Title:
Learning discrete Markov Random Fields with nearly optimal runtime and sample complexity
Learning discrete Markov Random Fields with nearly optimal runtime and sample complexity
| dc.contributor.author | Meka, Raghu | |
| dc.contributor.corporatename | Georgia Institute of Technology. Algorithms, Randomness and Complexity Center | en_US |
| dc.contributor.corporatename | University of California, Los Angeles. Computer Science Dept. | en_US |
| dc.date.accessioned | 2018-05-24T18:47:33Z | |
| dc.date.available | 2018-05-24T18:47:33Z | |
| dc.date.issued | 2018-05-17 | |
| dc.description | Presented as part of the Workshop on Algorithms and Randomness on May 17, 2018 at 11:30 a.m. in the Klaus Advanced Computing Building, Room 1116. | en_US |
| dc.description | Raghu Meka is an Associate Professor in the Computer Science Department at the University of California, Los Angeles. He is broadly interested in complexity theory, learning and probability theory. | en_US |
| dc.description | Runtime: 47:20 minutes | en_US |
| dc.description.abstract | We give an algorithm for learning the structure of an undirected graphical model that has essentially optimal sample complexity and running time. We make no assumptions on the structure of the graphical model. For Ising models, this subsumes and improves on all prior work. For general t-wise MRFs, these are the first results of their kind. Our approach is new and uses a multiplicative-weight update algorithm. Our algorithm-- Sparsitron-- is easy to implement (has only one parameter) and holds in the online setting. It also gives the first provably efficient solution to the problem of learning sparse Generalized Linear Models (GLMs). Joint work with Adam Klivans. | en_US |
| dc.format.extent | 47:20 minutes | |
| dc.identifier.uri | http://hdl.handle.net/1853/59724 | |
| dc.language.iso | en_US | en_US |
| dc.relation.ispartofseries | Workshop on Algorithms and Randomness 2018 | |
| dc.subject | Algorithms | en_US |
| dc.subject | Ising models | en_US |
| dc.subject | Sparsitron | en_US |
| dc.title | Learning discrete Markov Random Fields with nearly optimal runtime and sample complexity | en_US |
| dc.type | Moving Image | |
| dc.type.genre | Lecture | |
| dspace.entity.type | Publication | |
| local.contributor.corporatename | Algorithms and Randomness Center | |
| local.contributor.corporatename | College of Computing | |
| local.relation.ispartofseries | ARC Colloquium | |
| relation.isOrgUnitOfPublication | b53238c2-abff-4a83-89ff-3e7b4e7cba3d | |
| relation.isOrgUnitOfPublication | c8892b3c-8db6-4b7b-a33a-1b67f7db2021 | |
| relation.isSeriesOfPublication | c933e0bc-0cb1-4791-abb4-ed23c5b3be7e |
Files
Original bundle
1 - 3 of 3
No Thumbnail Available
- Name:
- meka.mp4
- Size:
- 380.19 MB
- Format:
- MP4 Video file
- Description:
- Download video
No Thumbnail Available
- Name:
- meka_videostream.html
- Size:
- 1.01 KB
- Format:
- Hypertext Markup Language
- Description:
- Streaming video
No Thumbnail Available
- Name:
- transcription.txt
- Size:
- 36.68 KB
- Format:
- Plain Text
- Description:
- Transcription
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: