No article text was recorded for this version.
sampling without replacement
Version 2 of 2105 papers116 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Incremental Without Replacement Sampling in Nonconvex Optimization
- Blog: Finito: A faster, permutable incremental gradient method for big data problems
- Blog: Without-Replacement Sampling for Stochastic Gradient Methods
- Blog: Provable Benefit of Random Permutations over Uniform Sampling in Stochastic Coordinate Descent
- Blog: Random Shuffling Beats SGD Only After Many Epochs on Ill-Conditioned Problems
- Blog: Finito: A Faster, Permutable Incremental Gradient Method for Big Data Problems
- Blog: Shuffling Heuristic in Variational Inequalities: Establishing New Convergence Guarantees
- Blog: Without-Replacement Sampling for Stochastic Gradient Methods: Convergence Results and Application to Distributed Optimization
- Blog: Benign Underfitting of Stochastic Gradient Descent
- Blog: A Unified Convergence Analysis for Shuffling-Type Gradient Methods
- Blog: Breaking Locality Accelerates Block Gauss-Seidel
- Blog: Random Shuffling Beats SGD Only After Many Epochs on Ill-Conditioned Problems
- Blog: Bolstering stochastic gradient descent with model building
- Blog: Revisiting Convergence: Shuffling Complexity Beyond Lipschitz Smoothness
- Blog: Stochastic Variance-Reduced Cubic Regularization for Nonconvex Optimization
- Blog: Implicit bias of SGD in L2-regularized linear DNNs: One-way jumps from high to low rank
- Blog: On Convergence of Incremental Gradient for Non-convex Smooth Functions
- Blog: Random Reshuffling is Not Always Better
- Blog: An Improved Analysis and Rates for Variance Reduction under Without-replacement Sampling Orders
- Blog: SVRG meets SAGA: k-SVRG - A Tale of Limited Memory
- Blog: Sampling Techniques for the Nystrom Method
- Blog: Sampling without Replacement Leads to Faster Rates in Finite-Sum Minimax Optimization
- Blog: Convergence of Variance-Reduced Stochastic Learning under Random Reshuffling
- Blog: Randomness and permutations in coordinate descent methods
- Blog: Near-Optimal Entrywise Sampling for Data Matrices
- Blog: Random Reshuffling: Simple Analysis with Vast Improvements
- Blog: Random Reshuffling with Variance Reduction: New Analysis and Better Rates
- Blog: High Probability Guarantees for Random Reshuffling
- Blog: Statistical Optimality of Stochastic Gradient Descent on Hard Learning Problems through Multiple Passes
- Blog: Subsampling Error in Stochastic Gradient Langevin Diffusions
- Blog: Sampling without Replacement Leads to Faster Rates in Finite-Sum Minimax Optimization
- Blog: Descend or Rewind? Stochastic Gradient Descent Unlearning
- Blog: Minimax Rates and Efficient Algorithms for Noisy Sorting
- Blog: Provable Adaptivity in Adam
- Blog: Empirical Risk Minimization with Shuffled SGD: A Primal-Dual Perspective and Improved Bounds
- Blog: Why random reshuffling beats stochastic gradient descent
- Blog: Optimal Importance Sampling for Federated Learning
- Blog: When is the Convergence Time of Langevin Algorithms Dimension Independent? A Composite Optimization Viewpoint
- Blog: How Good is SGD with Random Shuffling?
- Blog: Monte Carlo *-Minimax Search
- Blog: Toward a Noncommutative Arithmetic-geometric Mean Inequality: Conjectures, Case-studies, and Consequences
- Blog: Manipulating SGD with Data Ordering Attacks
- Blog: Online Matching Meets Sampling Without Replacement
- Blog: Recht-Re Noncommutative Arithmetic-Geometric Mean Conjecture is False
- Blog: On the Origin of Implicit Regularization in Stochastic Gradient Descent
- Blog: Implicit bias of SGD in $L_2$-regularized linear DNNs: One-way jumps from high to low rank
- Blog: Understanding the Impact of Model Incoherence on Convergence of Incremental SGD with Random Reshuffle
- Blog: SGD without Replacement: Sharper Rates for General Smooth Convex Functions
- Blog: Zeroth-Order Methods for Convex-Concave Minmax Problems: Applications to Decision-Dependent Risk Minimization
- Blog: Stochastic Learning Under Random Reshuffling With Constant Step-Sizes
- Blog: Stochastic Extragradient with Random Reshuffling: Improved Convergence for Variational Inequalities
- Blog: Convergence of Sign-based Random Reshuffling Algorithms for Nonconvex Optimization
- Blog: Fast Convergence of Random Reshuffling under Over-Parameterization and the Polyak-Łojasiewicz Condition
- Blog: Distributed Random Reshuffling Methods with Improved Convergence
- Blog: Convergence Analysis of Distributed Stochastic Gradient Descent with Shuffling
- Blog: Stochastic Extragradient with Random Reshuffling: Improved Convergence for Variational Inequalities
- Blog: Coordinate Descent Algorithms
- Blog: Stochastic Learning under Random Reshuffling
- Blog: Random Shuffling Beats SGD after Finite Epochs
- Blog: Proximal and Federated Random Reshuffling
Showing 60 of 105 papers.
History & citation
Current · Permanent link
- shuffling-induced gradient bias split from this direction (69% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_sampling_without_replacement_03c68318,
title = {sampling without replacement},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/sampling-without-replacement/rdr_03c68318c71645909bcfa3c81d52f7e0},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 2, frozen text):
@misc{lacuna_sampling_without_replacement_03c68318_v2,
title = {sampling without replacement},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/sampling-without-replacement/rdr_03c68318c71645909bcfa3c81d52f7e0/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-21},
}