{"total":150,"rows":[{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227,"area":null},{"id":"2204.13650","title":"Unlocking High-Accuracy Differentially Private Image Classification through Scale","created":"2022-04-28","cited_by_count":224,"area":null},{"id":"2101.12176","title":"On the Origin of Implicit Regularization in Stochastic Gradient Descent","created":"2021-01-28","cited_by_count":184,"area":null},{"id":"2101.12699","title":"Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training","created":"2021-01-29","cited_by_count":166,"area":null},{"id":"2105.14368","title":"Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation","created":"2021-05-29","cited_by_count":132,"area":null},{"id":"2202.08087","title":"Extended Unconstrained Features Model for Exploring Deep Neural Collapse","created":"2022-02-16","cited_by_count":102,"area":null},{"id":"2206.04041","title":"Neural Collapse: A Review on Modelling Principles and Generalization","created":"2022-06-08","cited_by_count":95,"area":null},{"id":"2102.00931","title":"Information-Theoretic Generalization Bounds for Stochastic Gradient Descent","created":"2021-02-01","cited_by_count":84,"area":null},{"id":"2106.07820","title":"On Large-Cohort Training for Federated Learning","created":"2021-06-15","cited_by_count":74,"area":null},{"id":"2410.21676","title":"How Does Critical Batch Size Scale in Pre-training?","created":"2024-10-29","cited_by_count":73,"area":null},{"id":"2201.04122","title":"In Defense of the Unitary Scalarization for Deep Multi-Task Learning","created":"2022-01-11","cited_by_count":67,"area":null},{"id":"2109.14119","title":"Stochastic Training is Not Necessary for Generalization","created":"2021-09-29","cited_by_count":63,"area":null},{"id":"2302.05882","title":"From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks","created":"2023-02-12","cited_by_count":43,"area":null},{"id":"2505.13738","title":"Power Lines: Scaling Laws for Weight Decay and Batch Size in LLM Pre-training","created":"2025-05-19","cited_by_count":43,"area":null},{"id":"2102.03183","title":"Last iterate convergence of SGD for Least-Squares in the Interpolation regime","created":"2021-02-05","cited_by_count":42,"area":null},{"id":"2110.00641","title":"Batch size-invariance for policy optimization","created":"2021-10-01","cited_by_count":35,"area":null},{"id":"2210.16658","title":"Perturbation Analysis of Neural Collapse","created":"2022-10-29","cited_by_count":35,"area":null},{"id":"2105.13343","title":"Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error","created":"2021-05-27","cited_by_count":33,"area":null},{"id":"2106.13897","title":"Implicit Gradient Alignment in Distributed and Federated Learning","created":"2021-06-25","cited_by_count":29,"area":null},{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29,"area":null},{"id":"2507.01598","title":"Convergence Bound and Critical Batch Size of Muon Optimizer","created":"2025-07-02","cited_by_count":28,"area":null},{"id":"2305.07583","title":"MoMo: Momentum Models for Adaptive Learning Rates","created":"2023-05-12","cited_by_count":24,"area":null},{"id":"2104.11125","title":"ScaleCom: Scalable Sparsified Gradient Compression for Communication-Efficient Distributed Training","created":"2021-04-21","cited_by_count":22,"area":null},{"id":"2107.05074","title":"SGD: The Role of Implicit Regularization, Batch-size and Multiple-epochs","created":"2021-07-11","cited_by_count":22,"area":null},{"id":"2110.15412","title":"Stochastic Mirror Descent: Convergence Analysis and Adaptive Variants via the Mirror Stochastic Polyak Stepsize","created":"2021-10-28","cited_by_count":22,"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":"2204.12446","title":"Beyond Lipschitz: Sharp Generalization and Excess Risk Bounds for Full-Batch GD","created":"2022-04-26","cited_by_count":19,"area":null},{"id":"2206.01029","title":"Trajectory of Mini-Batch Momentum: Batch Size Saturation and Convergence in High Dimensions","created":"2022-06-02","cited_by_count":19,"area":null},{"id":"2206.10713","title":"Beyond Uniform Lipschitz Condition in Differentially Private Optimization","created":"2022-06-21","cited_by_count":19,"area":null},{"id":"2306.09000","title":"When and Why Momentum Accelerates SGD:An Empirical Study","created":"2023-06-15","cited_by_count":19,"area":null},{"id":"2307.01951","title":"A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks","created":"2023-07-04","cited_by_count":19,"area":null},{"id":"2503.06339","title":"Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning","created":"2025-03-08","cited_by_count":19,"area":"safety"},{"id":"2202.12328","title":"Cutting Some Slack for SGD with Adaptive Polyak Stepsizes","created":"2022-02-24","cited_by_count":18,"area":null},{"id":"2103.02351","title":"Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates","created":"2021-03-03","cited_by_count":17,"area":null},{"id":"2306.17499","title":"The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks","created":"2023-06-30","cited_by_count":15,"area":null},{"id":"2101.02696","title":"Accelerated, Optimal, and Parallel: Some Results on Model-Based Stochastic Optimization","created":"2021-01-07","cited_by_count":14,"area":null},{"id":"2607.21716","title":"A Defense of the Quadratic Model","created":"2026-07-23","cited_by_count":14,"area":null},{"id":"2102.09645","title":"SVRG Meets AdaGrad: Painless Variance Reduction","created":"2021-02-18","cited_by_count":13,"area":null},{"id":"2206.07553","title":"On the fast convergence of minibatch heavy ball momentum","created":"2022-06-15","cited_by_count":13,"area":null},{"id":"2207.08171","title":"SP2: A Second Order Stochastic Polyak Method","created":"2022-07-17","cited_by_count":13,"area":null},{"id":"2302.02605","title":"Toward Large Kernel Models","created":"2023-02-06","cited_by_count":13,"area":null},{"id":"2406.04142","title":"Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance","created":"2024-06-06","cited_by_count":13,"area":null},{"id":"2102.07586","title":"On Riemannian Stochastic Approximation Schemes with Fixed Step-Size","created":"2021-02-15","cited_by_count":12,"area":null},{"id":"2210.14019","title":"The Curious Case of Benign Memorization","created":"2022-10-25","cited_by_count":12,"area":null},{"id":"2504.04579","title":"From Continual Learning to SGD and Back: Better Rates for Continual Linear Models","created":"2025-04-06","cited_by_count":12,"area":null},{"id":"2507.11274","title":"Fast Last-Iterate Convergence of SGD in the Smooth Interpolation Regime","created":"2025-07-15","cited_by_count":12,"area":null},{"id":"2112.02668","title":"On the Convergence of Shallow Neural Network Training with Randomly Masked Neurons","created":"2021-12-05","cited_by_count":11,"area":null},{"id":"2206.11124","title":"A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta","created":"2022-06-22","cited_by_count":11,"area":null},{"id":"2306.11497","title":"Convergence and concentration properties of constant step-size SGD through Markov chains","created":"2023-06-20","cited_by_count":11,"area":null},{"id":"2101.09849","title":"Deep Learning Generalization and the Convex Hull of Training Sets","created":"2021-01-25","cited_by_count":10,"area":null},{"id":"2102.07002","title":"On the Last Iterate Convergence of Momentum Methods","created":"2021-02-13","cited_by_count":10,"area":null},{"id":"2106.02720","title":"An Even More Optimal Stochastic Optimization Algorithm: Minibatching and Interpolation Learning","created":"2021-06-04","cited_by_count":10,"area":null},{"id":"2307.14642","title":"Linear Convergence of Black-Box Variational Inference: Should We Stick the Landing?","created":"2023-07-27","cited_by_count":10,"area":null},{"id":"2407.04358","title":"An Adaptive Stochastic Gradient Method with Non-negative Gauss-Newton Stepsizes","created":"2024-07-05","cited_by_count":10,"area":null},{"id":"2203.01744","title":"Accelerated SGD for Non-Strongly-Convex Least Squares","created":"2022-03-03","cited_by_count":9,"area":null},{"id":"2206.03927","title":"Boundary between noise and information applied to filtering neural network weight matrices","created":"2022-06-08","cited_by_count":9,"area":null},{"id":"2208.07951","title":"On the generalization of learning algorithms that do not converge","created":"2022-08-16","cited_by_count":9,"area":null},{"id":"2305.18285","title":"Partially Personalized Federated Learning: Breaking the Curse of Data Heterogeneity","created":"2023-05-29","cited_by_count":9,"area":null},{"id":"2307.14531","title":"Controlling the Inductive Bias of Wide Neural Networks by Modifying the Kernel's Spectrum","created":"2023-07-26","cited_by_count":9,"area":null},{"id":"2411.00247","title":"Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond","created":"2024-10-31","cited_by_count":9,"area":null},{"id":"2203.03159","title":"Risk Bounds of Multi-Pass SGD for Least Squares in the Interpolation Regime","created":"2022-03-07","cited_by_count":8,"area":null},{"id":"2308.14929","title":"Maestro: Uncovering Low-Rank Structures via Trainable Decomposition","created":"2023-08-28","cited_by_count":8,"area":null},{"id":"2103.12293","title":"Stochastic Reweighted Gradient Descent","created":"2021-03-23","cited_by_count":7,"area":null},{"id":"2112.12175","title":"Recur, Attend or Convolve? On Whether Temporal Modeling Matters for Cross-Domain Robustness in Action Recognition","created":"2021-12-22","cited_by_count":7,"area":null},{"id":"2210.11693","title":"Amos: An Adam-style Optimizer with Adaptive Weight Decay towards Model-Oriented Scale","created":"2022-10-21","cited_by_count":7,"area":null},{"id":"2403.02418","title":"The Role of the Time-Dependent Hessian in High-Dimensional Optimization","created":"2024-03-04","cited_by_count":7,"area":null},{"id":"2403.15654","title":"The Effectiveness of Local Updates for Decentralized Learning under Data Heterogeneity","created":"2024-03-23","cited_by_count":7,"area":null},{"id":"2208.00088","title":"Improved Policy Optimization for Online Imitation Learning","created":"2022-07-29","cited_by_count":6,"area":"offlinerl"},{"id":"2303.10472","title":"Practical and Matching Gradient Variance Bounds for Black-Box Variational Bayesian Inference","created":"2023-03-18","cited_by_count":6,"area":null},{"id":"2503.07501","title":"Trustworthy Machine Learning via Memorization and the Granular Long-Tail: A Survey on Interactions, Tradeoffs, and Beyond","created":"2025-03-10","cited_by_count":6,"area":null},{"id":"2602.14208","title":"Fast Catch-Up, Late Switching: Optimal Batch Size Scheduling via Functional Scaling Laws","created":"2026-02-15","cited_by_count":6,"area":null},{"id":"2305.11957","title":"Towards understanding neural collapse in supervised contrastive learning with the information bottleneck method","created":"2023-05-19","cited_by_count":5,"area":null},{"id":"2305.15912","title":"Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks","created":"2023-05-25","cited_by_count":5,"area":null},{"id":"2402.18824","title":"Batch size invariant Adam","created":"2024-02-29","cited_by_count":5,"area":null},{"id":"2405.15545","title":"Freya PAGE: First Optimal Time Complexity for Large-Scale Nonconvex Finite-Sum Optimization with Heterogeneous Asynchronous Computations","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2502.09003","title":"RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models","created":"2025-02-13","cited_by_count":5,"area":null},{"id":"2504.01898","title":"Analysis of an Idealized Stochastic Polyak Method and its Application to Black-Box Model Distillation","created":"2025-04-02","cited_by_count":5,"area":null},{"id":"2602.05813","title":"Where Does Warm-Up Come From? Adaptive Scheduling for Norm-Constrained Optimizers","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2112.03411","title":"Extrapolation Frameworks in Cognitive Psychology Suitable for Study of Image Classification Models","created":"2021-12-06","cited_by_count":4,"area":null},{"id":"2201.12719","title":"Faster Convergence of Local SGD for Over-Parameterized Models","created":"2022-01-30","cited_by_count":4,"area":null},{"id":"2302.02607","title":"Target-based Surrogates for Stochastic Optimization","created":"2023-02-06","cited_by_count":4,"area":"offlinerl"},{"id":"2406.02105","title":"Can Kernel Methods Explain How the Data Affects Neural Collapse?","created":"2024-06-04","cited_by_count":4,"area":null},{"id":"2406.13936","title":"Communication-Efficient Adaptive Batch Size Strategies for Distributed Local Gradient Methods","created":"2024-06-20","cited_by_count":4,"area":null},{"id":"2505.23489","title":"SGD as Free Energy Minimization: A Thermodynamic View on Neural Network Training","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2201.12678","title":"A Stochastic Bundle Method for Interpolating Networks","created":"2022-01-29","cited_by_count":3,"area":null},{"id":"2210.17070","title":"Private optimization in the interpolation regime: faster rates and hardness results","created":"2022-10-31","cited_by_count":3,"area":null},{"id":"2308.08070","title":"Max-affine regression via first-order methods","created":"2023-08-15","cited_by_count":3,"area":null},{"id":"2309.17316","title":"Robust Stochastic Optimization via Gradient Quantile Clipping","created":"2023-09-29","cited_by_count":3,"area":null},{"id":"2311.17539","title":"Critical Influence of Overparameterization on Sharpness-aware Minimization","created":"2023-11-29","cited_by_count":3,"area":null},{"id":"2402.17890","title":"From Inverse Optimization to Feasibility to ERM","created":"2024-02-27","cited_by_count":3,"area":null},{"id":"2503.00229","title":"Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster","created":"2025-02-28","cited_by_count":3,"area":null},{"id":"2509.02970","title":"Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation","created":"2025-09-03","cited_by_count":3,"area":null},{"id":"2202.10788","title":"Explicit Regularization via Regularizer Mirror Descent","created":"2022-02-22","cited_by_count":2,"area":null},{"id":"2204.04476","title":"High-dimensional Asymptotics of Langevin Dynamics in Spiked Matrix Models","created":"2022-04-09","cited_by_count":2,"area":null},{"id":"2206.05869","title":"On the Convergence to a Global Solution of Shuffling-Type Gradient Algorithms","created":"2022-06-13","cited_by_count":2,"area":null},{"id":"2303.08986","title":"Deep Learning Weight Pruning with RMT-SVD: Increasing Accuracy and Reducing Overfitting","created":"2023-03-15","cited_by_count":2,"area":null},{"id":"2305.08658","title":"On the connections between optimization algorithms, Lyapunov functions, and differential equations: theory and insights","created":"2023-05-15","cited_by_count":2,"area":null},{"id":"2406.00920","title":"Demystifying SGD with Doubly Stochastic Gradients","created":"2024-06-03","cited_by_count":2,"area":"diffusion"},{"id":"2406.01435","title":"Learning Analysis of Kernel Ridgeless Regression with Asymmetric Kernel Learning","created":"2024-06-03","cited_by_count":2,"area":null},{"id":"2408.03199","title":"Convergence Conditions for Stochastic Line Search Based Optimization of Over-parametrized Models","created":"2024-08-06","cited_by_count":2,"area":null}],"next_cursor":"100"}