Ashkan Yousefpour

10-second Summary

Research Scientist (2020-22)

Visiting Researcher (2019-20)

Ph.D. Student (2014-19)

45-second Summary

Ashkan is a human being. He liks pasta and pull ups. His friends and family know him by his smile. He thinks he is friendly and entertaining to sit next to.

More seriously, he is currently a Research Scientist at Facebook AI. Working in Responsible AI org, he develops technologis for privacy-preserving machine learning and federated learning. He contributes to Opacus, an open-source library that enables training PyTorch models with differential privacy, and FLSim, an open-source library for simulating federated learning scenarios.

He was a Visiting Researcher at University of California, Berkeley and member of the Berkeley Artificial Intelligence Research (BAIR). When he was at UC Berkeley, he contributed to FLOW, a framework for deep reinforcement learning in traffic control.

Ashkan finished his Masters and PhD in Computer Science at the University of Texas at Dallas. His research was on intersection of Systems, Edge Computing, and Machine Learning, and he worked on improving quality of service in IoT and Deep Leanring Applications through Fog Computing. We he was at UT Dallas, he created Fog Computing Conference Hub.

He was an instructor for Discrete Mathematics at UT Dallas, in 2018. He has been member of technical program committee of FL-ICML, AIChallengeIoT, and reviewer of several journals and conferences, including NeurIPS, IEEE/ACM TON; IEEE TNSM, TMC, NETWORK, TSC, IoTJ, INFOCOM, ICDCS, and ICC.