Shahin Shahrampour CONTACT INFORMATION

Size: px

Start display at page:

Download "Shahin Shahrampour CONTACT INFORMATION"

Poppy Pope
6 years ago
Views:

1 Shahin Shahrampour CONTACT INFORMATION Department of Electrical Engineering Harvard University 33 Oxford Street, 321 Maxwell Dworkin Building Cambridge, MA 02138, USA Web: RESEARCH INTERESTS Machine Learning, Optimization, Decision Theory, Statistical Signal Processing, Distributed Algorithms EXPERIENCE Harvard University, Cambridge, MA Postdoctoral Fellow in Electrical Engineering Host: Prof. Vahid Tarokh Sep present Sep Aug Graduate Research Assistant in Electrical and Systems Engineering Advisors: Prof. Ali Jadbabaie and Prof. Alexander Rakhlin EDUCATION Ph.D. in Electrical and Systems Engineering Aug Thesis: Online and Statistical Learning in Networks Advisors: Prof. Ali Jadbabaie and Prof. Alexander Rakhlin A.M. in Statistics, The Wharton School May 2014 Thesis: Online Learning of Dynamic Parameters in Social Networks M.S. in Electrical Engineering Aug B.S. in Electrical Engineering Aug Sharif University of Technology, Tehran, Iran 1 of 5

2 JOURNAL PAPERS J6) Analysis of Multi-State Autoregressive Models Jie Ding, Shahin Shahrampour, Kathryn Heal, and Vahid Tarokh Revised and resubmitted to IEEE Transactions on Signal Processing (TSP), 2017 J5) Online Learning for Multimodal Data Fusion with an Application to Object Recognition Shahin Shahrampour, Mohammad Noshad, Jie Ding, and Vahid Tarokh IEEE Transactions on Circuits and Systems II: Express Briefs (TCAS-II), In press. J4) Distributed Online Optimization in Dynamic Environments Using Mirror Descent IEEE Transactions on Automatic Control (TAC), March 2018 J3) On Sequential Elimination Algorithms for Best-Arm Identification in Multi-Armed Bandits Shahin Shahrampour, Mohammad Noshad, and Vahid Tarokh IEEE Transactions on Signal Processing (TSP), August 2017 J2) Distributed Detection: Finite-time Analysis and Impact of Network Topology IEEE Transactions on Automatic Control (TAC), November 2016 J1) Topology Identification of Directed Dynamical Networks via Power Spectral Analysis Shahin Shahrampour and Victor M. Preciado IEEE Transactions on Automatic Control (TAC), August 2015 PEER-REVIEWED CONFERENCE PAPERS C14) On Data-Dependent Random Features for Improved Generalization in Supervised Learning Shahin Shahrampour, Ahmad Beirami, and Vahid Tarokh AAAI Conference on Artificial Intelligence (AAAI), 2018 [Acceptance Rate: 24.5%] C13) On Optimal Generalizability in Parametric Learning Ahmad Beirami, Meisam Razaviyayn, Shahin Shahrampour, and Vahid Tarokh Advances in Neural Information Processing Systems (NIPS), 2017 [Acceptance Rate: 20.9%] C12) Nonlinear Sequential Accepts and Rejects for Identification of Top Arms in Stochastic Bandits Shahin Shahrampour and Vahid Tarokh Allerton Conference on Communication, Control, and Computing (Allerton), C11) An Online Optimization Approach for Multi-Agent Tracking of Dynamic Parameters in the Presence of Adversarial Noise IEEE American Control Conference (ACC), 2017 C10) Multi-Armed Bandits in Multi-Agent Networks IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017 C9) Online Optimization in Dynamic Environments: Improved Regret Rates for Strongly Convex Problems Aryan Mokhtari, Shahin Shahrampour, Ali Jadbabaie, and Alejandro Ribeiro IEEE Conference on Decision and Control (CDC), 2016 C8) Distributed Estimation of Dynamic Parameters : Regret Analysis IEEE American Control Conference (ACC), 2016 C7) Online Optimization : Competing with Dynamic Comparators Ali Jadbabaie, Alexander Rakhlin, Shahin Shahrampour, and Karthik Sridharan [Alphabetical Order] Artificial Intelligence and Statistics (AISTATS), 2015 [Acceptance Rate: 26.7%] 2 of 5

3 C6) Finite-time Analysis of the Distributed Detection Problem Allerton Conference on Communication, Control, and Computing (Allerton), 2015 C5) Learning without Recall by Random Walks on Directed Graphs Mohammad Amin Rahimian, Shahin Shahrampour, and Ali Jadbabaie IEEE Conference on Decision and Control (CDC), 2015 C4) Switching to Learn Shahin Shahrampour, Mohammad Amin Rahimian, and Ali Jadbabaie IEEE American Control Conference (ACC), 2015 C3) Online Learning of Dynamic Parameters in Social Networks Advances in Neural Information Processing Systems (NIPS), 2013 [Acceptance Rate: 25.3%] C2) Exponentially Fast Parameter Estimation in Networks Using Distributed Dual Averaging IEEE Conference on Decision and Control (CDC), 2013 C1) Reconstruction of Directed Networks from Consensus Dynamics Shahin Shahrampour and Victor M. Preciado IEEE American Control Conference (ACC), 2013 TALKS AND PRESENTATIONS Nonlinear Sequential Accepts and Rejects for Identification of Top Arms in Stochastic Bandits Allerton Conference on Communication, Control, and Computing (Allerton), Champaign, IL 2017 Distributed Online Optimization in Dynamic Environments Using Mirror Descent American Control Conference (ACC), Seattle, WA 2017 ISS Seminar at Harvard University, Cambridge, MA 2016 Multi-Armed Bandits in Multi-Agent Networks International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, LA 2017 Distributed Estimation of Dynamic Parameters : Regret Analysis American Control Conference (ACC), Boston, MA 2016 Finite-time Analysis of the Distributed Detection Problem Allerton Conference on Communication, Control, and Computing (Allerton), Champaign, IL 2015 Switching to Learn American Control Conference (ACC), Chicago, IL 2015 Online Optimization : Competing with Dynamic Comparators International Conference on Artificial Intelligence and Statistics (AISTATS), San Diego, CA 2015 Online Learning of Dynamic Parameters in Social Networks Annual Conference on Neural Information Processing Systems (NIPS), Lake Tahoe, NV 2013 Reconstruction of Directed Networks from Consensus Dynamics American Control Conference (ACC), Washington, DC of 5

4 TEACHING EXPERIENCE Instructor, Applied Probability and Financial Time-Series 2016 High School Apprenticeship Program at Harvard University School of Engineering and Applied Science Teaching Assistant, Elements of Probability Theory 2010, 2011 University of Pennsylvania Teaching Assistant, Signal and Systems 2008 Sharif University of Technology Teaching Assistant, Fundamentals of Electrical Engineering (Lab) 2008 Sharif University of Technology MEDIA COVERAGE ARO High School Apprenticeship Program at Harvard University 2016 Link: HONORS AND AWARDS Travel award for NIPS conference 2013, 2017 Postdoctoral fellowship, Harvard Univeristy 2015 Ph.D. fellowship, University of Pennsylvania 2009 Ranked 12-th (among 400,000 students) in the nation-wide universities entrance exam, Iran 2005 SERVICE Co-chair of the invited session Learning and Estimation in Networks in IEEE American Control Conference (ACC), Reviewed for : IEEE Transactions on Automatic Control (TAC) IEEE Transactions on Signal Processing (TSP) IEEE Transactions on Signal and Information Processing over Networks (TSIPN) IEEE Transactions on Network Science and Engineering (TNSE) IEEE Transactions on Control of Network Systems (TCNS) IEEE Transactions on Circuits and Systems (TCAS) Operations Research (OPRE), INFORMS Distributed Computing (DIST), Springer 4 of 5

5 Automatica, Elsevier Neural Information Processing Systems (NIPS) IEEE Conference on Decision and Control (CDC) IEEE American Control Conference (ACC) IEEE Global Conference on Signal and Information Processing (GlobalSIP) 5 of 5

CEYHUN EKSIN. EXPERIENCE & EDUCATION Atlanta, GA Postdoctoral Researcher April

CEYHUN EKSIN. EXPERIENCE & EDUCATION Atlanta, GA Postdoctoral Researcher April CEYHUN EKSIN Georgia Institute of Technology T: +1 (267) 994 74 07 (Mobile) School of Electrical & Computer Engineering School of Biological Sciences Tech. Square Research Building #436A Email: ceyhuneksin@gatech.edu