22 citations · 28 across the 8 of their papers we have counts for
10 papers
Envelope Characterizations for Trajectories of the Ćuk Converter
Aleksandra Lekić, Dušan Stipanović
In this paper, a complete characterization of the stability and the boundaries of the envelopes for trajectories of the Ćuk converter is provided in the cases of time and state-dep…
LMI Approach for Sliding Mode Control and Analysis of DC-DC Converters
Aleksandra Lekić, Dušan Stipanović
Circuits' and in particular DC/DC converters' switching behavior is analyzed in this paper using the equivalent control modeling of the dynamic systems' sliding mode regime. As a r…
Communication Efficient Curvature Aided Primal-dual Algorithms for Decentralized Optimization
Yichuan Li, Petros G. Voulgaris, Dusan M. Stipanovic +1
This paper presents a family of algorithms for decentralized convex composite problems. We consider the setting of a network of agents that cooperatively minimize a global objectiv…
Accelerated Almost-Sure Convergence Rates for Nonconvex Stochastic Gradient Descent using Stochastic Learning Rates
Theodoros Mamalis, Dusan Stipanovic, Petros Voulgaris
Large-scale optimization problems require algorithms both effective and efficient. One such popular and proven algorithm is Stochastic Gradient Descent which uses first-order gradi…
Stochastic Learning Rate Optimization in the Stochastic Approximation and Online Learning Settings
Theodoros Mamalis, Dusan Stipanovic, Petros Voulgaris
In this work, multiplicative stochasticity is applied to the learning rate of stochastic optimization algorithms, giving rise to stochastic learning-rate schemes. In-expectation th…
BFGS-ADMM for Large-Scale Distributed Optimization
Yichuan Li, Yonghai Gong, Nikolaos M. Freris +2
We consider a class of distributed optimization problem where the objective function consists of a sum of strongly convex and smooth functions and a (possibly nonsmooth) convex reg…
DN-ADMM: Distributed Newton ADMM for Multi-agent Optimization
Yichuan Li, Nikolaos M. Freris, Petros Voulgaris +1
In a multi-agent network, we consider the problem of minimizing an objective function that is expressed as the sum of private convex and smooth functions, and a (possibly) non-diff…
Biologically Inspired Collision Avoidance Without Distance Information
Thiago Marinho, Massi Amrouche, Dusan Stipanovic +2
Biological evidence shows that animals are capable of evading eminent collision without using depth information, relying solely on looming stimuli. In robotics, collision avoidance…
Dynamically Computing Adversarial Perturbations for Recurrent Neural Networks
Shankar A. Deka, Dušan M. Stipanović, Claire J. Tomlin
Convolutional and recurrent neural networks have been widely employed to achieve state-of-the-art performance on classification tasks. However, it has also been noted that these ne…
Fast Neural Network Verification via Shadow Prices
Vicenc Rubies-Royo, Roberto Calandra, Dusan M. Stipanovic +1
To use neural networks in safety-critical settings it is paramount to provide assurances on their runtime operation. Recent work on ReLU networks has sought to verify whether input…