Wu Lin
Wu Lin
@lisitsyn @karlnapf paper at ICRL 2015: http://arxiv.org/abs/1412.6623
At default, inference methods in GP module will compute gradients wrt model parameters, which is not always necessary. - offer users an option to ask inference methods do not compute...
I will do most of the following things in the order. - Sparse inference (batch update) - Stochastic inference (online/streaming update) - GPU related stuff - deep GP - Inference...
Most of methods in the list will be implemented in the order. - inference for Sparse Gaussian process regression (based on JMLR 2005 "A unifying view of sparse approximate Gaussian...
@bayerj The `152-th` line of `rmsprop.py` ``` self.moving_mean_squared = 1 ``` I think the initial value should be `0` instead of `1`. Any reason why `1` is better than `0`
The Kronecker approximation depends on a NN architecture. We should support important GNN layers such as the [`GCNConv` layer](https://pytorch-geometric.readthedocs.io/en/latest/modules/nn.html#convolutional-layers). A reference Kronecker approximation for the GCNConv can be found at...