35 citations · 95 across the 11 of their papers we have counts for
3 papers · 1 filter
Learning the Truth From Only One Side of the Story
Heinrich Jiang, Qijia Jiang, Aldo Pacchiano
Learning under one-sided feedback (i.e., where we only observe the labels for examples we predicted positively on) is a fundamental problem in machine learning -- applications incl…
Optimizing Black-box Metrics with Adaptive Surrogates
Qijia Jiang, Olaoluwa Adigun, Harikrishna Narasimhan +2
We address the problem of training models with black-box and hard-to-optimize metrics by expressing the metric as a monotonic function of a small number of easy-to-optimize surroga…
Subgradient Descent Learns Orthogonal Dictionaries
Yu Bai, Qijia Jiang, Ju Sun
This paper concerns dictionary learning, i.e., sparse coding, a fundamental representation learning problem. We show that a subgradient descent algorithm, with random initializatio…