Title:
What 2-layer neural nets can we optimize?
What 2-layer neural nets can we optimize?
dc.contributor.author | Ge, Rong | |
dc.contributor.corporatename | Georgia Institute of Technology. Algorithms, Randomness and Complexity Center | en_US |
dc.contributor.corporatename | Duke University. Dept. of Computer Science | en_US |
dc.date.accessioned | 2019-11-12T18:41:32Z | |
dc.date.available | 2019-11-12T18:41:32Z | |
dc.date.issued | 2019-10-28 | |
dc.description | Presented on October 28, 2019 at 11:00 a.m. in the Klaus Advanced Computing Building, Room 1116E. | en_US |
dc.description | Rong Ge is an assistant professor at the Computer Science Department of Duke University. He is broadly interested in theoretical computer science and machine learning. | en_US |
dc.description | Runtime: 55:49 minutes | en_US |
dc.description.abstract | Optimizing neural networks is a highly nonconvex problem, and even optimizing a 2-layer neural network can be challenging. In the recent years many different approaches were proposed to learn 2-layer neural networks under different assumptions. This talk will give a brief survey on these approaches, and discuss some new results using spectral methods and optimization landscape. | en_US |
dc.format.extent | 55:49 minutes | |
dc.identifier.uri | http://hdl.handle.net/1853/62021 | |
dc.language.iso | en_US | en_US |
dc.relation.ispartofseries | Algorithms and Randomness Center (ARC) Colloquium | |
dc.subject | Neural networks | en_US |
dc.subject | Optimization | en_US |
dc.title | What 2-layer neural nets can we optimize? | 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:
- ge.mp4
- Size:
- 448.29 MB
- Format:
- MP4 Video file
- Description:
- Download video
No Thumbnail Available
- Name:
- ge_videostream.html
- Size:
- 1.29 KB
- Format:
- Hypertext Markup Language
- Description:
- Streaming video
- Name:
- thumbnail.jpg
- Size:
- 85.53 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: