Sequential Learning of Principal Curves: Summarizing Data Streams on the Fly
Keyword(s):
When confronted with massive data streams, summarizing data with dimension reduction methods such as PCA raises theoretical and algorithmic pitfalls. A principal curve acts as a nonlinear generalization of PCA, and the present paper proposes a novel algorithm to automatically and sequentially learn principal curves from data streams. We show that our procedure is supported by regret bounds with optimal sublinear remainder terms. A greedy local search implementation (called slpc, for sequential learning principal curves) that incorporates both sleeping experts and multi-armed bandit ingredients is presented, along with its regret computation and performance on synthetic and real-life data.
Keyword(s):
Keyword(s):
Keyword(s):
2014 ◽
Vol 25
(4)
◽
pp. 233-238
◽
2010 ◽
Vol 57
(2)
◽
pp. 117-125
◽
Keyword(s):
2019 ◽
Keyword(s):