Exploring Machine Learning Privacy/Utility Trade-Off from a Hyperparameters Lens.
Ayoub ArousAmira GuesmiMuhammad Abdullah HanifIhsen AlouaniMuhammad ShafiquePublished in: IJCNN (2023)
Keyphrases
- high dimensional data
- hyperparameters
- trade off
- machine learning
- model selection
- missing values
- differential privacy
- cross validation
- bayesian inference
- closed form
- random sampling
- bayesian framework
- prior information
- incomplete data
- support vector
- data sets
- gaussian process
- sample size
- data points
- em algorithm
- maximum a posteriori
- noise level
- incremental learning
- privacy preserving
- maximum likelihood
- active learning
- gaussian processes
- machine learning methods
- learning algorithm
- supervised learning
- support vector machine
- feature selection
- parameter space
- grid search
- machine learning algorithms
- data mining
- worst case
- decision trees
- computer vision
- parameter settings
- error rate
- expectation maximization
- markov random field
- reinforcement learning
- gaussian process regression