Trade-offs in learning controllers from noisy data

Mutual Learning with Trade-Offs

Computational Trade-offs in Statistical Learning

Computational Trade-offs in Statistical Learning by Alekh Agarwal Doctor of Philosophy in Computer Science and the Designated Emphasis

Trade-offs in Explanatory Model Learning

In many practical applications, accuracy of a prediction is as important as understandability of the process that leads to it. Explanatory learning emerges as an important capability of systems designed for close interaction with human users. Many generic white-box predictive model types are readily available and potentially appropriate for the task (decision trees, association rules, sub-spaci...

Data compression trade-offs in sensor networks

This paper first discusses the need for data compression within sensor networks and argues that data compression is a fundamental tool for achieving trade-offs in sensor networks among three important sensor network parameters: energy-efficiency, accuracy, and latency. Next, it discusses how to use Fisher information to design data compression algorithms that address the trade-offs inherent in ...

Iterative Concept Learning from Noisy Data Iterative Concept Learning from Noisy Data

In the present paper, we study iterative learning of indexable concept classes from noisy data. We distinguish between learning from positive data only and learning from positive and negative data; synonymously, learning from text and informant, respectively. Following 20], a noisy text (a noisy informant) for some target concept contains every correct data item innnitely often while in additio...