Parameter Estimation in Gaussian Mixture Models with Malicious Noise, without Balanced Mixing Coefficients.
Jing XuJakub MarecekPublished in: Allerton (2018)
Keyphrases
- parameter estimation
- gaussian mixture model
- em algorithm
- malicious noise
- noise tolerant
- maximum likelihood
- expectation maximization
- mixture model
- likelihood function
- maximum likelihood estimation
- generative model
- probability density function
- model selection
- posterior distribution
- least squares
- label noise
- probabilistic model
- covariance matrices
- gaussian distribution
- wavelet coefficients
- noisy data
- parameter estimation algorithm
- feature vectors
- markov random field
- hyperparameters
- unsupervised learning
- image segmentation
- low degree
- clustering algorithm
- feature space
- machine learning
- statistical queries
- decision trees
- high dimensional