72 citations · 143 across the 30 of their papers we have counts for
33 papers
Active Sensing Subserves Task-Level Control
Andrew Lamperski, Debojyoti Biswas, Eric S. Fortune +3
Active sensing is traditionally defined as the expenditure of energy, typically in the form of movement, for obtaining information. Here, we propose that the combination of relianc…
Approximation with Random Shallow ReLU Networks with Applications to Model Reference Adaptive Control
Andrew Lamperski, Tyler Lekang
Neural networks are regularly employed in adaptive control of nonlinear systems and related methods of reinforcement learning. A common architecture uses a neural network with a si…
An algorithm for bilevel optimization with traffic equilibrium constraints: convergence rate analysis
Akshit Goyal, Andrew Lamperski
Bilevel optimization with traffic equilibrium constraints plays an important role in transportation planning and management problems such as traffic control, transport network desi…
Function Approximation with Randomly Initialized Neural Networks for Approximate Model Reference Adaptive Control
Tyler Lekang, Andrew Lamperski
Classical results in neural network approximation theory show how arbitrary continuous functions can be approximated by networks with a single hidden layer, under mild assumptions…
Non-Asymptotic Pointwise and Worst-Case Bounds for Classical Spectrum Estimators
Andrew Lamperski
Spectrum estimation is a fundamental methodology in the analysis of time-series data, with applications including medicine, speech analysis, and control design. The asymptotic theo…
Sufficient Conditions for Persistency of Excitation with Step and ReLU Activation Functions
Tyler Lekang, Andrew Lamperski
This paper defines geometric criteria which are then used to establish sufficient conditions for persistency of excitation with vector functions constructed from single hidden-laye…
Constrained Langevin Algorithms with L-mixing External Random Variables
Yuping Zheng, Andrew Lamperski
Langevin algorithms are gradient descent methods augmented with additive noise, and are widely used in Markov Chain Monte Carlo (MCMC) sampling, optimization, and machine learning.…
Wasserstein Contraction Bounds on Closed Convex Domains with Applications to Stochastic Adaptive Control
Tyler Lekang, Andrew Lamperski
This paper is motivated by the problem of quantitatively bounding the convergence of adaptive control methods for stochastic systems to a stationary distribution. Such bounds are u…
Projected Stochastic Gradient Langevin Algorithms for Constrained Sampling and Non-Convex Learning
Andrew Lamperski
Langevin algorithms are gradient descent methods with additive noise. They have been used for decades in Markov chain Monte Carlo (MCMC) sampling, optimization, and learning. Their…
Topology Learning in Radial Dynamical Systems with Unreliable Data
Venkat Ram Subramanian, Deepjyoti Deka, Saurav Talukdar +2
Many complex engineering systems admit bidirectional and linear couplings between their agents. Blind and passive methods to identify such influence pathways/couplings from data ar…
Network Structure Identification from Corrupt Data Streams
Venkat Ram Subramanian, Andrew Lamperski, Murti V. Salapaka
Complex networked systems can be modeled as graphs with nodes representing the agents and links describing the dynamic coupling between them. Previous work on network identificatio…
Causal Structure Identification from Corrupt Data-Streams
Venkat Ram Subramanian, Andrew Lamperski, Murti V. Salapaka
Complex networked systems can be modeled and represented as graphs, with nodes representing the agents and the links describing the dynamic coupling between them. The fundamental o…
First-Order Algorithms for Constrained Nonlinear Dynamic Games
Bolei Di, Andrew Lamperski
This paper presents algorithms for non-zero sum nonlinear constrained dynamic games with full information. Such problems emerge when multiple players with action constraints and di…
Non-asymptotic Closed-Loop System Identification using Autoregressive Processes and Hankel Model Reduction
Bruce Lee, Andrew Lamperski
One of the primary challenges of system identification is determining how much data is necessary to adequately fit a model. Non-asymptotic characterizations of the performance of s…
Trading-Off Static and Dynamic Regret in Online Least-Squares and Beyond
Jianjun Yuan, Andrew Lamperski
Recursive least-squares algorithms often use forgetting factors as a heuristic to adapt to non-stationary data streams. The first contribution of this paper rigorously characterize…
Simple Algorithms for Dueling Bandits
Tyler Lekang, Andrew Lamperski
In this paper, we present simple algorithms for Dueling Bandits. We prove that the algorithms have regret bounds for time horizon T of order O(T^rho ) with 1/2 <= rho <= 3/4, which…
Newton's Method and Differential Dynamic Programming for Unconstrained Nonlinear Dynamic Games
Bolei Di, Andrew Lamperski
Dynamic games arise when multiple agents with differing objectives control a dynamic system. They model a wide variety of applications in economics, defense, energy systems and etc…
Online Adaptive Principal Component Analysis and Its extensions
Jianjun Yuan, Andrew Lamperski
We propose algorithms for online principal component analysis (PCA) and variance minimization for adaptive settings. Previous literature has focused on upper bounding the static ad…
Differential Dynamic Programming for Nonlinear Dynamic Games
Bolei Di, Andrew Lamperski
Dynamic games arise when multiple agents with differing objectives choose control inputs to a dynamic system. Dynamic games model a wide variety of applications in economics, defen…
Online convex optimization for cumulative constraints
Jianjun Yuan, Andrew Lamperski
We propose the algorithms for online convex optimization which lead to cumulative squared constraint violations of the form ,…
Moment Analysis of Stochastic Hybrid Systems Using Semidefinite Programming
Khem Raj Ghusinga, Andrew Lamperski, Abhyudai Singh
This paper proposes a semidefinite programming based method for estimating moments of a stochastic hybrid system (SHS). For polynomial SHSs -- which consist of polynomial continuou…
Estimating stationary characteristic functions of stochastic systems via semidefinite programming
Khem Raj Ghusinga, Andrew Lamperski, Abhyudai Singh
This paper proposes a methodology to estimate characteristic functions of stochastic differential equations that are defined over polynomials and driven by Lévy noise. For such sys…
Approximate moment dynamics for polynomial and trigonometric stochastic systems
Khem Raj Ghusinga, Mohammad Soltani, Andrew Lamperski +2
Stochastic dynamical systems often contain nonlinearities which make it hard to compute probability density functions or statistical moments of these systems. For the moment comput…
Analysis and Control of Stochastic Systems using Semidefinite Programming over Moments
Andrew Lamperski, Khem Raj Ghusinga, Abhyudai Singh
This paper develops a unified methodology for probabilistic analysis and optimal control design for jump diffusion processes defined by polynomials. For such systems, the evolution…