Reshad Hosseini

Assistant Professor at University of Tehran

My professional interest topics are machine learning, computational vision and signal processing. I am particularly interested in mathematical foundation of these fields such as differential geometry, optimization, functional analysis and statistics. My current research themes are: Developing optimization methods on manifolds; Statistical modeling of natural images; Using developed methods in applications like image segmentation, object recognition, etc.

Selected Journal Papers

P. H. Zadeh, R. Hosseini

Expected logarithm of central quadratic form and its use in KL-Divergence of some distributions

Entropy, 2016

A. Mehrjou, R. Hosseini, B.N. Araabi

Improved Bayesian information criterion for mixture model selection

Pattern Recognition Letters, 2016

R. Hosseini, S. Sra, L. Theis, M. Bethge

Inference and mixture modeling with the elliptical gamma distribution

Computational Statistics & Data Analysis, 2016

S. Sra, R. Hosseini

Conic geometric optimization on the manifold of positive definite matrices

SIAM Journal on Optimization, 2015

Selected Conference Papers

P. H. Zadeh, R. Hosseini, S. Sra

Geometric Mean Metric Learning

International Conference on Machine Learning, 2016

R. Hosseini, S. Sra

Matrix manifold optimization for Gaussian mixtures

Advances in Neural Information Processing Systems, 2015

R. Hosseini, S. Sra, L. Theis, M. Bethge

Data modeling with the elliptical gamma distribution.

Artificial Intelligence and Statistics, 2015