File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Learning Entangled Single-Sample Distributions via Iterative Trimming
Title | Learning Entangled Single-Sample Distributions via Iterative Trimming |
---|---|
Authors | |
Issue Date | 2020 |
Citation | Proceedings of Machine Learning Research, 2020, v. 108, p. 2666-2676 How to Cite? |
Abstract | In the setting of entangled single-sample distributions, the goal is to estimate some common parameter shared by a family of distributions, given one single sample from each distribution. We study mean estimation and linear regression under general conditions, and analyze a simple and computationally efficient method based on iteratively trimming samples and re-estimating the parameter on the trimmed sample set. We show that the method in logarithmic iterations outputs an estimation whose error only depends on the noise level of the dαne-th noisiest data point where α is a constant and n is the sample size. This means it can tolerate a constant fraction of high-noise points. These are the first such results under our general conditions with computationally efficient estimators. It also justifies the wide application and empirical success of iterative trimming in practice. Our theoretical results are complemented by experiments on synthetic data. |
Persistent Identifier | http://hdl.handle.net/10722/341406 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yuan, Hui | - |
dc.contributor.author | Liang, Yingyu | - |
dc.date.accessioned | 2024-03-13T08:42:34Z | - |
dc.date.available | 2024-03-13T08:42:34Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | Proceedings of Machine Learning Research, 2020, v. 108, p. 2666-2676 | - |
dc.identifier.uri | http://hdl.handle.net/10722/341406 | - |
dc.description.abstract | In the setting of entangled single-sample distributions, the goal is to estimate some common parameter shared by a family of distributions, given one single sample from each distribution. We study mean estimation and linear regression under general conditions, and analyze a simple and computationally efficient method based on iteratively trimming samples and re-estimating the parameter on the trimmed sample set. We show that the method in logarithmic iterations outputs an estimation whose error only depends on the noise level of the dαne-th noisiest data point where α is a constant and n is the sample size. This means it can tolerate a constant fraction of high-noise points. These are the first such results under our general conditions with computationally efficient estimators. It also justifies the wide application and empirical success of iterative trimming in practice. Our theoretical results are complemented by experiments on synthetic data. | - |
dc.language | eng | - |
dc.relation.ispartof | Proceedings of Machine Learning Research | - |
dc.title | Learning Entangled Single-Sample Distributions via Iterative Trimming | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.scopus | eid_2-s2.0-85161902415 | - |
dc.identifier.volume | 108 | - |
dc.identifier.spage | 2666 | - |
dc.identifier.epage | 2676 | - |
dc.identifier.eissn | 2640-3498 | - |