activity
20192024
most citedDADAM: A Consensus-based Distributed Adaptive Gradient Method for Online Optimization

15 citations · 25 across the 6 of their papers we have counts for

collaborators

6 papers

math.OC20211 cited

Certainty Equivalent Quadratic Control for Markov Jump Systems

Zhe Du, Yahya Sattar, Davoud Ataee Tarzanagh +3

Real-world control applications often involve complex dynamics subject to abrupt changes or variations. Markov jump linear systems (MJS) provide a rich framework for modeling such…

math.OC2021

Solving a class of non-convex min-max games using adaptive momentum methods

Babak Barazandeh, Davoud Ataee Tarzanagh, George Michailidis

Adaptive momentum methods have recently attracted a lot of attention for training of deep neural networks. They use an exponential moving average of past gradients of the objective…

math.OC20201 cited

A Newton-Type Active Set Method for Nonlinear Optimization with Polyhedral Constraints

William W. Hager, Davoud Ataee Tarzanagh

A Newton-type active set algorithm for large-scale minimization subject to polyhedral constraints is proposed. The algorithm consists of a gradient projection step, a second-order…

math.OC20208 cited

Adaptive First-and Zeroth-order Methods for Weakly Convex Stochastic Optimization Problems

Parvin Nazari, Davoud Ataee Tarzanagh, George Michailidis

In this paper, we design and analyze a new family of adaptive subgradient methods for solving an important class of weakly convex (possibly nonsmooth) stochastic optimization probl…

stat.ML2019

Online Distributed Estimation of Principal Eigenspaces

Davoud Ataee Tarzanagh, Mohamad Kazem Shirani Faradonbeh, George Michailidis

Principal components analysis (PCA) is a widely used dimension reduction technique with an extensive range of applications. In this paper, an online distributed algorithm is propos…

cs.LG201915 cited

DADAM: A Consensus-based Distributed Adaptive Gradient Method for Online Optimization

Parvin Nazari, Davoud Ataee Tarzanagh, George Michailidis

Adaptive gradient-based optimization methods such as \textsc{Adagrad}, \textsc{Rmsprop}, and \textsc{Adam} are widely used in solving large-scale machine learning problems includin…