Han Shao
@HanShao16
Assistant Professor @umdcs. Prev: Postdoc @Harvard, PhD @TTIC_Connect. Interested in machine learning theory problems.
Are you hesitant to review for #NeurIPS2022 because you cannot commit to reviewing 5 papers? Worry no more! In our blog, we explain how you can request a reduced workload. Thank you for helping the community. blog.neurips.cc/2022/04/01/how…
Check out our paper on incentivized collaboration in Federated Learning. We explore the question: what happens if some agents are satisfied with the instantaneous model on their local data during the training process and drop out immediately?
Please find our paper here: arxiv.org/abs/2311.16459 I believe the most important direction in Federated Learning right now is understanding the incentives and strategic behaviors around collaborations.
Super excited about this new position! I will be hiring PhD students this upcoming cycle :) Feel free to reach out if you are interested in machine learning theory.
.@UofMaryland's CS dept is welcoming eight new tenure-track faculty members! With expertise in cutting-edge areas, they'll boost our academic & research capabilities. Welcome aboard! 🐢📚 Read more: go.umd.edu/Hires24
Thrilled to be organizing the first Multimodal AI Workshop at TTI-Chicago! As we push the boundaries of #AI, the timing for the #MultimodalAI Workshop couldn’t be more perfect. Hear from our fantastic speakers across nlp, cv, speech, & robotics. Sign-up and submit your poster👇
We are excited to announce the #Multimodal AI Workshop as part of TTIC's 2024 Summer Workshop Program. Engage with pioneering researchers in language, speech, vision, and #robotics at the frontier of #AI. Learn more, register, and submit your posters here: buff.ly/3LaXVhF
We've got a new paper in which we solve Principal/Agent problems without any common prior assumptions. The abstract has some CS Jargon, so I asked ChatGPT to translate it for 1) an economic theorist, 2) a "development economist in a business school", and 3) a bright 3rd grader.
Applications are open for our 2023 Summer Internship program! Visiting student alumni have published their work at top venues, won best paper awards, and earned recognition by the CRA for outstanding undergraduate research. Learn more and apply: ttic.edu/visiting-stude…
Excited about our workshop at TTIC this summer - July 13-15th on "Online decision-making and real-world applications". We invite graduate students to present their work in the poster session (Deadline: June 30th). We also invite researchers to present interesting open problems!
Organized by researchers from Microsoft Research's NYC lab, TTIC Chicago Summer Workshop will look at the contemporary decision-making models that are being actively researched, aiming to bridge theory and practice. Register by the first week of July: msft.it/6014bmMRj
TR22-035 | A Characterization of Multiclass Learnability | Nataly Brukhim, Daniel Carmon, Irit Dinur, Shay Moran, Amir Yehudayoff ift.tt/9RzInW3
Can we boost barely robust learning algorithms to learn predictors with high robust accuracy? I am very excited to share new work putting forward a theory for boosting adversarial robustness: arxiv.org/abs/2202.05920. (1/6)
Last week I gave a 4-part tutorial on "Learning and Incentives" at @SimonsInstitute program on Learning & Games. I discussed adversarial, strategic, and collaborative interactions in learning. The slides are available at tinyurl.com/25wme25k. Videos are linked below.
This caught my attention, as someone who is interested in decision theory, online learning, and statistical learning. arxiv.org/abs/2112.13487
Tomorrow I’ll be presenting my first (!) first-author grad school paper at ICML with my brilliant coauthor @HanShao16. Along with @nhaghtal and Avrim Blum, we study the mathematical concerns behind collaboratively sampling when groups have different needs (eg federated learning).
Our second seminar of the season will take place on March 18 (Thursday), at 11 am Pacific Time (2pm ET): Tim Roughgarden from @ColumbiaCompSci will speak about "Data-Driven Algorithm Design." Details on the talk and how to join: sites.google.com/view/dstheory