To foster the development of new models for collaborative AI-assisted re...
Supervised learning is often affected by a covariate shift in which the
...
Prevalent deep learning models suffer from significant over-confidence u...
It can be difficult to identify trends and perform quality control in la...
Task-oriented dialog(TOD) aims to assist users in achieving specific goa...
Autonomous cars are indispensable when humans go further down the hands-...
Contemporary vision benchmarks predominantly consider tasks on which hum...
Hip fracture risk assessment is an important but challenging task.
Quant...
We study the problem of invariant learning when the environment labels a...
We propose JAWS, a series of wrapper methods for distribution-free
uncer...
Tracking and collecting fast-evolving online discussions provides vast d...
Discovering the complete set of causal relations among a group of variab...
Making predictions that are fair with regard to protected group membersh...
We propose a distributionally robust learning (DRL) method for unsupervi...
Distribution shift poses a challenge for active data collection in the r...
Learning-based control algorithms require collection of abundant supervi...
We propose a robust regression approach to off-policy evaluation (OPE) f...
Online harassment is a significant social problem. Prevention of online
...
We study the problem of safe learning and exploration in sequential cont...
We model human decision-making behaviors in a risk-taking task using inv...
We propose Regularized Learning under Label shifts (RLLS), a principled ...
We propose a robust adversarial prediction framework for general multicl...
Under covariate shift, training (source) data and testing (target) data
...
Covariate shift relaxes the widely-employed independent and identically
...