123 citations · 534 across the 48 of their papers we have counts for
47 papers · 1 filter
Interpretable Gradient Descent for Kalman Gain
M. A. Belabbas, A. Olshevsky
We derive a decomposition for the gradient of the innovation loss with respect to the filter gain in a linear time-invariant system, decomposing as a product of an observability Gr…
Sample Complexity of Linear Quadratic Regulator Without Initial Stability
Amirreza Neshaei Moghaddam, Alex Olshevsky, Bahman Gharesifard
Inspired by REINFORCE, we introduce a novel receding-horizon algorithm for the Linear Quadratic Regulator (LQR) problem with unknown dynamics. Unlike prior methods, our algorithm a…
A Small Gain Analysis of Single Timescale Actor Critic
Alex Olshevsky, Bahman Gharesifard
We consider a version of actor-critic which uses proportional step-sizes and only one critic update with a single sample from the stationary distribution per actor step. We provide…
Optimal Vaccine Allocation for Pandemic Stabilization
Qianqian Ma, Yang-Yu Liu, Alex Olshevsky
How to strategically allocate the available vaccines is a crucial issue for pandemic control. In this work, we propose a mathematical framework for optimal stabilizing vaccine allo…
Optimal Lockdown for Pandemic Control
Qianqian Ma, Yang-Yu Liu, Alex Olshevsky
As a common strategy of contagious disease containment, lockdowns will inevitably weaken the economy. The ongoing COVID-19 pandemic underscores the trade-off arising from public he…
Local SGD With a Communication Overhead Depending Only on the Number of Workers
Artin Spiridonoff, Alex Olshevsky, Ioannis Ch. Paschalidis
We consider speeding up stochastic gradient descent (SGD) by parallelizing it across multiple workers. We assume the same data set is shared among workers, who can take SGD ste…
Asymptotic Network Independence and Step-Size for A Distributed Subgradient Method
Alex Olshevsky
We consider whether distributed subgradient methods can achieve a linear speedup over a centralized subgradient method. While it might be hoped that distributed network of node…
Asymptotic Network Independence in Distributed Stochastic Optimization for Machine Learning
Shi Pu, Alex Olshevsky, Ioannis Ch. Paschalidis
We provide a discussion of several recent results which, in certain scenarios, are able to overcome a barrier in distributed stochastic optimization for machine learning. Our focus…
A Sharp Estimate on the Transient Time of Distributed Stochastic Gradient Descent
Shi Pu, Alex Olshevsky, Ioannis Ch. Paschalidis
This paper is concerned with minimizing the average of cost functions over a network in which agents may communicate and exchange information with each other. We consider the s…
On the Inapproximability of the Discrete Witsenhausen Problem
Alex Olshevsky
We consider a discrete version of the Witsenhausen problem where all random variables are bounded and take on integer values. Our main goal is to understand the complexity of compu…
Robust Asynchronous Stochastic Gradient-Push: Asymptotically Optimal and Network-Independent Performance for Strongly Convex Functions
Artin Spiridonoff, Alex Olshevsky, Ioannis Ch. Paschalidis
We consider the standard model of distributed optimization of a sum of functions $F(\bz) = \sum_{i=1}^n f_i(\bz)$, where node in a network holds the function $f_i(\bz)$. We all…
Graph-Theoretic Analysis of Belief System Dynamics under Logic Constraints
Angelia Nedić, Alex Olshevsky, César A. Uribe
Opinion formation cannot be modeled solely as an ideological deduction from a set of principles; rather, repeated social interactions and logic constraints among statements are con…
Fully Asynchronous Push-Sum With Growing Intercommunication Intervals
Alex Olshevsky, Ioannis Ch. Paschalidis, Artin Spiridonoff
We propose an algorithm for average consensus over a directed graph which is both fully asynchronous and robust to unreliable communications. We show its convergence to the average…
Network Topology and Communication-Computation Tradeoffs in Decentralized Optimization
Angelia Nedić, Alex Olshevsky, Michael G. Rabbat
In decentralized optimization, nodes cooperate to minimize an overall objective function that is the sum (or average) of per-node private objective functions. Algorithms interleave…
Distributed Learning for Cooperative Inference
Angelia Nedić, Alex Olshevsky, César A. Uribe
We study the problem of cooperative inference where a group of agents interact over a network and seek to estimate a joint parameter that best explains a set of observations. Agent…
Distributed Gaussian Learning over Time-varying Directed Graphs
Angelia Nedić, Alex Olshevsky, César A. Uribe
We present a distributed (non-Bayesian) learning algorithm for the problem of parameter estimation with Gaussian noise. The algorithm is expressed as explicit updates on the parame…
On the geometric convergence rate of distributed economic dispatch/demand response in power networks
Thinh T. Doan, Alex Olshevsky
Motivated by potential applications in power systems, we study a problem of optimizing a sum of convex functions on dynamic networks of nodes when each function is known to…
A Tutorial on Distributed (Non-Bayesian) Learning: Problem, Algorithms and Results
Angelia Nedić, Alex Olshevsky, César A. Uribe
We overview some results on distributed learning with focus on a family of recently proposed algorithms known as non-Bayesian social learning. We consider different approaches to t…
On (Non)Supermodularity of Average Control Energy
Alex Olshevsky
Given a linear system, we consider the expected energy to move from the origin to a uniformly random point on the unit sphere as a function of the set of actuated variables. We sho…
Achieving Geometric Convergence for Distributed Optimization over Time-Varying Graphs
Angelia Nedich, Alex Olshevsky, Wei Shi
This paper considers the problem of distributed optimization over time-varying graphs. For the case of undirected graphs, we introduce a distributed algorithm, referred to as DIGin…
Distributed Learning with Infinitely Many Hypotheses
Angelia Nedić, Alex Olshevsky, César Uribe
We consider a distributed learning setup where a network of agents sequentially access realizations of a set of random variables with unknown distributions. The network objective i…
Eigenvalue Clustering, Control Energy, and Logarithmic Capacity
Alex Olshevsky
We prove two bounds showing that if the eigenvalues of a matrix are clustered in a region of the complex plane then the corresponding discrete-time linear system requires significa…
Network Independent Rates in Distributed Learning
Angelia Nedić, Alex Olshevsky, César A. Uribe
We propose a new belief update rule for Distributed Non-Bayesian learning in time-varying directed graphs, where a group of agents tries to collectively identify a hypothesis that…
Fast Convergence Rates for Distributed Non-Bayesian Learning
Angelia Nedić, Alex Olshevsky, César A. Uribe
We consider the problem of distributed learning, where a network of agents collectively aim to agree on a hypothesis that best explains a set of distributed observations of conditi…