Stochastic optimization lies at the heart of machine learning, and its cornerstone is
stochastic gradient descent (SGD), a method introduced over 60 years ago. The last eight …

Electricity load forecasting has been attracting research and industry attention because of its
importance for energy management, infrastructure planning, and budgeting. In recent years …

Intense recent discussions have focused on how to provide individuals with control over
when their data can and cannot be used---the EU's Right To Be Forgotten regulation is an …

We show that parametric models trained by a stochastic gradient method (SGM) with few
iterations have vanishing generalization error. We prove our results by arguing that SGM is …

Federated learning is a novel paradigm that involves learning from data samples distributed
across a large network of clients while the data remains local. It is, however, known that …

We propose a new stochastic L-BFGS algorithm and prove a linear convergence rate for
strongly convex and smooth functions. Our algorithm draws heavily from a recent stochastic …

We consider a distributed learning problem over multiple access channel (MAC) using a
large wireless network. The computation is made by the network edge and is based on …

Minimax optimal convergence rates for numerous classes of stochastic convex optimization
problems are well characterized, where the majority of results utilize iterate averaged …

In recent years, various notions of capacity and complexity have been proposed for
characterizing the generalization properties of stochastic gradient descent (SGD) in deep …

We propose a new stochastic first-order algorithmic framework to solve stochastic composite
nonconvex optimization problems that covers both finite-sum and expectation settings. Our …