},{"id":"2307.11782","title":"Convergence of Adam for Non-convex Objectives: Relaxed Hyperparameters and Non-ergodic Case","created":"2023-07-20","cited_by_count":14,"area":null},{"id":"2401.12033","title":"Momentum-SAM: Sharpness Aware Minimization without Computational Overhead","created":"2024-01-22","cited_by_count":14,"area":null},{"id":"2507.18807","title":"Fishers for Free? Approximating the Fisher Information Matrix by Recycling the Squared Gradient Accumulator","created":"2025-07-24","cited_by_count":14,"area":null},{"id":"2106.02119","title":"A Scalable Second Order Method for Ill-Conditioned Matrix Completion from Few Samples","created":"2021-06-03","cited_by_count":13,"area":null},{"id":"2212.02083","title":"On the Overlooked Structure of Stochastic Gradients","created":"2022-12-05","cited_by_count":13,"area":null},{"id":"2505.02809","title":"Towards Quantifying the Hessian Structure of Neural Networks","created":"2025-05-05","cited_by_count":13,"area":null},{"id":"2111.13331","title":"Impact of classification difficulty on the weight matrices spectra in Deep Learning and application to early-stopping","created":"2021-11-26","cited_by_count":12,"area":null},{"id":"2210.12936","title":"Selecting and Composing Learning Rate Policies for Deep Neural Networks","created":"2022-10-24","cited_by_count":12,"area":null},{"id":"2310.06756","title":"Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory","created":"2023-10-10","cited_by_count":12,"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":"2111.14069","title":"Escape saddle points by a simple gradient-descent based algorithm","created":"2021-11-28","cited_by_count":11,"area":null},{"id":"2212.07959","title":"Scalable Bayesian Uncertainty Quantification for Neural Network Potentials: Promise and Pitfalls","created":"2022-12-15","cited_by_count":11,"area":null},{"id":"2302.01952","title":"On a continuous time model of gradient descent dynamics and instability in deep learning","created":"2023-02-03","cited_by_count":11,"area":null},{"id":"2404.06106","title":"Unifying Low Dimensional Spectra in Deep Learning","created":"2024-04-09","cited_by_count":11,"area":null},{"id":"2305.09088","title":"The Hessian perspective into the Nature of Convolutional Neural Networks","created":"2023-05-16","cited_by_count":10,"area":null},{"id":"2510.08177","title":"Long-tailed Recognition with Model Rebalancing","created":"2025-10-09","cited_by_count":10,"area":null},{"id":"2107.12910","title":"Sparse Bayesian Deep Learning for Dynamic System Identification","created":"2021-07-27","cited_by_count":9,"area":null},{"id":"2203.00089","title":"Amortized Proximal Optimization","created":"2022-02-28","cited_by_count":9,"area":null},{"id":"2106.02985","title":"Escaping Saddle Points Faster with Stochastic Momentum","created":"2021-06-05","cited_by_count":8,"area":null},{"id":"2108.12107","title":"An Introduction to Hamiltonian Monte Carlo Method for Sampling","created":"2021-08-27","cited_by_count":8,"area":null},{"id":"2202.12262","title":"On the Omnipresence of Spurious Local Minima in Certain Neural Network Training Problems","created":"2022-02-23","cited_by_count":8,"area":null},{"id":"2303.13093","title":"Type-II Saddles and Probabilistic Stability of Stochastic Gradient Descent","created":"2023-03-23","cited_by_count":8,"area":null},{"id":"2405.18979","title":"MANO: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts","created":"2024-05-29","cited_by_count":8,"area":null},{"id":"2410.21481","title":"A Mathematical Analysis of Neural Operator Behaviors","created":"2024-10-28","cited_by_count":8,"area":null},{"id":"2506.02269","title":"A Tale of Two Symmetries: Exploring the Loss Landscape of Equivariant Models","created":"2025-06-02","cited_by_count":8,"area":null},{"id":"2102.06740","title":"Appearance of Random Matrix Theory in Deep Learning","created":"2021-02-12","cited_by_count":7,"area":null},{"id":"2102.13233","title":"Spurious Local Minima Are Common for Deep Neural Networks with Piecewise Linear Activations","created":"2021-02-25","cited_by_count":7,"area":null},{"id":"2210.00973","title":"NCVX: A General-Purpose Optimization Solver for Constrained Machine and Deep Learning","created":"2022-10-03","cited_by_count":7,"area":null},{"id":"2407.10780","title":"Correlations Are Ruining Your Gradient Descent","created":"2024-07-15","cited_by_count":7,"area":null},{"id":"2412.10153","title":"EVOS: Efficient Implicit Neural Training via EVOlutionary Selector","created":"2024-12-13","cited_by_count":7,"area":null},{"id":"2602.15322","title":"On Surprising Effectiveness of Masking Updates in Adaptive Optimizers","created":"2026-02-17","cited_by_count":7,"area":null},{"id":"2108.06711","title":"Towards Understanding Theoretical Advantages of Complex-Reaction Networks","created":"2021-08-15","cited_by_count":6,"area":null},{"id":"2109.15048","title":"Scale-invariant Learning by Physics Inversion","created":"2021-09-30","cited_by_count":6,"area":null},{"id":"2111.05496","title":"ResNEsts and DenseNEsts: Block-based DNN Models with Improved Representation Guarantees","created":"2021-11-10","cited_by_count":6,"area":null},{"id":"2111.12927","title":"Rethinking Generic Camera Models for Deep Single Image Camera Calibration to Recover Rotation and Fisheye Distortion","created":"2021-11-25","cited_by_count":6,"area":null},{"id":"2304.04858","title":"Simulated Annealing in Early Layers Leads to Better Generalization","created":"2023-04-10","cited_by_count":6,"area":null},{"id":"2107.09532","title":"Estimation of a regression function on a manifold by fully connected deep neural networks","created":"2021-07-20","cited_by_count":5,"area":null},{"id":"2110.07098","title":"A Cubic Regularization Approach for Finding Local Minimax Points in Nonconvex Minimax Optimization","created":"2021-10-14","cited_by_count":5,"area":null},{"id":"2111.13984","title":"NCVX: A User-Friendly and Scalable Package for Nonconvex Optimization in Machine Learning","created":"2021-11-27","cited_by_count":5,"area":null},{"id":"2202.10600","title":"Myriad: a real-world testbed to bridge trajectory optimization and deep learning","created":"2022-02-22","cited_by_count":5,"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":"2306.07104","title":"Unveiling the Hessian's Connection to the Decision Boundary","created":"2023-06-12","cited_by_count":5,"area":null},{"id":"2306.10404","title":"The RL Perceptron: Generalisation Dynamics of Policy Learning in High Dimensions","created":"2023-06-17","cited_by_count":5,"area":null},{"id":"2310.03165","title":"Enhancing Accuracy in Deep Learning Using Random Matrix Theory","created":"2023-10-04","cited_by_count":5,"area":null},{"id":"2409.15734","title":"Trust-Region Sequential Quadratic Programming for Stochastic Optimization with Random Models","created":"2024-09-24","cited_by_count":5,"area":null},{"id":"2502.02002","title":"The Ball-Proximal (=\"Broximal\") Point Method: a New Algorithm, Convergence Theory, and Applications","created":"2025-02-04","cited_by_count":5,"area":null},{"id":"2506.05713","title":"Come Together, But Not Right Now: A Progressive Strategy to Boost Low-Rank Adaptation","created":"2025-06-06","cited_by_count":5,"area":null},{"id":"2102.02837","title":"Escaping Saddle Points for Nonsmooth Weakly Convex Functions via Perturbed Proximal Algorithms","created":"2021-02-04","cited_by_count":4,"area":null},{"id":"2109.04983","title":"A Neural Tangent Kernel Perspective of Infinite Tree Ensembles","created":"2021-09-10","cited_by_count":4,"area":null},{"id":"2110.00959","title":"Boost Neural Networks by Checkpoints","created":"2021-10-03","cited_by_count":4,"area":null},{"id":"2112.04266","title":"Forecasting Brain Activity Based on Models of Spatio-Temporal Brain Dynamics: A Comparison of Graph Neural Network Architectures","created":"2021-12-08","cited_by_count":4,"area":null},{"id":"2205.00832","title":"Gradient Descent, Stochastic Optimization, and Other Tales","created":"2022-05-02","cited_by_count":4,"area":null},{"id":"2303.08096","title":"MELON: NeRF with Unposed Images in SO(3)","created":"2023-03-14","cited_by_count":4,"area":null},{"id":"2304.07247","title":"The R-mAtrIx Net","created":"2023-04-14","cited_by_count":4,"area":null},{"id":"2308.04457","title":"A Critical Review of Physics-Informed Machine Learning Applications in Subsurface Energy Systems","created":"2023-08-06","cited_by_count":4,"area":null},{"id":"2310.19059","title":"Escaping Saddle Points in Heterogeneous Federated Learning via Distributed SGD with Communication Compression","created":"2023-10-29","cited_by_count":4,"area":null},{"id":"2502.15496","title":"Verification and Validation for Trustworthy Scientific Machine Learning","created":"2025-02-21","cited_by_count":4,"area":null},{"id":"2503.19091","title":"High Probability Complexity Bounds of Trust-Region Stochastic Sequential Quadratic Programming with Heavy-Tailed Noise","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2101.11487","title":"K\\\"ahler Geometry of Quiver Varieties and Machine Learning","created":"2021-01-27","cited_by_count":3,"area":null},{"id":"2103.09424","title":"Escaping Saddle Points in Distributed Newton's Method with Communication Efficiency and Byzantine Resilience","created":"2021-03-17","cited_by_count":3,"area":null},{"id":"2103.12685","title":"Generative Minimization Networks: Training GANs Without Competition","created":"2021-03-23","cited_by_count":3,"area":null},{"id":"2105.12920","title":"Search Spaces for Neural Model Training","created":"2021-05-27","cited_by_count":3,"area":null}],"next_cursor":"100"}