*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Title: Feedback Coding for Efficient Interactive Machine Learning
Committee:
Dr. Chris Rozell, ECE, Char , Advisor
Dr. Mark Davenport, ECE
Dr. Matthieu Bloch, ECE
Dr. Robert Nowak, University of Wisconsin-Madison
Dr. Yao Xie, ISyE
Abstract: When training machine learning systems, the most basic scenario consists of the learning algorithm operating on a fixed batch of data, provided in its entirety before training. However, there are a large number of applications where there lies a choice in which data points are selected for labeling, and where this choice can be made “on the fly” after each selected data point is labeled. In such interactive machine learning (IML) systems, it is possible to train a model with far fewer labels than would be required with random sampling. In this thesis, we identify and model query structures in IML to develop direct information maximization solutions as well as approximations that allow for computationally efficient query selection. To do so, we frame IML as a feedback communications problem and directly apply principles and tools from coding theory to design and analyze new interaction selection algorithms. First, we directly apply a recently developed feedback coding scheme to sequential human-computer interaction systems. We then identify simplifying query structures to develop approximate methods for efficient, informative query selection in interactive ordinal embedding construction and preference learning systems. Finally, we combine the direct application of feedback coding with approximate information maximization to design and analyze a general active learning algorithm, which we study in detail for logistic regression.
