Learning and optimization in the face of data perturbations
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, May, 2020
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | eng |
| Published: |
Massachusetts Institute of Technology
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/1721.1/127004 |
| _version_ | 1826193353966878720 |
|---|---|
| author | Staib, Matthew James. |
| author2 | Stefanie Jegelka. |
| author_facet | Stefanie Jegelka. Staib, Matthew James. |
| author_sort | Staib, Matthew James. |
| collection | MIT |
| description | Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, May, 2020 |
| first_indexed | 2024-09-23T09:38:04Z |
| format | Thesis |
| id | mit-1721.1/127004 |
| institution | Massachusetts Institute of Technology |
| language | eng |
| last_indexed | 2024-09-23T09:38:04Z |
| publishDate | 2020 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1270042020-09-04T03:38:39Z Learning and optimization in the face of data perturbations Staib, Matthew James. Stefanie Jegelka. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Electrical Engineering and Computer Science. Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, May, 2020 Cataloged from the official PDF of thesis. Includes bibliographical references (pages 145-163). Many problems in the machine learning pipeline boil down to maximizing the expectation of a function over a distribution. This is the classic problem of stochastic optimization. There are two key challenges in solving such stochastic optimization problems: 1) the function is often non-convex, making optimization difficult; 2) the distribution is not known exactly, but may be perturbed adversarially or is otherwise obscured. Each issue is individually so challenging to warrant a substantial accompanying body of work addressing it, but addressing them simultaneously remains difficult. This thesis addresses problems at the intersection of non-convexity and data perturbations. We study the intersection of the two issues along two dual lines of inquiry: first, we build perturbation-aware algorithms with guarantees for non-convex problems; second, we seek to understand how data perturbations can be leveraged to enhance non-convex optimization algorithms. Along the way, we will study new types of data perturbations and seek to understand their connection to generalization. by Matthew James Staib. Ph. D. Ph.D. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science 2020-09-03T17:41:26Z 2020-09-03T17:41:26Z 2020 2020 Thesis https://hdl.handle.net/1721.1/127004 1191230169 eng MIT theses may be protected by copyright. Please reuse MIT thesis content according to the MIT Libraries Permissions Policy, which is available through the URL provided. http://dspace.mit.edu/handle/1721.1/7582 241 pages application/pdf Massachusetts Institute of Technology |
| spellingShingle | Electrical Engineering and Computer Science. Staib, Matthew James. Learning and optimization in the face of data perturbations |
| title | Learning and optimization in the face of data perturbations |
| title_full | Learning and optimization in the face of data perturbations |
| title_fullStr | Learning and optimization in the face of data perturbations |
| title_full_unstemmed | Learning and optimization in the face of data perturbations |
| title_short | Learning and optimization in the face of data perturbations |
| title_sort | learning and optimization in the face of data perturbations |
| topic | Electrical Engineering and Computer Science. |
| url | https://hdl.handle.net/1721.1/127004 |
| work_keys_str_mv | AT staibmatthewjames learningandoptimizationinthefaceofdataperturbations |