Maruan Al-Shedivat

8223 Gates & Hillman

5000 Forbes Avenue

Pittsburgh, PA 15213

I’m a Ph.D. student in Machine Learning Department at CMU, advised by Eric Xing.

Research interests:
Sequential decision making, multi-task learning, deep learning, graphical models, interpretable ML. Applications in healthcare, natural language, multi-agent systems, and general AI.

I’ve recently co-founded Carnegie Mellon AI+. If you are interested in sponsoring events, please contact me by email.

I hold M.Sc. in Computer Science from KAUST where I worked with Khaled Salama and collaborated with Gert Cauwenberghs on neuromorphic approaches to machine learning. Before that I studied Physics at Lomonosov Moscow State University and Data Analysis at Yandex School of Data Analysis.

Besides my professional activities, I am a member of Carnegie Marathon Club, love doing sports and hiking in beautiful places. Also, I grew up in Moscow. Feel free to talk to me in Russian.

news

Jul 15, 2018

Some highlights from AAMAS 2018 and ICML 2018:

We’ve presented a number of papers:
Code for LOLA and DiCE has been released. Check it out on GitHub.

May 21, 2018

Spending this summer at Google Research on the Language team in NYC, hosted by Ankur Parikh. Thinking about language generation in low-resource and multi-task settings.

May 5, 2018

Some highlights from ICLR 2018:

Our paper on Continuous Adaptation via Meta-Learning (joint work with Trapit, Yura, Ilya, Igor, Pieter at OpenAI) received a Best Paper Award! Check out: poster, talk (starts around 1:20:50).
We presented DiCE: The Infinitely Differentiable Monte-Carlo Estimator at the workshop. Here is the poster. Reach out if you have questions!

Apr 15, 2018

Very grateful to be awarded the 2018 CMLH Fellowship in Digital Healthcare by the Center of Machine Learning and Health. Looking forward to doing a lot of new exciting work in #ML4Health!

Apr 3, 2018

I gave a talk at ML Lunch seminar on meta-learning for continuous adaptation. Here are the slides.