Gradient Noise Convolution (GNC): Smoothing Loss Function for Distributed Large-Batch SGD.
Kosuke HarukiTaiji SuzukiYohei HamakawaTakeshi TodaRyuji SakaiMasahiro OzawaMitsuhiro KimuraPublished in: CoRR (2019)
Keyphrases
- loss function
- stochastic gradient descent
- pairwise
- support vector
- boosting framework
- noise removal
- risk minimization
- logistic regression
- learning to rank
- empirical risk
- edge detection
- regularization term
- reproducing kernel hilbert space
- diffusion equation
- image processing
- missing data
- noise level
- binary classification
- boosting algorithms
- online algorithms
- active learning