Ph.D in Computer Science, University of Oregon, 2017
M.S. in Computer Science, University of Oregon, 2016
M.S. in Information Technology, Sharif University of Technology, 2010
B.S. in Software Engineering, Shahid Beheshti University, 2007
Work experience
Aug. 2022 - present: Assistant Professor
University of Illinois Chicago
Aug. 2020 - June 2022: Assistant Professor
University of North Caroline, Charlotte
Apr. 2017 - Aug. 2020: Postdoctoral Research Associate
University of Massachusetts Amherst
Sep. 2011 - Mar 2017: Graduate Employee
University of Oregon
Apr. 2010 - Aug. 2011: Software Engineer
Maharan Engineering Group - Tehran, Iran
Sep. 2005 - Sep. 2007: Founder/Project Manager
Sepidan System Idea - Tehran, Iran
Jun. 2004 - Apr. 2005: Software Developer
Eimaa Telecommunication Inc. - Tehran, Iran
Jun. 2003 - May. 2004: Linux System Developer
Maharan Engineering Group. Tehran, Iran
Publications
A. Pokkunuru, A. Rooshenas, T. Strauss, A. Abhishek, T. Khan, Improved Training of Physics-informed Neural Networks using Energy-Based priors: A Study on Electrical Impedance Tomography, In Proceedings of the 11th International Conference on Learning Representations (ICLR), 2023.
S. Bhattacharyya, A. Rooshenas, S. Naskar, S. Sun, M. Iyyer, and A. McCallum, Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Models. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 4528–4537. Association for Computational Linguistics (ACL), 2021.
MA. Torkamani, S. Shankar, A. Rooshenas, and Phillip Wallis, Differential Equation Units: Learning Functional Forms of Activation Functions from Data, To be appeared in In Proc. of The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), 2020.
A. Rooshenas, Dongxu Zhang, Gopal Sharma, and Andrew McCallum, Search- Guided, Lightly-Supervised Training of Structured Prediction Energy Networks, In Advances in Neural Information Processing Systems 32 (NeurIPS), 2019.
A. Rooshenas, A. Kamath, and Andrew McCallum, Training Structured Prediction Energy Networks with Indirect Supervision, In Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics (HLT/NAACL), 2018.
A. Rooshenas and D. Lowd, Discriminative Structure Learning of Arithmetic Circuits, In Proc. of 19th International Conference on Artificial Intelligence and Statistics (AISTATS), 2016.
D. Lowd and A. Rooshenas, The Libra Toolkit for Probabilistic Models, Journal of Machine Learning Research (JMLR), 16:2459-2463, 2015.
A. Rooshenas and D. Lowd, Learning Sum-Product Networks with Direct andIndirect Variable Interactions, In Proc. of the Thirty-First International Conference on Machine Learning (ICML), 2014.
A. Rooshenas and D. Lowd, Learning Tractable Graphical Models Using Mixture of Arithmetic Circuits, Late-Breaking Developments in the Field of Artificial Intelligence, Presented at the Twenty-Seventh AAAI Conference on Artificial Intelligence (AAAI), 2013.
D. Lowd, A. Rooshenas, Learning Markov Networks with Arithmetic Circuits, In Proc. of The Sixteenth International Conference on Artificial Intelligence and Statistics (AISTATS), 2013.
A. Rooshenas, H. R. Rabiee, A. Movaghar. M. Y. Naderi. Reducing Data Transmission in Wireless Sensor Networks Using Principal Component Analysis. In Proc. of The Sixth International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP), 2010.
Teaching
Spring 2023: “Intro to Machine Learning” @ University of Illinois Chicago
Fall 2022: “Deep Generative Models” @ University of Illinois Chiacgo
Spring 2021, Fall 2021, Spring, 2022: “Machine Learning” @ University of North Carolina, Charlotte.
Fall 2020: “Advanced Machine Learning” @ University of North Carolina, Charlotte.
Fall 2018: “ML Seminar” @ University of Massachusetts Amherst.
Fall 2017: “AI/ML Seminar” @ University of Massachusetts Amherst.
Professional Service
Reviewer: Journal of Machine Learning Research - Software Track.
Program Committee/Reviewer: ICLR’23, Neurips’23.
Program Committee/Reviewer: ICML’22, NeurIPS’22.
Program Committee/Reviewer: ICLR’21, ICML’21.
Workshop Co-chair for Tractable Probabilistic Methods, TPM 2021, at UAI’21.
Program Committee/Reviewer: AAAI’20, ICLR’20, IJCAI’20, ICML’20, NeurIPS’20.
Program Committee/Reviewer: AAAI’19, ICLR’19, ICML’19, IJCAI’19, NAACL’19, NeurIPS’19.
Program Committee/Reviewer: IJCAI’18, TPM’18, LND4IR, NIPS’18.
Program Committee: ICML’17 Workshop on Deep Structured Prediction.
Reviewer: Machine Learning Journal - Springer, International Journal of Approximate Reasoning, ICML 17.
