65 citations · 203 across the 32 of their papers we have counts for
41 papers
Deep learning from a control vantage point
Álvaro Rodríguez Abella, João Pedro Silvestre, Bahman Gharesifard +1
This article offers an overview of recent developments in deep learning from a control vantage point. It reviews several classes of models including feedforward and residual neural…
Generating Preferential Attachment Graphs via a Pólya Urn with Expanding Colors
Somya Singh, Fady Alajaji, Bahman Gharesifard
We introduce a novel preferential attachment model using the draw variables of a modified Pólya urn with an expanding number of colors, notably capable of modeling influential opin…
A Unifying Generator Loss Function for Generative Adversarial Networks
Justin Veiner, Fady Alajaji, Bahman Gharesifard
A unifying -parametrized generator loss function is introduced for a dual-objective generative adversarial network (GAN), which uses a canonical (or classical) discriminator los…
A Unified Framework for Continuous-time Unconstrained Distributed Optimization
Behrouz Touri, Bahman Gharesifard
We introduce a class of distributed nonlinear control systems, termed as the flow-tracker dynamics, which capture phenomena where the average state is controlled by the average con…
Flexible-step Model Predictive Control based on Generalized Lyapunov Functions
Annika Fürnsinn, Christian Ebenbauer, Bahman Gharesifard
We present a novel nonlinear model predictive control (MPC) scheme with relaxed stability criteria, based on the idea of generalized discrete-time control Lyapunov functions. These…
Logarithmic Regret in Adaptive Control of Noisy Linear Quadratic Regulator Systems Using Hints
Mohammad Akbari, Bahman Gharesifard, Tamas Linder
The problem of regret minimization for online adaptive control of linear-quadratic systems is studied. In this problem, the true system transition parameters (matrices and )…
Event-Triggered Control for Discrete-Time Delay Systems
Kexue Zhang, Elena Braverman, Bahman Gharesifard
This study focuses on event-triggered control of nonlinear discrete-time systems with time delays. Based on a Lyapunov-Krasovskii type input-to-state stability result, we propose a…
A Note on Stability of Event-Triggered Control Systems with Time Delays
Kexue Zhang, Bahman Gharesifard, Elena Braverman
This note studies stability of event-triggered control systems with the event-triggered control algorithm proposed in [1]. We construct a novel Halanay-type inequality, which is us…
Event-Triggered Control for Nonlinear Time-Delay Systems
Kexue Zhang, Bahman Gharesifard, Elena Braverman
This article studies the event-triggered control problem of general nonlinear systems with time delay. A novel event-triggering scheme is presented with two tunable design paramete…
Classification Utility, Fairness, and Compactness via Tunable Information Bottleneck and Rényi Measures
Adam Gronowski, William Paul, Fady Alajaji +2
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 criti…
Neural ODE Control for Trajectory Approximation of Continuity Equation
Karthik Elamvazhuthi, Bahman Gharesifard, Andrea Bertozzi +1
We consider the controllability problem for the continuity equation, corresponding to neural ordinary differential equations (ODEs), which describes how a probability measure is pu…
Renyi Fair Information Bottleneck for Image Classification
Adam Gronowski, William Paul, Fady Alajaji +2
We develop a novel method for ensuring fairness in machine learning which we term as the Renyi Fair Information Bottleneck (RFIB). We consider two different fairness constraints -…
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…
Submodular Maximization with Limited Function Access
Andrew Downie, Bahman Gharesifard, Stephen L. Smith
We consider a class of submodular maximization problems in which decision-makers have limited access to the objective function. We explore scenarios where the decision-maker can ob…
A Note on Nussbaum-type Control and Lie-bracket Approximation
Marc Weber, Christian Ebenbauer, Bahman Gharesifard
In this paper, we propose an adaptive control law for completely unknown scalar linear systems based on Lie-bracket approximation methods. We investigate stability and convergence…
Structural averaged controllability of linear ensemble systems
Bahman Gharesifard, Xudong Chen
In the paper, we introduce and address the problem of structural averaged controllability for linear ensemble systems. We provide examples highlighting the differences between this…
On the lack of monotonicity of Newton-Hewer updates for Riccati equations
Mohammad Akbari, Bahman Gharesifard, Tamas Linder
We provide a set of counterexamples for the monotonicity of the Newton-Hewer method for solving the discrete-time algebraic Riccati equation in dynamic settings, drawing a contrast…
A Finite Memory Interacting Pólya Contagion Network and its Approximating Dynamical Systems
Somya Singh, Fady Alajaji, Bahman Gharesifard
We introduce a new model for contagion spread using a network of interacting finite memory two-color Pólya urns, which we refer to as the finite memory interacting Pólya contagion…
Initialization and Curing Policies for Polya Contagion Networks
Greg Harrington, Fady Alajaji, Bahman Gharesifard
This paper investigates optimization policies for resource distribution in network epidemics using a model that derives from the classical Polya process. The basic mechanics of thi…
Universal Approximation Power of Deep Residual Neural Networks via Nonlinear Control Theory
Paulo Tabuada, Bahman Gharesifard
In this paper, we explain the universal approximation capabilities of deep residual neural networks through geometric nonlinear control. Inspired by recent work establishing links…
Anytime Proximity Moving Horizon Estimation: Stability and Regret
Meriem Gharbi, Bahman Gharesifard, Christian Ebenbauer
In this paper, we address the efficient implementation of moving horizon state estimation of constrained discrete-time linear systems. We propose a novel iteration scheme which emp…
Least th-Order and Rényi Generative Adversarial Networks
Himesh Bhatia, William Paul, Fady Alajaji +2
We investigate the use of parametrized families of information-theoretic measures to generalize the loss functions of generative adversarial networks (GANs) with the objective of i…
Rate of Convergence for Distributed Optimization with Uncertain Communications
Pouya Rezaeinia, Bahman Gharesifard
We consider the distributed optimization problem for the sum of convex functions where the underlying communications network connecting agents at each time is drawn at random from…
The trouble with imaginary eigenvalues. Optimal control, controllability, frequency response
Bahman Gharesifard, Andrew D. Lewis
We investigate a few problems in the theory of linear time-invariant systems that arise when the open-loop system possesses imaginary eigenvalues. The problems are: (1) the infinit…