Adjunct Lecturer

Arnak Poghosyan joined AUA as an adjunct lecturer in 2016. Before joining VMware, Inc. in 2010, Dr. Poghosyan worked as the head of the “Differential and Integral Equations” department at the Institute of Mathematics. Arnak Poghosyan holds 20 US patents. His research interests are in approximations and interpolations, Fourier analysis, data science, time series analysis, machine learning, and deep learning.

**Higher Education**

**1998,** Ph.D. in Mathematics,

Institute of Mathematics

**1994,** Bachelor of Physics,

Yerevan State University

**Courses taught:**

- Machine Learning
- Time Series Analysis

**Publications:**

- A.V. Poghosyan, A.N. Harutyunyan, and N.M. Grigoryan, Methods and Systems to Reduce time Series Data and Detect Outliers. US patent #10,452,665. Granted Oct 22, 2019.
- A.V. Poghosyan, A.N. Harutyunyan, N.M. Grigoryan, and M.A. Marvasti, Data-Agnostic Anomaly Detection. US patent #10,241,887. Granted Mar 26, 2019.
- A.V. Poghosyan, A.N. Harutyunyan, N.M. Grigoryan, Kh. Nazaryan, and R. Hovhannisyan, Datacenter Resource Allocation based on Estimated Capacity Metric. US patent #10,275,284. Granted Apr 30, 2019.
- A.V. Poghosyan, and T.K. Bakaryan, On an Interpolation by the Modied Trigonometric System, Journal of Contemporary Mathematical Analysis, vol. 53, N3, pp. 121-129, 2018
- A.V. Poghosyan, A.N. Harutyunyan, N.M. Grigoryan, V. Khachikyan, and M. Kerobyan, Multi-stage Data Compression for Time-Series Metric Data Within Computer Systems. US patent #9,742,435. Granted Aug 22, 2017.
- A.V. Poghosyan, A.N. Harutyunyan, and N.M. Grigoryan, Compression for Time Series Databases using Independent and Principal Component Analysis, Proc. 14th IEEE International Conference on Autonomic Computing (ICAC 2017), Columbus, OH, USA, July 17-21, pp. 279 - 284, 2017
- A.V. Poghosyan, A.N. Harutyunyan, and N.M. Grigoryan, Managing Cloud Infrastructures by a Multi-Layer Data Analytics, Proc. 2016 IEEE International Conference on Autonomic Computing (ICAC 2016), Wuerzburg, Germany, July 18-22, pp. 351 - 356, 2016
- M.A. Marvasti, A.V. Poghosyan, A.N. Harutyunyan, and N.M. Grigoryan, An Anomaly Event Correlation Engine: Identifying Root Causes, Bottlenecks, and Black Swans in IT Environments, VMware Technical Journal, vol. 2, N 1, pp. 35-45, 2013
- A. Poghosyan, On an Auto-correction Phenomenon of the Krylov-Gottlieb-Eckhoff Method, IMA Journal of Numerical Analysis, vol. 31, N 2, pp. 512-527, 2011

**Office location: **310W/PAB