Super excited about a new paper (with applications to conformal prediction and large action space games) that asks what properties online predictions should have such that acting on them gives good results. Calibration would be nice, but is too hard in high dimensions. But...

Ok -- as promised, more about uncertainty quantification. Suppose we are sequentially making predictions in a k-class setting: We see images that could be hot dogs, stop signs, rabbits, etc. If we are unsure of a label, we should produce a set of labels --- a "prediction set".

I'm at #NeurIPS2023 workshops today! Check out our work on high dimensional prediction and applications to online combinatorial optimization, extensive form games, and prediction sets! ⏱️ Talk 2:30-3, poster 3-4 📍OPT for ML w/ Georgy, Ramya, Aaron Roth arxiv.org/abs/2310.17651

belated but I'm excited to start a PhD at Machine Learning Dept. at Carnegie Mellon this fall as a NSF fellow!! I'm incredibly grateful to my mentors and advisors Aaron Roth, Kevin He, and Yi Xing for all their guidance and support along the way 😀

🧵 on surprising revelations from our study of specialized foundation models (FMs beyond vision/text): after evaluating dozens of scientific & time series FMs we found that most weren’t even competitive with simple supervised models, some with as little as 513 parameters. 1/n

I am on the industry job market, and am planning to interview around next March. I am attending NeurIPS Conference, and I hope to meet you there if you are hiring! My website: soyeonm.github.io Short bio about me: I am a 5th year PhD student at CMU MLD, working with Russ Salakhutdinov

I have some news to share! Datadog, Inc. is forming a new AI research lab, and I'm excited to announce that I've joined as Chief Scientist to lead this effort. Datadog has a great work culture, lots of data and compute, and is committed to open science and open sourcing. Our team

Interacting with the external world and reacting based on outcomes are crucial capabilities of agentic systems, but existing LLMs’ ability to do so is limited. Introducing Paprika 🌶️, our work on making LLMs general decision makers than can solve new tasks zero-shot. 🧵 1/n

Hard to overstate how important observability data is in forecasting! The complex nature of the data led to huge challenges in even evaluating time series models but also helped us make Toto super capable. Excited to share this work led by Ben and Emaad at Datadog AI Research!