activity
20152021
most citedSparse Multi-layer Image Approximation: Facial Image Compression

2 citations · 3 across the 7 of their papers we have counts for

collaborators

11 papers

cs.IR2021

Privacy-Preserving Near Neighbor Search via Sparse Coding with Ambiguation

Behrooz Razeghi, Sohrab Ferdowsi, Dimche Kostadinov +2

In this paper, we propose a framework for privacy-preserving approximate near neighbor search via stochastic sparsifying encoding. The core of the framework relies on sparse coding…

cs.CV20201 cited

Unsupervised Feature Learning for Event Data: Direct vs Inverse Problem Formulation

Dimche Kostadinov, Davide Scaramuzza

Event-based cameras record an asynchronous stream of per-pixel brightness changes. As such, they have numerous advantages over the standard frame-based cameras, including high temp…

math.OC2020

Online Weight-adaptive Nonlinear Model Predictive Control

Dimche Kostadinov, Davide Scaramuzza

Nonlinear Model Predictive Control (NMPC) is a powerful and widely used technique for nonlinear dynamic process control under constraints. In NMPC, the state and control weights of…

cs.LG2019

Network Parameter Learning Using Nonlinear Transforms, Local Representation Goals and Local Propagation Constraints

Dimche Kostadinov, Behrooz Razdehi, Slava Voloshynovskiy

In this paper, we introduce a novel concept for learning of the parameters in a neural network. Our idea is grounded on modeling a learning problem that addresses a trade-off betwe…

cs.LG2019

Clustering with Jointly Learned Nonlinear Transforms Over Discriminating Min-Max Similarity/Dissimilarity Assignment

Dimche Kostadinov, Behrooz Razeghi, Taras Holotyak +1

This paper presents a novel clustering concept that is based on jointly learned nonlinear transforms (NTs) with priors on the information loss and the discrimination. We introduce…

cs.IT2018

Privacy-Preserving Identification via Layered Sparse Code Design: Distributed Servers and Multiple Access Authorization

Behrooz Razeghi, Slava Voloshynovskiy, Sohrab Ferdowsi +1

We propose a new computationally efficient privacy-preserving identification framework based on layered sparse coding. The key idea of the proposed framework is a sparsifying trans…