An Efficient Algorithm For Generalized Linear Bandit: Online Stochastic Gradient Descent and Thompson Sampling.
Qin DingCho-Jui HsiehJames SharpnackPublished in: CoRR (2020)
Keyphrases
- stochastic gradient descent
- online algorithms
- learning algorithm
- similarity measure
- k means
- expectation maximization
- monte carlo
- worst case
- generalized linear
- convergence rate
- kalman filter
- least squares
- cost function
- markov chain
- support vector machine svm
- parameter estimation
- sample size
- probabilistic model
- high dimensional
- random sampling
- face recognition
- image sequences
- machine learning