Fine-tuning generative models

Deep generative models have emerged as a powerful modeling paradigm for making sense of large amounts of unlabeled real-world data. In particular, the representations produced by these models have proven to be useful both in improving human understanding of the factors of variation in the original dataset and in downstream tasks such as classification. Most current algorithms, however, require training a bespoke model from scratch, which can be both expensive and time-consuming. Instead, we propose various methods of fine-tuning pre-trained generative models to achieve these goals, and evaluate these methods quantitatively on few-shot classification and interpretability tasks.

Name thesis:degree_name

Master

Department dc:contributor.department

Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science

Grantor dc:publisher

Massachusetts Institute of Technology

Year dc:date.issued

2019

Author dc:creator

• Khandelwal, Arjun(Arjun Sunil)

Advisor dc:contributor.advisor

• David Sontag.

• Electrical Engineering and Computer Science.

Statement dc:rights

• MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission.

Licence dc:rights.uri

• http://dspace.mit.edu/handle/1721.1/7582

Language dc:language.iso

eng

Handle dc:identifier.uri

https://hdl.handle.net/1721.1/124252

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/124252