Statistical Learning
Conditional Density Estimation with Histogram Trees
This makes CDE particularly useful in critical application domains. However, interpretable CDE methods are understudied.
Learning Low-Rank Feature for Thorax Disease Classification
We study thorax disease classification in this paper.
Conformalized Credal Set Predictors
However, the design of methods for learning credal set predictors remains a challenging problem. In this paper, we make use of conformal prediction for this purpose.
Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learning
Meta-learning offers a promising avenue for few-shot learning (FSL), enabling models to glean a generalizable feature embedding through episodic training on synthetic FSL tasks in a source domain.
Label Noise: Ignorance Is Bliss
We establish a new theoretical framework for learning under multi-class, instance-dependent label noise. This framework casts learning with label noise as a form of domain adaptation, in particular, domain adaptation under posterior drift.
