CountSketches, Feature Hashing and the Median of Three
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Documents
- Fulltext
Final published version, 450 KB, PDF document
In this paper, we revisit the classic CountSketch method, which is a sparse, random projection that transforms a (high-dimensional) Euclidean vector v to a vector of dimension (2t - 1)s, where t, s > 0 are integer parameters. It is known that a CountSketch allows estimating coordinates of v with variance bounded by parallel to v parallel to/s. For t > 1, the estimator takes the median of 2t - 1 independent estimates, and the probability that the estimate is off by more than 2 parallel to v parallel to/root s is exponentially small in t. This suggests choosing t to be logarithmic in a desired inverse failure probability. However, implementations of CountSketch often use a small, constant t. Previous work only predicts a constant factor improvement in this setting. Our main contribution is a new analysis of CountSketch, showing an improvement in variance to O(min{parallel to v parallel to, parallel to v parallel to/s}) when t > 1. That is, the variance decreases proportionally to s, asymptotically for large enough s.
Original language | English |
---|---|
Title of host publication | Proceedings of the 38 th International Conference on Machine Learning |
Editors | M Meila, T Zhang |
Publisher | PMLR |
Publication date | 2021 |
Pages | 6011-6020 |
Publication status | Published - 2021 |
Event | 38th International Conference on Machine Learning (ICML) - Virtual Duration: 18 Jul 2021 → 24 Jul 2021 |
Conference
Conference | 38th International Conference on Machine Learning (ICML) |
---|---|
By | Virtual |
Periode | 18/07/2021 → 24/07/2021 |
Series | Proceedings of Machine Learning Research |
---|---|
Volume | 139 |
ISSN | 2640-3498 |
Links
- https://proceedings.mlr.press/v139/
Final published version
ID: 301135523