Search Results for author:
Found 12 papers, 1 papers with code
Sample Complexity of the Linear Quadratic Regulator: A Reinforcement Learning Lens
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.
A Unifying Generator Loss Function for Generative Adversarial Networks
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.
Classification Utility, Fairness, and Compactness via Tunable Information Bottleneck and Rényi Measures
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.
Event-Triggered Control for Nonlinear Time-Delay Systems
This article studies the event-triggered control problem of general nonlinear systems with time delay.
Neural ODE Control for Trajectory Approximation of Continuity Equation
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.
Renyi Fair Information Bottleneck for Image Classification
We develop a novel method for ensuring fairness in machine learning which we term as the Renyi Fair Information Bottleneck (RFIB).
A Small Gain Analysis of Single Timescale Actor Critic
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.
Universal Approximation Power of Deep Residual Neural Networks via Nonlinear Control Theory
In this paper, we explain the universal approximation capabilities of deep residual neural networks through geometric nonlinear control.
Riccati updates for online linear quadratic control
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.
Least $k$th-Order and Rényi Generative Adversarial Networks
Another novel GAN generator loss function is next proposed in terms of R\'{e}nyi cross-entropy functionals with order $\alpha >0$, $\alpha\neq 1$.
Hybrid Event-Triggered and Impulsive Control for Time-Delay Systems
In this sense, the proposed algorithm is a hybrid impulsive and event-triggered strategy.
Distributed Optimization Under Adversarial Nodes
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
