I am an assistant professor in the EECS department at Syracuse University.

I work on artificial intelligence, privacy, and machine learning. My recent work focuses on (1) how to make AI algorithms better aligned with societal values, especially privacy and fairness, and (2) how to use machine learning for solving complex optimization problems. I study these questions using methods and models from optimization, differential privacy, and multiagent systems. For more details, please see my publications.

My research has been generously supported by the National Science Foundation (NSF).

I received a double PhD in Computer Science from the University of Udine and from the New Mexico State University, co-advised by Agostino Dovier and Enrico Pontelli. My doctoral dissertation titled "Exploiting the Structure of Distributed Constrained Optimization" received a AI*IA award for best AI dissertation.
Before joining Syracuse University, I was a postdoctoral research associate at the Georgia Institute of Technology and a research fellow at the University of Michigan. For more details, please see my CV.
Curriculum Vitae Google Scholar DBLP GitHub Twitter

News Highlights

The 12th Workshop on Optimization and Learning in Multiagent Systems

Together with Amulya Yadav, Gauthier Picard, and Bryan Wilder, I am organizing the 12th workshop Optimization and Learning in Multiagent Systems (OptLearnMAS) at AAMAS-21.
This workshop invites works from different strands of the multi-agent systems community that pertain to the design of algorithms, models, and techniques to deal with multi-agent optimization and learning problems or problems that can be effectively solved by adopting a multi-agent framework. OptLearnMAS aims to provide a forum for researchers to discuss common issues that arise in solving optimization and learning problems in different areas, to introduce new application domains for multi-agent optimization techniques, and to elaborate common benchmarks to test solutions.
Consider submitting your best work!

The Second AAAI Workshop on Privacy Preserving Artificial Intelligence

Together with Pascal Van Hentenryck and Richard Evans, I am organizing the second workshop at AAAI-21 on Privacy Preserving Artificial Intelligence.
The aim of the workshop is to provide a platform for researchers, AI practitioners, and policymakers to discuss technical and societal issues and present solutions related to privacy in AI applications. The workshop will focus on both the theoretical and practical challenges related to the design of privacy-preserving AI systems and algorithms and will have strong multidisciplinary components, including soliciting contributions about policy, legal issues, and societal impact of privacy in AI.
Check out the outstanding program!

Other recent News and Highlights

Feb 2021 AIJ paper accepted: "Differential privacy of hierarchical Census data: An optimization approach".
Jan 2021 New preprint "Load Embeddings for Scalable AC-OPF Learning".
AAMAS 2021 paper accepted: "A Privacy-Preserving and Accountable Multi-agent Learning Framework".
Dec 2020 AAAI 2021 paper accepted: "Bias and Variance of Post-processing in Differential Privacy".
AAAI 2021 paper accepted: "Differentially Private and Fair Deep Learning: A Lagrangian Dual Approach".
Oct 2020 PRIMA 2020 paper accepted: "The Smart Appliance Scheduling Problem: A Bayesian Optimization Approach".
IEEE Transactions on Power Systems paper accepted: "Differentially Private Optimal Power Flow for Distribution Grids".
Aug 2020Our NSF proposal in the Robust Intelligence (RI) program has been funded. Check the Deep Constrained Learning project page.
Jul 2020 New preprint "High-Fidelity Machine Learning Approximations of Large-Scale Optimal Power Flow".
New preprint "Differential Privacy of Hierarchical Census Data: An Optimization Approach".
Jun 2020 New preprint "Differentially Private Convex Optimization with Feasibility Guarantees".
ECML 2020 paper accepted: "Lagrangian Duality for Constrained Deep Learning".
Apr 2020 IJCAI 2020 paper accepted: "Differential Privacy for Stackebelg Games".
IJCAI 2020 paper accepted: "OptStream Releasing Time Series Privately".
Apr 2020 PSCC 2020 paper accepted: "Privacy-Preserving Obfuscation for Distributed Power Systems".
Jan 2020 New preprint "Bilevel Optimization for Differentially Private Optimization".
I am excited to be joining the EECS department at Syracuse University.
More News

Honors and Awards


    4-125 CST
    Department of Electrical Engineering & Computer Science
    Syracuse University
    Syracuse - NY 13244 - U.S.A.
    +1 (575) 621-5948