Title:
Learning Tree Models in Noise: Exact Asymptotics and Robust Algorithms
Learning Tree Models in Noise: Exact Asymptotics and Robust Algorithms
dc.contributor.author | Tan, Vincent Y. F. | |
dc.contributor.corporatename | Georgia Institute of Technology. Machine Learning | en_US |
dc.contributor.corporatename | National University of Singapore. Dept. of Electrical and Computer Engineering | en_US |
dc.date.accessioned | 2021-02-22T16:28:46Z | |
dc.date.available | 2021-02-22T16:28:46Z | |
dc.date.issued | 2021-02-10 | |
dc.description | Presented online on February 10, 2021 at 12:15 p.m. | en_US |
dc.description | Vincent Y. F. Tan is an Assistant Professor in the Department of Electrical and Computer Engineering (ECE) and the Department of Mathematics at the National University of Singapore (NUS). His research interests include information theory, machine learning and statistical signal processing. | |
dc.description | Runtime: 54:22 minutes | |
dc.description.abstract | We consider the classical problem of learning tree-structured graphical models but with the twist that the observations are corrupted in independent noise. For the case in which the noise is identically distributed, we derive the exact asymptotics via the use of probabilistic tools from the theory of strong large deviations. Our results strictly improve those of Bresler and Karzand (2020) and Nikolakakis et al. (2019) and demonstrate keen agreement with experimental results for sample sizes as small as that in the hundreds. When the noise is non-identically distributed, Katiyar et al. (2020) showed that although the exact tree structure cannot be recovered, one can recover a "partial" tree structure; that is, one that belongs to the equivalence class containing the true tree. We propose Symmetrized Geometric Averaging (SGA), a statistically robust algorithm for partial tree recovery. We provide error exponent analyses and extensive numerical results on a variety of trees to show that the sample complexity of SGA is significantly better than the algorithm of Katiyar et al. (2020). SGA can be readily extended to Gaussian models and is shown via numerical experiments to be similarly superior. | en_US |
dc.format.extent | 54:22 minutes | |
dc.identifier.uri | http://hdl.handle.net/1853/64282 | |
dc.language.iso | en_US | en_US |
dc.relation.ispartofseries | Machine Learning @ Georgia Tech (ML@GT) Seminar Series | |
dc.subject | Graphical models | en_US |
dc.subject | Noisy samples | en_US |
dc.title | Learning Tree Models in Noise: Exact Asymptotics and Robust Algorithms | en_US |
dc.type | Moving Image | |
dc.type.genre | Lecture | |
dspace.entity.type | Publication | |
local.contributor.corporatename | Machine Learning Center | |
local.contributor.corporatename | College of Computing | |
local.relation.ispartofseries | ML@GT Seminar Series | |
relation.isOrgUnitOfPublication | 46450b94-7ae8-4849-a910-5ae38611c691 | |
relation.isOrgUnitOfPublication | c8892b3c-8db6-4b7b-a33a-1b67f7db2021 | |
relation.isSeriesOfPublication | 9fb2e77c-08ff-46d7-b903-747cf7406244 |
Files
Original bundle
1 - 4 of 4
No Thumbnail Available
- Name:
- tan.mp4
- Size:
- 216.35 MB
- Format:
- MP4 Video file
- Description:
- Download Video
No Thumbnail Available
- Name:
- tan_videostream.html
- Size:
- 1.32 KB
- Format:
- Hypertext Markup Language
- Description:
- Streaming Video
No Thumbnail Available
- Name:
- transcript.txt
- Size:
- 44.82 KB
- Format:
- Plain Text
- Description:
- Transcription
- Name:
- thumbnail.jpg
- Size:
- 66.21 KB
- Format:
- Joint Photographic Experts Group/JPEG File Interchange Format (JFIF)
- Description:
- Thumbnail
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 3.13 KB
- Format:
- Item-specific license agreed upon to submission
- Description: