no code implementations • ICML 2020 • Julien Hendrickx, Alex Olshevsky, Venkatesh Saligrama
We consider the problem of learning the qualities w_1, ... , w_n of a collection of items by performing noisy comparisons among them.
no code implementations • 16 Apr 2024 • Amirreza Neshaei Moghaddam, Alex Olshevsky, Bahman Gharesifard
We provide the first known algorithm that provably achieves $\varepsilon$-optimality within $\widetilde{\mathcal{O}}(1/\varepsilon)$ function evaluations for the discounted discrete-time LQR problem with unknown parameters, without relying on two-point gradient estimates.
no code implementations • 13 Mar 2024 • Haoxing Tian, Ioannis Ch. Paschalidis, Alex Olshevsky
We consider a distributed setup for reinforcement learning, where each agent has a copy of the same Markov Decision Process but transitions are sampled from the corresponding Markov chain independently by each agent.
no code implementations • 8 Jan 2024 • Julien Hendrickx, Alex Olshevsky
We consider the generalization error associated with stochastic gradient descent on a smooth convex function over a compact set.
no code implementations • 8 Dec 2023 • Haoxing Tian, Ioannis Ch. Paschalidis, Alex Olshevsky
Neural Temporal Difference (TD) Learning is an approximate temporal difference method for policy evaluation that uses a neural network for function approximation.
no code implementations • 25 May 2023 • Rui Liu, Alex Olshevsky
We provide a new non-asymptotic analysis of distributed temporal difference learning with linear function approximation.
1 code implementation • 29 Nov 2022 • Arsenii Mustafin, Alex Olshevsky, Ioannis Ch. Paschalidis
Our main result is a geometric convergence bound with predetermined learning rate of $1/8$, which is identical to the convergence bound available for SVRG in the convex setting.
no code implementations • 4 Mar 2022 • 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.
no code implementations • NeurIPS 2021 • Artin Spiridonoff, Alex Olshevsky, Ioannis Ch. Paschalidis
While it is possible to obtain a linear reduction in the variance by averaging all the stochastic gradients at every step, this requires a lot of communication between the workers and the server, which can dramatically reduce the gains from parallelism.
no code implementations • 16 Apr 2021 • Rui Liu, Alex Olshevsky
In the global state model, we show that the convergence rate of our distributed one-shot averaging method matches the known convergence rate of TD(0).
no code implementations • 27 Oct 2020 • Rui Liu, Alex Olshevsky
Temporal difference learning with linear function approximation is a popular method to obtain a low-dimensional approximation of the value function of a policy in a Markov Decision Process.
1 code implementation • NeurIPS 2020 • Qianqian Ma, Alex Olshevsky
We consider the problem of reconstructing a rank-one matrix from a revealed subset of its entries when some of the revealed entries are corrupted with perturbations that are unknown and can be arbitrarily large.
no code implementations • 11 Aug 2020 • Rui Liu, Alex Olshevsky
We study alternating minimization for matrix completion in the simplest possible setting: completing a rank-one matrix from a revealed subset of the entries.
no code implementations • 3 Jun 2020 • Artin Spiridonoff, Alex Olshevsky, Ioannis Ch. Paschalidis
While the initial analysis of Local SGD showed it needs $\Omega ( \sqrt{T} )$ communications for $T$ local gradient steps in order for the error to scale proportionately to $1/(nT)$, this has been successively improved in a string of papers, with the state-of-the-art requiring $\Omega \left( n \left( \mbox{ polynomial in log } (T) \right) \right)$ communications.
no code implementations • 28 Jun 2019 • 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.
no code implementations • 6 Jun 2019 • Shi Pu, Alex Olshevsky, Ioannis Ch. Paschalidis
This paper is concerned with minimizing the average of $n$ cost functions over a network, in which agents may communicate and exchange information with their peers in the network.
no code implementations • ICML 2018 • Yao Ma, Alex Olshevsky, Venkatesh Saligrama, Csaba Szepesvari
We consider worker skill estimation for the single-coin Dawid-Skene crowdsourcing model.
no code implementations • 1 Feb 2019 • Julien M. Hendrickx, Alex Olshevsky, Venkatesh Saligrama
The algorithm has a relative error decay that scales with the square root of the graph resistance, and provide a matching lower bound (up to log factors).
1 code implementation • 9 Nov 2018 • 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 $i$ in a network holds the function $f_i(\bz)$.
Optimization and Control
no code implementations • 26 Sep 2017 • 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.
Optimization and Control Distributed, Parallel, and Cluster Computing Multiagent Systems
no code implementations • 20 Jun 2017 • Yao Ma, Alex Olshevsky, Venkatesh Saligrama, Csaba Szepesvari
We then formulate a weighted rank-one optimization problem to estimate skills based on observations on an irreducible, aperiodic interaction graph.
no code implementations • 10 Apr 2017 • 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.
no code implementations • 6 Dec 2016 • Angelia Nedić, Alex Olshevsky, César A. Uribe
We show a convergence rate of $O(1/k)$ with the constant term depending on the number of agents and the topology of the network.
no code implementations • 23 Sep 2016 • 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.
no code implementations • 19 Sep 2016 • Angelia Nedić, Alex Olshevsky, Wei Shi, César A. Uribe
A recent algorithmic family for distributed optimization, DIGing's, have been shown to have geometric convergence over time-varying undirected/directed graphs.
no code implementations • 6 May 2016 • 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.
no code implementations • 9 Jun 2014 • Angelia Nedic, Alex Olshevsky
We investigate the convergence rate of the recently proposed subgradient-push method for distributed optimization over time-varying directed graphs.
Optimization and Control Systems and Control
no code implementations • 11 Sep 2012 • Naomi Ehrich Leonard, Alex Olshevsky
Motivated by the problem of tracking a direction in a decentralized way, we consider the general problem of cooperative learning in multi-agent systems with time-varying connectivity and intermittent measurements.
no code implementations • 8 Mar 2008 • Angelia Nedić, Alex Olshevsky, Asuman Ozdaglar, John N. Tsitsiklis
We consider a convex unconstrained optimization problem that arises in a network of agents whose goal is to cooperatively optimize the sum of the individual agent objective functions through local computations and communications.
Optimization and Control