Stochastic Gradient Descent as Approximate Bayesian Inference.
Stephan MandtMatthew D. HoffmanDavid M. BleiPublished in: CoRR (2017)
Keyphrases
- bayesian inference
- stochastic gradient descent
- expectation propagation
- hyperparameters
- least squares
- step size
- loss function
- regularization parameter
- matrix factorization
- probabilistic model
- random forests
- prior information
- markov chain monte carlo
- collaborative filtering
- multiple kernel learning
- online algorithms
- particle filter
- convergence speed
- gaussian process
- density estimation
- importance sampling