An Efficient, Sparsity-Preserving, Online Algorithm for Data Approximation.
David G. AndersonMing GuPublished in: CoRR (2016)
Keyphrases
- noisy data
- input data
- data sets
- data collection
- error bounds
- computationally efficient
- dynamic programming
- probabilistic model
- data reduction
- training data
- k means
- similarity measure
- data analysis
- preprocessing
- computational cost
- simulated annealing
- data points
- worst case
- database
- segmentation algorithm
- detection algorithm
- synthetic data
- original data
- information loss
- learning algorithm
- synthetic datasets
- np hard
- cost function
- data structure
- computational complexity
- approximation ratio
- decision trees
- expectation maximization
- bayesian networks
- online learning
- objective function
- data mining techniques
- knowledge discovery
- data sources
- optimal solution
- high dimensional