We study the convergence of accelerated stochastic gradient descent for strongly convex objectives under the growth condition, which states that the variance of stochastic gradient …
We propose a fast temporal decomposition procedure for solving long-horizon nonlinear dynamic programs. The core of the procedure is sequential quadratic programming (SQP), with a …
We study the optimization aspects of personalized Federated Learning (FL). We develop a universal optimization theory applicable to all convex personalized FL models in the …
Stochastic gradient-based optimization methods, such as L-SVRG and its accelerated variant L-Katyusha [12], are widely used to train machine learning models. Theoretical and …
We study nonlinear optimization problems with stochastic objective and deterministic equality and inequality constraints, which emerge in numerous applications including finance, …
Training a classifier under non-convex constraints has gotten increasing attention in the machine learning community thanks to its wide range of applications such as algorithmic …
Large scale convex-concave minimax problems arise in numerous applications, including game theory, robust training, and training of generative adversarial networks. Despite their …
We consider solving nonlinear optimization problems with a stochastic objective and deterministic equality constraints. We assume for the objective that its evaluation, gradient, …
Abstract Graphs representing complex systems often share a partial underlying structure across domains while retaining individual features. Thus, identifying common structures can …
We consider the problem of estimating the difference between two undirected functional graphical models with shared structures. In many applications, data are naturally regarded as …