Stabilized SVRG: Simple Variance Reduction for Nonconvex Optimization

1. 2021ZeroSARAH: Efficient Nonconvex Finite-Sum Optimization with Zero Full Gradient Computationcited by 28
2. 2021FedPAGE: A Fast Local Stochastic Gradient Method for Communication-Efficient Federated Learningcited by 19
3. 2021Escape saddle points by a simple gradient-descent based algorithmcited by 11
4. 2021ANITA: An Optimal Loopless Accelerated Variance-Reduced Gradient Methodcited by 9
5. 2023Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Timecited by 8
6. 2025Unbiased Gradient Low-Rank Projectioncited by 6
7. 2022Simple and Optimal Stochastic Gradient Methods for Nonsmooth Nonconvex Optimizationcited by 5
8. 2023Escaping Saddle Points in Heterogeneous Federated Learning via Distributed SGD with Communication Compressioncited by 4
9. 2025Second-Order Convergence in Private Stochastic Non-Convex Optimizationcited by 3
10. 2022Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learningcited by 2
11. 2021Distributed Policy Gradient with Variance Reduction in Multi-Agent Reinforcement Learningcited by 1
12. 2023Greedy Pruning with Group Lasso Provably Generalizes for Matrix Sensingcited by 1

1. 2026AdaCubic: An Adaptive Cubic Regularization Optimizer for Deep Learning10 Apr 2026
2. 2025Unbiased Gradient Low-Rank Projection20 Oct 2025
3. 2025Second-Order Convergence in Private Stochastic Non-Convex Optimization21 May 2025
4. 2023Escaping Saddle Points in Heterogeneous Federated Learning via Distributed SGD with Communication Compression29 Oct 2023
5. 2023Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time24 May 2023
6. 2023Greedy Pruning with Group Lasso Provably Generalizes for Matrix Sensing20 Mar 2023
7. 2022Versatile Single-Loop Method for Gradient Estimator: First and Second Order Optimality, and its Application to Federated Learning1 Sep 2022
8. 2022Simple and Optimal Stochastic Gradient Methods for Nonsmooth Nonconvex Optimization22 Aug 2022
9. 2022SPIRAL: A superlinearly convergent incremental proximal algorithm for nonconvex finite sum minimization17 Jul 2022
10. 2022Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning12 Feb 2022
11. 2021Escape saddle points by a simple gradient-descent based algorithm28 Nov 2021
12. 2021Distributed Policy Gradient with Variance Reduction in Multi-Agent Reinforcement Learning25 Nov 2021

1. 2021ZeroSARAH: Efficient Nonconvex Finite-Sum Optimization with Zero Full Gradient Computationcited by 28
2. 2021FedPAGE: A Fast Local Stochastic Gradient Method for Communication-Efficient Federated Learningcited by 19
3. 2021Escape saddle points by a simple gradient-descent based algorithmcited by 11
4. 2021ANITA: An Optimal Loopless Accelerated Variance-Reduced Gradient Methodcited by 9
5. 2023Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Timecited by 8
6. 2025Unbiased Gradient Low-Rank Projectioncited by 6
7. 2022Simple and Optimal Stochastic Gradient Methods for Nonsmooth Nonconvex Optimizationcited by 5
8. 2023Escaping Saddle Points in Heterogeneous Federated Learning via Distributed SGD with Communication Compressioncited by 4
9. 2025Second-Order Convergence in Private Stochastic Non-Convex Optimizationcited by 3
10. 2022Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learningcited by 2
11. 2021Distributed Policy Gradient with Variance Reduction in Multi-Agent Reinforcement Learningcited by 1
12. 2023Greedy Pruning with Group Lasso Provably Generalizes for Matrix Sensingcited by 1

12 most cited of 15 · All 15 (JSON)

1. 2026AdaCubic: An Adaptive Cubic Regularization Optimizer for Deep Learning10 Apr 2026
2. 2025Unbiased Gradient Low-Rank Projection20 Oct 2025
3. 2025Second-Order Convergence in Private Stochastic Non-Convex Optimization21 May 2025
4. 2023Escaping Saddle Points in Heterogeneous Federated Learning via Distributed SGD with Communication Compression29 Oct 2023
5. 2023Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time24 May 2023
6. 2023Greedy Pruning with Group Lasso Provably Generalizes for Matrix Sensing20 Mar 2023
7. 2022Versatile Single-Loop Method for Gradient Estimator: First and Second Order Optimality, and its Application to Federated Learning1 Sep 2022
8. 2022Simple and Optimal Stochastic Gradient Methods for Nonsmooth Nonconvex Optimization22 Aug 2022
9. 2022SPIRAL: A superlinearly convergent incremental proximal algorithm for nonconvex finite sum minimization17 Jul 2022
10. 2022Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning12 Feb 2022
11. 2021Escape saddle points by a simple gradient-descent based algorithm28 Nov 2021
12. 2021Distributed Policy Gradient with Variance Reduction in Multi-Agent Reinforcement Learning25 Nov 2021

12 newest of 15 · All 15 (JSON)