SOTAVerified

Distributed Optimization

The goal of Distributed Optimization is to optimize a certain objective defined over millions of billions of data that is distributed over many machines by utilizing the computational power of these machines.

Source: Analysis of Distributed StochasticDual Coordinate Ascent

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 426–450 of 536 papers

TitleStatusHype
TernaryVote: Differentially Private, Communication Efficient, and Byzantine Resilient Distributed Optimization on Heterogeneous Data—0
The Communication Complexity of Optimization—0
The Geometry of Sign Gradient Descent—0
The Limits and Potentials of Local SGD for Distributed Heterogeneous Learning with Intermittent Communication—0
The Minimax Complexity of Distributed Optimization—0
Tie-Line Characteristics based Partitioning for Distributed Optimization of Power Systems—0
Tighter Performance Theory of FedExProx—0
Toward Communication Efficient Adaptive Gradient Method—0
Towards privacy-preserving cooperative control via encrypted distributed optimization—0
Towards Scalable Multi-View Reconstruction of Geometry and Materials—0
Fairness-Oriented User Scheduling for Bursty Downlink Transmission Using Multi-Agent Reinforcement Learning—0
Trading Computation for Communication: Distributed Stochastic Dual Coordinate Ascent—0
Training Deep Neural Networks via Optimization Over Graphs—0
Trajectory Normalized Gradients for Distributed Optimization—0
Unbiased and Sign Compression in Distributed Learning: Comparing Noise Resilience via SDEs—0
Unbiased Compression Saves Communication in Distributed Optimization: When and How Much?—0
Uncertain Multi-Agent Systems with Distributed Constrained Optimization Missions and Event-Triggered Communications: Application to Resource Allocation—0
Understanding A Class of Decentralized and Federated Optimization Algorithms: A Multi-Rate Feedback Control Perspective—0
Utilizing Redundancy in Cost Functions for Resilience in Distributed Optimization and Learning—0
Variance Reduction in Deep Learning: More Momentum is All You Need—0
vqSGD: Vector Quantized Stochastic Gradient Descent—0
When Evolutionary Computation Meets Privacy—0
Widely-distributed Radar Imaging Based on Consensus ADMM—0
Without-Replacement Sampling for Stochastic Gradient Methods: Convergence Results and Application to Distributed Optimization—0
Without-Replacement Sampling for Stochastic Gradient Methods—0
Show:102550
← PrevPage 18 of 22Next →

No leaderboard results yet.