{"total":133,"rows":[{"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":"2111.10603","title":"Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning","created":"2021-11-20","cited_by_count":101,"area":null},{"id":"2205.09588","title":"How catastrophic can catastrophic forgetting be in linear regression?","created":"2022-05-19","cited_by_count":81,"area":null},{"id":"2206.04030","title":"High-dimensional limit theorems for SGD: Effective dynamics and critical scaling","created":"2022-06-08","cited_by_count":70,"area":null},{"id":"2112.11256","title":"Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Sampling","created":"2021-12-21","cited_by_count":66,"area":null},{"id":"2105.13462","title":"On Linear Stability of SGD and Input-Smoothness of Neural Networks","created":"2021-05-27","cited_by_count":63,"area":null},{"id":"2105.01650","title":"Stochastic gradient descent with noise of machine learning type. Part I: Discrete time analysis","created":"2021-05-04","cited_by_count":39,"area":null},{"id":"2102.06704","title":"Proximal and Federated Random Reshuffling","created":"2021-02-12","cited_by_count":33,"area":null},{"id":"2306.03638","title":"Provable convergence guarantees for black-box variational inference","created":"2023-06-04","cited_by_count":29,"area":null},{"id":"2102.07158","title":"Distributed Second Order Methods with Fast Rates and Compressed Communication","created":"2021-02-14","cited_by_count":25,"area":null},{"id":"2410.05578","title":"Swift Sampler: Efficient Learning of Sampler by 10 Parameters","created":"2024-10-08","cited_by_count":25,"area":null},{"id":"2206.07252","title":"Implicit Regularization or Implicit Conditioning? Exact Risk Trajectories of SGD in High Dimensions","created":"2022-06-15","cited_by_count":23,"area":null},{"id":"2103.08933","title":"Reweighting Augmented Samples by Minimizing the Maximal Expected Loss","created":"2021-03-16","cited_by_count":21,"area":null},{"id":"2205.10733","title":"GraB: Finding Provably Better Data Permutations than Random Reshuffling","created":"2022-05-22","cited_by_count":19,"area":null},{"id":"2206.00737","title":"Walk for Learning: A Random Walk Approach for Federated Learning from Heterogeneous Data","created":"2022-06-01","cited_by_count":19,"area":null},{"id":"2209.02257","title":"Faster federated optimization under second-order similarity","created":"2022-09-06","cited_by_count":18,"area":null},{"id":"2504.09951","title":"Towards Weaker Variance Assumptions for Stochastic Optimization","created":"2025-04-14","cited_by_count":17,"area":null},{"id":"2102.09700","title":"AI-SARAH: Adaptive and Implicit Stochastic Recursive Gradient Methods","created":"2021-02-19","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":"2110.01528","title":"Large Batch Experience Replay","created":"2021-10-04","cited_by_count":14,"area":null},{"id":"2110.15590","title":"Adaptive Importance Sampling meets Mirror Descent: a Bias-variance tradeoff","created":"2021-10-29","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":"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":"2307.07652","title":"DIGEST: Fast and Communication Efficient Decentralized Learning with Local Updates","created":"2023-07-14","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":"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":"2406.11151","title":"Recent and Upcoming Developments in Randomized Numerical Linear Algebra for Machine Learning","created":"2024-06-17","cited_by_count":11,"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":"2103.12243","title":"Adaptive Importance Sampling for Finite-Sum Optimization and Sampling with Decreasing Step-Sizes","created":"2021-03-23","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":"2302.11147","title":"Stochastic Approximation Beyond Gradient for Signal Processing and Machine Learning","created":"2023-02-22","cited_by_count":10,"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":"2210.03510","title":"Learning to Learn and Sample BRDFs","created":"2022-10-07","cited_by_count":9,"area":null},{"id":"2404.13804","title":"Adaptive Heterogeneous Client Sampling for Federated Learning over Wireless Networks","created":"2024-04-22","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":"2307.06915","title":"Weighted Averaged Stochastic Gradient Descent: Asymptotic Normality and Optimality","created":"2023-07-13","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":"2106.12261","title":"Learning Under Delayed Feedback: Implicitly Adapting to Gradient Delays","created":"2021-06-23","cited_by_count":7,"area":null},{"id":"2112.14332","title":"Adaptive Client Sampling in Federated Learning via Online Learning with Bandit Feedback","created":"2021-12-28","cited_by_count":7,"area":null},{"id":"2208.05287","title":"Adaptive Learning Rates for Faster Stochastic Gradient Methods","created":"2022-08-10","cited_by_count":7,"area":null},{"id":"2212.07282","title":"Low-Variance Forward Gradients using Direct Feedback Alignment and Momentum","created":"2022-12-14","cited_by_count":7,"area":null},{"id":"2302.00845","title":"Coordinating Distributed Example Orders for Provably Accelerated Training","created":"2023-02-02","cited_by_count":7,"area":null},{"id":"2303.01135","title":"Tight Risk Bounds for Gradient Descent on Separable Data","created":"2023-03-02","cited_by_count":7,"area":null},{"id":"2405.05818","title":"Fine-grained Analysis and Faster Algorithms for Iteratively Solving Linear Systems","created":"2024-05-09","cited_by_count":7,"area":null},{"id":"2501.11673","title":"Randomized Kaczmarz Methods with Beyond-Krylov Convergence","created":"2025-01-20","cited_by_count":7,"area":null},{"id":"2510.17802","title":"Unbiased Gradient Low-Rank Projection","created":"2025-10-20","cited_by_count":7,"area":null},{"id":"2302.14772","title":"PA&DA: Jointly Sampling PAth and DAta for Consistent NAS","created":"2023-02-28","cited_by_count":6,"area":null},{"id":"2110.14283","title":"How Important is Importance Sampling for Deep Budgeted Training?","created":"2021-10-27","cited_by_count":5,"area":null},{"id":"2601.23135","title":"Why GRPO Needs Normalization: A Local-Curvature Perspective on Adaptive Gradients","created":"2026-01-30","cited_by_count":5,"area":"lr"},{"id":"2105.11818","title":"SGD with Coordinate Sampling: Theory and Practice","created":"2021-05-25","cited_by_count":4,"area":null},{"id":"2405.15941","title":"A Unified Theory of Stochastic Proximal Point Methods without Smoothness","created":"2024-05-24","cited_by_count":4,"area":null},{"id":"2407.20611","title":"The Entrapment Problem in Random Walk Decentralized Learning","created":"2024-07-30","cited_by_count":4,"area":null},{"id":"2409.10959","title":"Leveraging Reviewer Experience in Code Review Comment Generation","created":"2024-09-17","cited_by_count":4,"area":null},{"id":"2103.05857","title":"Fast block-coordinate Frank-Wolfe algorithm for semi-relaxed optimal transport","created":"2021-03-10","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":"2103.13909","title":"Regularization by Denoising Sub-sampled Newton Method for Spectral CT Multi-Material Decomposition","created":"2021-03-25","cited_by_count":3,"area":null},{"id":"2210.01891","title":"Adaptively Weighted Data Augmentation Consistency Regularization for Robust Optimization under Concept Shift","created":"2022-10-04","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":"2303.10599","title":"Convergence Analysis of Stochastic Gradient Descent with MCMC Estimators","created":"2023-03-19","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":"2401.09415","title":"Randomized Kaczmarz with geometrically smoothed momentum","created":"2024-01-17","cited_by_count":3,"area":null},{"id":"2402.17227","title":"Efficient Backpropagation with Variance-Controlled Adaptive Sampling","created":"2024-02-27","cited_by_count":3,"area":null},{"id":"2408.03193","title":"Efficient NeRF Optimization -- Not All Samples Remain Equally Hard","created":"2024-08-06","cited_by_count":3,"area":null},{"id":"2207.07822","title":"Adaptive Sketches for Robust Regression with Importance Sampling","created":"2022-07-16","cited_by_count":2,"area":null},{"id":"2211.15310","title":"Stochastic Steffensen method","created":"2022-11-28","cited_by_count":2,"area":null},{"id":"2310.02698","title":"Enhanced Federated Optimization: Adaptive Unbiased Client Sampling with Reduced Variance","created":"2023-10-04","cited_by_count":2,"area":null},{"id":"2310.12969","title":"Demystifying the Myths and Legends of Nonconvex Convergence of SGD","created":"2023-10-19","cited_by_count":2,"area":null},{"id":"2311.08745","title":"Using Stochastic Gradient Descent to Smooth Nonconvex Functions: Analysis of Implicit Graduated Optimization","created":"2023-11-15","cited_by_count":2,"area":null},{"id":"2402.07052","title":"Understanding the Training Speedup from Sampling with Approximate Losses","created":"2024-02-10","cited_by_count":2,"area":null},{"id":"2403.00853","title":"Parallel Momentum Methods Under Biased Gradient Estimations","created":"2024-02-29","cited_by_count":2,"area":null},{"id":"2403.02347","title":"On the Convergence of Federated Learning Algorithms without Data Similarity","created":"2024-02-29","cited_by_count":2,"area":null},{"id":"2502.00882","title":"Worth Their Weight: Randomized and Regularized Block Kaczmarz Algorithms without Preprocessing","created":"2025-02-02","cited_by_count":2,"area":null},{"id":"2505.17965","title":"Bias-Optimal Bounds for SGD: A Computer-Aided Lyapunov Analysis","created":"2025-05-23","cited_by_count":2,"area":null},{"id":"2506.12648","title":"Glocal Smoothness: Line search and adaptive step sizes can help in theory too!","created":"2025-06-14","cited_by_count":2,"area":null},{"id":"2510.21598","title":"Fisher meets Feynman: score-based variational inference with a product of experts","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2511.07604","title":"Infinite-Dimensional Operator/Block Kaczmarz Algorithms: Regret Bounds and $\\lambda$-Effectiveness","created":"2025-11-10","cited_by_count":2,"area":null},{"id":"2604.09909","title":"Last-Iterate Convergence of Randomized Kaczmarz and SGD with Greedy Step Size","created":"2026-04-10","cited_by_count":2,"area":null},{"id":"2201.13387","title":"L-SVRG and L-Katyusha with Adaptive Sampling","created":"2022-01-31","cited_by_count":1,"area":null},{"id":"2202.12224","title":"An optimal scheduled learning rate for a randomized Kaczmarz algorithm","created":"2022-02-24","cited_by_count":1,"area":null},{"id":"2206.00632","title":"Computing the Variance of Shuffling Stochastic Gradient Algorithms via Power Spectral Density Analysis","created":"2022-06-01","cited_by_count":1,"area":null},{"id":"2208.13080","title":"Information FOMO: The unhealthy fear of missing out on information. A method for removing misleading data for healthier models","created":"2022-08-27","cited_by_count":1,"area":null},{"id":"2211.05749","title":"Linear Discriminant Analysis with the Randomized Kaczmarz Method","created":"2022-11-10","cited_by_count":1,"area":null},{"id":"2303.16529","title":"Importance Sampling for Stochastic Gradient Descent in Deep Neural Networks","created":"2023-03-29","cited_by_count":1,"area":null},{"id":"2304.00459","title":"Fast Convergence of Random Reshuffling under Over-Parameterization and the Polyak-\\L ojasiewicz Condition","created":"2023-04-02","cited_by_count":1,"area":null},{"id":"2310.10102","title":"KAKURENBO: Adaptively Hiding Samples in Deep Neural Network Training","created":"2023-10-16","cited_by_count":1,"area":null},{"id":"2310.15411","title":"Efficient Active Learning Halfspaces with Tsybakov Noise: A Non-convex Optimization Approach","created":"2023-10-23","cited_by_count":1,"area":null},{"id":"2311.14468","title":"Online Importance Sampling for Stochastic Gradient Optimization","created":"2023-11-24","cited_by_count":1,"area":null},{"id":"2406.05637","title":"A Generalized Version of Chung's Lemma and its Applications","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2406.18623","title":"Unbiased least squares regression via averaged stochastic gradient descent","created":"2024-06-26","cited_by_count":1,"area":null},{"id":"2407.15525","title":"Multiple Importance Sampling for Stochastic Gradient Estimation","created":"2024-07-22","cited_by_count":1,"area":null},{"id":"2504.00564","title":"Geometric Median Matching for Robust k-Subset Selection from Noisy Data","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2507.21670","title":"Probabilistic Consistency in Machine Learning and Its Connection to Uncertainty Quantification","created":"2025-07-29","cited_by_count":1,"area":null},{"id":"2511.02258","title":"Limit Theorems for Stochastic Gradient Descent in High-Dimensional Single-Layer Networks","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2601.18080","title":"Use of operator defect identities in multi-channel signal plus residual-analysis via iterated products and telescoping energy-residuals: Applications to kernels in machine learning","created":"2026-01-26","cited_by_count":1,"area":null},{"id":"2604.10373","title":"Shuffling the Data, Stretching the Step-size: Sharper Bias in constant step-size SGD","created":"2026-04-11","cited_by_count":1,"area":null},{"id":"2604.28020","title":"Cost-Aware Learning","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2101.10037","title":"Optimizing Convergence for Iterative Learning of ARIMA for Stationary Time Series","created":"2021-01-25","cited_by_count":0,"area":null},{"id":"2102.13653","title":"On the Generalization of Stochastic Gradient Descent with Momentum","created":"2021-02-26","cited_by_count":0,"area":null}],"next_cursor":"100"}