Shifted compression framework: generalizations and improvements. | 0 | 0.34 | 2022 |
Proximal and Federated Random Reshuffling. | 0 | 0.34 | 2022 |
ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally! | 0 | 0.34 | 2022 |
Basis Matters: Better Communication-Efficient Second Order Methods for Federated Learning | 0 | 0.34 | 2022 |
FLIX: A Simple and Communication-Efficient Alternative to Local Methods in Federated Learning | 0 | 0.34 | 2022 |
3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation. | 0 | 0.34 | 2022 |
An Optimal Algorithm for Strongly Convex Minimization under Affine Constraints | 0 | 0.34 | 2022 |
Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization. | 0 | 0.34 | 2022 |
Permutation Compressors for Provably Faster Distributed Nonconvex Optimization | 0 | 0.34 | 2022 |
Dualize, Split, Randomize: Toward Fast Nonsmooth Optimization Algorithms | 0 | 0.34 | 2022 |
IntSGD: Adaptive Floatless Compression of Stochastic Gradients | 0 | 0.34 | 2022 |
FedNL: Making Newton-Type Methods Applicable to Federated Learning. | 0 | 0.34 | 2022 |
Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information | 0 | 0.34 | 2022 |
Error Compensated Distributed SGD Can Be Accelerated. | 0 | 0.34 | 2021 |
Marina: Faster Non-Convex Distributed Learning With Compression | 0 | 0.34 | 2021 |
Adom: Accelerated Decentralized Optimization Method For Time-Varying Networks | 0 | 0.34 | 2021 |
Revisiting Randomized Gossip Algorithms: General Framework, Convergence Rates and Novel Block and Accelerated Protocols | 1 | 0.35 | 2021 |
A Better Alternative to Error Feedback for Communication-Efficient Distributed Learning | 0 | 0.34 | 2021 |
Local Sgd: Unified Theory And New Efficient Methods | 0 | 0.34 | 2021 |
L-Svrg And L-Katyusha With Arbitrary Sampling | 0 | 0.34 | 2021 |
Stochastic Sign Descent Methods: New Algorithms and Better Theory | 0 | 0.34 | 2021 |
A Linearly Convergent Algorithm For Decentralized Optimization: Sending Less Bits For Free! | 0 | 0.34 | 2021 |
A Stochastic Derivative-Free Optimization Method With Importance Sampling: Theory And Learning To Control | 0 | 0.34 | 2020 |
Stochastic Subspace Cubic Newton Method | 0 | 0.34 | 2020 |
Variance-Reduced Methods for Machine Learning | 3 | 0.36 | 2020 |
99% of Worker-Master Communication in Distributed Optimization Is Not Needed. | 0 | 0.34 | 2020 |
Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems | 0 | 0.34 | 2020 |
Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization | 0 | 0.34 | 2020 |
From Local SGD to Local Fixed-Point Methods for Federated Learning. | 0 | 0.34 | 2020 |
Primal Dual Interpretation of the Proximal Stochastic Gradient Langevin Algorithm | 0 | 0.34 | 2020 |
Random Reshuffling: Simple Analysis with Vast Improvements | 0 | 0.34 | 2020 |
Optimal and Practical Algorithms for Smooth and Strongly Convex Decentralized Optimization | 0 | 0.34 | 2020 |
Lower Bounds and Optimal Algorithms for Personalized Federated Learning | 0 | 0.34 | 2020 |
Convergence Analysis Of Inexact Randomized Iterative Methods | 1 | 0.35 | 2020 |
Don't Jump Through Hoops and Remove Those Loops - SVRG and Katyusha are Better Without the Outer Loop. | 1 | 0.34 | 2020 |
Best Pair Formulation & Accelerated Scheme for Non-convex Principal Component Pursuit. | 0 | 0.34 | 2019 |
Convergence Analysis of Inexact Randomized Iterative Methods. | 0 | 0.34 | 2019 |
Revisiting Stochastic Extragradient. | 0 | 0.34 | 2019 |
Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates. | 0 | 0.34 | 2019 |
Revisiting Randomized Gossip Algorithms: General Framework, Convergence Rates and Novel Block and Accelerated Protocols. | 0 | 0.34 | 2019 |
Online and Batch Supervised Background Estimation via L1 Regression. | 1 | 0.35 | 2019 |
One Method to Rule Them All: Variance Reduction for Data, Parameters and Many New Methods. | 0 | 0.34 | 2019 |
99% of Parallel Optimization is Inevitably a Waste of Time. | 0 | 0.34 | 2019 |
Randomized Projection Methods for Convex Feasibility: Conditioning and Convergence Rates | 1 | 0.35 | 2019 |
SAGA with Arbitrary Sampling. | 0 | 0.34 | 2019 |
Nonconvex Variance Reduced Optimization with Arbitrary Sampling | 2 | 0.36 | 2019 |
Scaling Distributed Machine Learning with In-Network Aggregation. | 3 | 0.38 | 2019 |
Distributed Learning with Compressed Gradient Differences. | 2 | 0.36 | 2019 |
Stochastic Convolutional Sparse Coding | 0 | 0.34 | 2019 |
A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and Coordinate Descent. | 0 | 0.34 | 2019 |