DBScholar

Back to papers

Streaming Anomaly Detection Using Randomized Matrix Sketching

Summary: One-pass, bounded-storage anomaly detection for massive streams via randomized matrix sketching that maintains an orthogonal low-rank basis. Reconstruction-error tests approximate costly global SVD updates, with randomized low-rank acceleration and strong empirical scalability. (summarized by gpt-5.6-luna on Jul 24 2026)

Paper ID
11500
Venue
VLDB
Year
2016
Pagerank
6.0324341e-05
Overall Rank
5,946 | 59.21%
DOI
10.14778/2850583.2850593

Incoming Non-self Citations Over Time

Authors

BibTeX Citation

@article{huang_vldb16,
        title = {{Streaming Anomaly Detection Using Randomized Matrix Sketching}},
        author = {Huang, Hao and Kasiviswanathan, Shiva Prasad},
        journal = {PVLDB},
        series = {{VLDB} '16},
        volume = {9},
        number = {3},
        pages = {192},
        doi = {10.14778/2850583.2850593},
        url = {https://doi.org/10.14778/2850583.2850593},
        year = {2016}
}

Incoming Citations (Sorted by Pagerank)

Showing 3 of 3 citing papers.

Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 2 of 2 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank Cited Paper Year Venue Pagerank
142 LOF: Identifying Density-Based Local Outliers 2000 SIGMOD 0.0002962566
1,252 Streaming Pattern Discovery in Multiple Time-Series 2005 VLDB 0.00011483752
Previous Page 1 / 1 Next

Semantically Similar Papers