5 papers · 1 filter
MAdam: Metric-Aware Multi-Objective Adam
Fengbei Liu, Rachit Saluja, Sunwoo Kwak +5
Multi-objective optimization (MOO) underlies many machine learning problems, yet MOO solvers across the loss-balancing, gradient-balancing, and Pareto-based families almost univers…
Adapting to Shifting Correlations with Unlabeled Data Calibration
Minh Nguyen, Alan Q. Wang, Heejong Kim +1
Distribution shifts between sites can seriously degrade model performance since models are prone to exploiting unstable correlations. Thus, many methods try to find features that a…
Knockout: A simple way to handle missing inputs
Minh Nguyen, Batuhan K. Karaman, Heejong Kim +3
Deep learning models benefit from rich (e.g., multi-modal) input features. However, multimodal models might be challenging to deploy, because some inputs may be missing at inferenc…
Robust Learning via Conditional Prevalence Adjustment
Minh Nguyen, Alan Q. Wang, Heejong Kim +1
Healthcare data often come from multiple sites in which the correlations between confounding variables can vary widely. If deep learning models exploit these unstable correlations,…
A Framework for Interpretability in Machine Learning for Medical Imaging
Alan Q. Wang, Batuhan K. Karaman, Heejong Kim +4
Interpretability for machine learning models in medical imaging (MLMI) is an important direction of research. However, there is a general sense of murkiness in what interpretabilit…