• Publications
  • Influence
Federated Learning: Strategies for Improving Communication Efficiency
TLDR
Federated Learning is a machine learning setting where the goal is to train a high-quality centralized model while training data remains distributed over a large number of clients each with unreliable and relatively slow network connections. Expand
Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function
TLDR
In this paper we develop a randomized block-coordinate descent method for minimizing the sum of a smooth and a simple nonsmooth block-separable convex function and prove that it obtains an $$\varepsilon $$-accurate solution with probability at least $$1-\rho $$ in at most $$O((n/\varrepsilon ) \log (1/\ rho ))$$ iterations, where $$n$$ is the number of blocks. Expand
Generalized Power Method for Sparse Principal Component Analysis
TLDR
We propose two single-unit and two block optimization formulations of the sparse PCA problem, aimed at extracting a single sparse dominant principal component of a data matrix, or more components at once, respectively. Expand
Federated Optimization: Distributed Machine Learning for On-Device Intelligence
TLDR
We introduce a new and increasingly relevant setting for distributed optimization in machine learning, where the data defining the optimization are unevenly distributed over an extremely large number of nodes. Expand
Parallel coordinate descent methods for big data optimization
TLDR
We show that randomized (block) coordinate descent methods can be accelerated by parallelization when applied to the problem of minimizing the sum of a partially separable smooth convex function and a simple separable convexfunction. Expand
Adding vs. Averaging in Distributed Primal-Dual Optimization
TLDR
In this paper, we present a novel generalization of the recent communication-efficient primal-dual framework (COCOA) for distributed optimization. Expand
Smooth minimization of nonsmooth functions with parallel coordinate descent methods
TLDR
We study the performance of a family of randomized parallel coordinate descent methods for minimizing the sum of a nonsmooth and separable convex functions. Expand
Accelerated, Parallel, and Proximal Coordinate Descent
TLDR
We propose a new randomized coordinate descent method for minimizing the sum of convex functions each of which depends on a small number of coordinates only. Expand
Semi-Stochastic Gradient Descent Methods
TLDR
We propose a new method, S2GD (Semi-Stochastic Gradient Descent), which runs for one or several epochs in each of which a single full gradient and a random number of stochastic gradients is computed, following a geometric law. Expand
Even Faster Accelerated Coordinate Descent Using Non-Uniform Sampling
TLDR
Accelerated coordinate descent is widely used in optimization due to its cheap per-iteration cost and scalability to large-scale problems. Expand
...
1
2
3
4
5
...