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 481–490 of 536 papers

TitleStatusHype
Sign Operator for Coping with Heavy-Tailed Noise in Non-Convex Optimization: High Probability Bounds Under (L_0, L_1)-Smoothness—0
Simulation-Integrated Distributed Optimal Power Flow for Unbalanced Power Distribution Systems—0
Simultaneous Contact-Rich Grasping and Locomotion via Distributed Optimization Enabling Free-Climbing for Multi-Limbed Robots—0
Single Point-Based Distributed Zeroth-Order Optimization with a Non-Convex Stochastic Objective Function—0
Smoothed Normalization for Efficient Distributed Private Optimization—0
Theoretically Better and Numerically Faster Distributed Optimization with Smoothness-Aware Quantization Techniques—0
Distributed Optimization using Heterogeneous Compute SystemsCode0
Private Multi-Task Learning: Formulation and Applications to Federated LearningCode0
GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational ComplexityCode0
Sparsified SGD with MemoryCode0
Show:102550
← PrevPage 49 of 54Next →

No leaderboard results yet.