Motivated by large-scale optimization problems arising in the context of machine learning,
there have been several advances in the study of asynchronous parallel and distributed …

Federated learning (FL) involves training machine learning models over distributed edge
nodes (ie, workers) while facing three critical challenges, edge heterogeneity, Non-IID data …

Despite the success of single-agent reinforcement learning, multi-agent reinforcement
learning (MARL) remains challenging due to complex interactions between agents …

Motivated by applications to distributed optimization over networks and large-scale data
processing in machine learning, we analyze the deterministic incremental aggregated …

We introduce the decentralized Broyden-Fletcher-Goldfarb-Shanno (D-BFGS) method as a
variation of the BFGS quasi-Newton method for solving decentralized optimization problems …

Mini-batch optimization has proven to be a powerful paradigm for large-scale learning.
However, the state-of-the-art parallel mini-batch algorithms assume synchronous operation …

Motivated by applications in large-scale and multi-agent reinforcement learning, we study
the non-asymptotic performance of stochastic approximation (SA) schemes with delayed …

We establish matching upper and lower complexity bounds for gradient descent and
stochastic gradient descent on quadratic functions, when the gradients are delayed and …

Distributed optimization algorithms have the advantages of privacy protection and parallel
computing. However, the distributed nature of these algorithms makes the system vulnerable …

We present a convergence rate analysis for biased stochastic gradient descent (SGD),
where individual gradient updates are corrupted by computation errors. We develop …