Online active learning with linear models
Abstract/Contents
- Abstract
- In this thesis we address online decision making problems where an agent needs to collect optimal training data to fit statistical models. Decisions on whether to request the response of incoming stochastic observations or not must be made on the spot, and, when selected, the outcomes are immediately revealed. In particular, in the first part, we study scenarios where a single linear model is estimated given a limited budget: only k out of the n incoming observations can be labelled. In the second part, we focus on active learning in the presence of several linear models with heterogeneous unknown noise levels. The goal is to estimate all the models equally well. We design algorithms to efficiently solve the problems, extend them to sparse high-dimensional settings, and derive statistical guarantees in all cases. In addition, we validate our algorithms with synthetic and real-world data, where most of our technical assumptions are violated. Finally, we briefly explore active learning in pure exploration settings for reinforcement learning. In this case, an unknown Markov Decision Process needs to be learned under a fixed budget of episodes.
Description
| Type of resource | text |
|---|---|
| Form | electronic; electronic resource; remote |
| Extent | 1 online resource. |
| Publication date | 2017 |
| Issuance | monographic |
| Language | English |
Creators/Contributors
| Associated with | Riquelme, Carlos |
|---|---|
| Associated with | Stanford University, Department of Mathematical and Computational Engineering. |
| Primary advisor | Johari, Ramesh, 1976- |
| Thesis advisor | Johari, Ramesh, 1976- |
| Thesis advisor | Duchi, John |
| Thesis advisor | Ugander, Johan |
| Advisor | Duchi, John |
| Advisor | Ugander, Johan |
Subjects
| Genre | Theses |
|---|
Bibliographic information
| Statement of responsibility | Carlos Riquelme. |
|---|---|
| Note | Submitted to the Department of Mathematical and Computational Engineering. |
| Thesis | Thesis (Ph.D.)--Stanford University, 2017. |
| Location | electronic resource |
Access conditions
- Copyright
- © 2017 by Carlos Riquelme Ruiz
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...