Constrained Optimization of Nonconvex Problems and its Applications in Fairness in Machine Learning
| dc.contributor.author | Du, Zhuangjin | |
| dc.contributor.chair | Sridharan, Karthik | |
| dc.contributor.committeeMember | Townsend, Alex John | |
| dc.date.accessioned | 2022-01-24T18:06:41Z | |
| dc.date.available | 2022-01-24T18:06:41Z | |
| dc.date.issued | 2021-12 | |
| dc.description | 26 pages | |
| dc.description.abstract | Fairness is an important concern in machine learning. One way to characterize the problem is to minimize some objective function, representing a quantity like loss, under constraints that represent fairness conditions like demographic parity. Previous papers show how a two-player approach to optimizing the Lagrangian can be computationally efficient and provably converge to a good, constraint-satisfying solution on convex objective functions. This work analyzes the convergence of the two-player framework in previous works on nonconvex functions, in particular those that satisfy the PL inequality. | |
| dc.identifier.doi | https://doi.org/10.7298/nk0w-gt37 | |
| dc.identifier.other | Du_cornell_0058O_11340 | |
| dc.identifier.other | http://dissertations.umi.com/cornell:11340 | |
| dc.identifier.uri | https://hdl.handle.net/1813/110792 | |
| dc.language.iso | en | |
| dc.subject | Constrained Optimization | |
| dc.subject | Fairness | |
| dc.subject | Machine Learning | |
| dc.title | Constrained Optimization of Nonconvex Problems and its Applications in Fairness in Machine Learning | |
| dc.type | dissertation or thesis | |
| dcterms.license | https://hdl.handle.net/1813/59810.2 | |
| thesis.degree.discipline | Computer Science | |
| thesis.degree.grantor | Cornell University | |
| thesis.degree.level | Master of Science | |
| thesis.degree.name | M.S., Computer Science |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Du_cornell_0058O_11340.pdf
- Size:
- 253.6 KB
- Format:
- Adobe Portable Document Format