This work considers the trade-off between accuracy and testtime computational cost of deep
neural networks (DNNs) via anytime predictions from auxiliary predictions. Specifically, we …

Abstract Machine learning algorithms have successfully entered industry through many real-
world applications (eg, search engines and product recommendations). In these …

We present SpeedBoost, a natural extension of functional gradient descent, for learning
anytime predictors, which automatically trade computation time for predictive accuracy by …

As machine learning methods are utilized in more and more real-world applications
involving constraints on computational budgets, the systematic integration of such …

• Select the feature that yields the maximum immediate reward r (st, at)= margin (st, at)− cost
(st, at) λ= 1, cost scaled to [0, 1], H1N1= positive order feat. marg. cost reward 1 coughing …

Dynamic inference networks, aimed at promoting computational efficiency, go along an
adaptive executing path for a given sample. Prevalent methods typically assign a router for …

In this paper, we tackle the problem of feature-efficient prediction: classification using a
limited number of features per test example. We show that modifying an ensemble classifier …

Lower urinary tract dysfunction (LUTD) is a debilitating condition that affects millions of
individuals worldwide, greatly diminishing their quality of life. The use of wireless, catheter …

We consider\textit {anytime} linear prediction in the common machine learning setting,
where features are in groups that have costs. We achieve anytime (or interruptible) …

With the rapid growth of real-time machine learning applications, the process of feature
selection and model optimization requires to integrate with the constraints on computational …