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 • 14 Aug 2023 • Justin Veiner, Fady Alajaji, Bahman Gharesifard
A unifying $\alpha$-parametrized generator loss function is introduced for a dual-objective generative adversarial network (GAN), which uses a canonical (or classical) discriminator loss function such as the one in the original GAN (VanillaGAN) system.
1 code implementation • 20 Jun 2022 • Adam Gronowski, William Paul, Fady Alajaji, Bahman Gharesifard, Philippe Burlina
Designing machine learning algorithms that are accurate yet fair, not discriminating based on any sensitive attribute, is of paramount importance for society to accept AI for critical applications.
no code implementations • 8 Jun 2022 • Kexue Zhang, Bahman Gharesifard, Elena Braverman
This article studies the event-triggered control problem of general nonlinear systems with time delay.
no code implementations • 18 May 2022 • Karthik Elamvazhuthi, Bahman Gharesifard, Andrea Bertozzi, Stanley Osher
As a corollary to this result, we establish that the continuity equation of the neural ODE is approximately controllable on the set of compactly supported probability measures that are absolutely continuous with respect to the Lebesgue measure.
no code implementations • 9 Mar 2022 • Adam Gronowski, William Paul, Fady Alajaji, Bahman Gharesifard, Philippe Burlina
We develop a novel method for ensuring fairness in machine learning which we term as the Renyi Fair Information Bottleneck (RFIB).
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 • ICLR 2021 • Paulo Tabuada, Bahman Gharesifard
In this paper, we explain the universal approximation capabilities of deep residual neural networks through geometric nonlinear control.
no code implementations • L4DC 2020 • Mohammad Akbari, Bahman Gharesifard, Tamas Linder
We study an online setting of the linear quadratic Gaussian optimal control problem on a sequence of cost functions, where similar to classical online optimization, the future decisions are made by only knowing the cost in hindsight.
no code implementations • 3 Jun 2020 • Himesh Bhatia, William Paul, Fady Alajaji, Bahman Gharesifard, Philippe Burlina
Another novel GAN generator loss function is next proposed in terms of R\'{e}nyi cross-entropy functionals with order $\alpha >0$, $\alpha\neq 1$.
no code implementations • 5 Dec 2019 • Kexue Zhang, Bahman Gharesifard
In this sense, the proposed algorithm is a hybrid impulsive and event-triggered strategy.
no code implementations • 29 Jun 2016 • Shreyas Sundaram, Bahman Gharesifard
We then propose a resilient distributed optimization algorithm that guarantees that the non-adversarial nodes converge to the convex hull of the minimizers of their local functions under certain conditions on the graph topology, regardless of the actions of a certain number of adversarial nodes.
Systems and Control Distributed, Parallel, and Cluster Computing Optimization and Control