On Seven Fundamental Optimization Challenges in Machine Learning

TL;DR

This paper addresses seven key optimization challenges in machine learning, providing theoretical guarantees, new algorithms, and improved methods for federated learning, adaptive optimization, and distributed systems.

Contribution

It introduces novel solutions and theoretical insights for seven fundamental optimization problems inspired by machine learning and federated learning.

Findings

First theoretical guarantees for Local SGD in heterogeneous data regimes

Closing the gap for Random Reshuffling and Shuffle-Once algorithms

Development of FedRR algorithm that outperforms gradient descent in communication efficiency

Abstract

Many recent successes of machine learning went hand in hand with advances in optimization. The exchange of ideas between these fields has worked both ways, with machine learning building on standard optimization procedures such as gradient descent, as well as with new directions in the optimization theory stemming from machine learning applications. In this thesis, we discuss new developments in optimization inspired by the needs and practice of machine learning, federated learning, and data science. In particular, we consider seven key challenges of mathematical optimization and develop a solution to each. Our first contribution is the resolution of a key open problem in Federated Learning: we establish the first theoretical guarantees for the famous Local SGD algorithm in the heterogeneous data regime. As the second challenge, we close the gap between the upper and lower bounds for the theory of two algorithms known as Random Reshuffling (RR) and Shuffle-Once that are widely used in practice, and set as the default data selection strategies for SGD in modern machine learning software. Our third contribution can be seen as a combination of our new theory for proximal RR and Local SGD yielding a new algorithm, which we call FedRR. Unlike Local SGD, FedRR can provably beat gradient descent in communication complexity in the heterogeneous data regime. The fourth challenge is related to the class of adaptive methods. In particular, we present the first parameter-free stepsize rule for gradient descent that provably works for any locally smooth convex objective. The fifth challenge is the development of an algorithm for distributed optimization with quantized updates that preserves linear convergence of gradient descent. Finally, in our sixth and seventh challenges, we develop new VR mechanisms applicable to the non-smooth setting based on proximal operators.