Emile van Krieken

Results 113 issues of Emile van Krieken

There should be a tutorial on how to walk the stochastic computation graph, given a node. This would allow people to more easily create complex local baselines and critics.

documentation

There should be a good explanation/tutorial on credit assignment, showing the difference when not splitting up different loss functions to allow storchastic to properly assign credit.

documentation

Not sure what this thing is called, but this paper: https://arxiv.org/abs/1806.02867

enhancement

See https://arxiv.org/abs/1807.11143 and http://proceedings.mlr.press/v97/yin19c/yin19c.pdf

enhancement

After training for a while, some methods (at least ScoreFunction with no baseline and LAX) on the normal vae will crash using: ``` /opt/conda/conda-bld/pytorch_1579040055865/work/aten/src/THCUNN/BCECriterion.cu:57: void bce_updateOutput_no_reduce_functor::operator()(const Dtype *, const Dtype...

bug

For advanced users, there should be a storchastic version that does not monkey patch. As a lot of code relies on monkey patched code right now, this could require a...

The generic backwards call that collects all losses and just calls backward on it, is incompatible with the implementation of REBAR. We require computing the gradients with respect to the...

bug

For some reason, `Tensor.backward` is not monkey patched: Putting a `storch.Tensor` as input to `Tensor.backward` crashes.

bug

TorchScript and Storchastic are fundamentally incompatible. Problems - [ ] Monkey patching built-in methods makes TorchScript unable to recognize these methods. Example to reproduce: First import storch, so that monkey...

incompatibility

Write a __iter__ for storch tensors, possibly by iterating over all event dims and properly wrapping everything. Is this allowed? It exposes the length of the torch tensor, but that's...

enhancement