Qi Lou

Interleave Variational Optimization with Monte Carlo Sampling: A Tale of Two Approximate Inference Paradigms

2019 · Proceedings of the AAAI Conference on Artificial Intelligence

Computing the partition function of a graphical model is a fundamental task in probabilistic inference. Variational bounds and Monte Carlo methods, two important approximate paradigms for this task, each has its respective strengths for solving …

Deep Multi-instance Networks with Sparse Label Assignment for Whole Mammogram Classification

2016 · bioRxiv (Cold Spring Harbor Laboratory)

Abstract Mammogram classification is directly related to computer-aided diagnosis of breast cancer. Traditional methods requires great effort to annotate the training data by costly manual labeling and specialized computational models to detect these annotations during …