Parallel and Distributed algorithms for ML problems
arXiv:2010.09585
Abstract
In this paper we make a survey of modern parallel and distributed approaches to solve sum-type convex minimization problems come from ML applications.
arXiv commentin Russian
References in corpus (24)
- Optimal algorithms for smooth and strongly convex distributed optimization in networks
- A Unified Theory of Decentralized SGD with Changing Topology and Local Updates
- An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback
- Communication Complexity of Distributed Convex Learning and Optimization
- Parametric estimation. Finite sample theory
- On Biased Compression for Distributed Learning
- Minibatch vs Local SGD for Heterogeneous Distributed Learning
- High probability generalization bounds for uniformly stable algorithms with nearly optimal rate
- Optimal Gradient Compression for Distributed and Federated Learning
- Multi-consensus Decentralized Accelerated Gradient Descent
- Linearly Converging Error Compensated SGD
- Random Reshuffling: Simple Analysis with Vast Improvements
- An Accelerated Directional Derivative Method for Smooth Stochastic Convex Optimization
- On the Complexity of Approximating Wasserstein Barycenter
- Recent theoretical advances in decentralized distributed convex optimization
- Universal gradient descent
- Estimate Sequences for Variance-Reduced Stochastic Composite Optimization
- Learning From An Optimization Viewpoint
- Statistically Preconditioned Accelerated Gradient Method for Distributed Optimization
- The Min-Max Complexity of Distributed Stochastic Convex Optimization with Intermittent Communication
- Near-Optimal Hyperfast Second-Order Method for convex optimization and its Sliding
- On Primal-Dual Approach for Distributed Stochastic Convex Optimization over Networks
- Error Compensated Distributed SGD Can Be Accelerated
- A Primal-Dual Framework for Decentralized Stochastic Optimization