6 papers · 1 filter
Mind the Residual Gap: Probabilistic Downscaling under Real-World Bias
Yujin Kim, Nidhi Soma, Sarah Dean
Probabilistic downscaling models the conditional distribution of high-resolution fields given coarse inputs and is a core challenge in atmospheric science, climate modeling, and ot…
Sparse-to-Field Reconstruction via Stochastic Neural Dynamic Mode Decomposition
Yujin Kim, Sarah Dean
Many consequential real-world systems, like wind fields and ocean currents, are dynamic and hard to model. Learning their governing dynamics remains a central challenge in scientif…
Pre-trained Large Language Models Learn Hidden Markov Models In-context
Yijia Dai, Zhaolin Gao, Yahya Sattar +2
Hidden Markov Models (HMMs) are foundational tools for modeling sequential data with latent Markovian structure, yet fitting them to real-world data remains computationally challen…
Learning from Streaming Data when Users Choose
Jinyan Su, Sarah Dean
In digital markets comprised of many competing services, each user chooses between multiple service providers according to their preferences, and the chosen service makes use of th…
Strategic Usage in a Multi-Learner Setting
Eliot Shekhtman, Sarah Dean
Real-world systems often involve some pool of users choosing between a set of services. With the increase in popularity of online learning algorithms, these services can now self-o…
Initializing Services in Interactive ML Systems for Diverse Users
Avinandan Bose, Mihaela Curmei, Daniel L. Jiang +4
This paper investigates ML systems serving a group of users, with multiple models/services, each aimed at specializing to a sub-group of users. We consider settings where upon depl…