chop
chop copied to clipboard
openopt
CHOP: An optimization library based on PyTorch, with applications to adversarial examples and structured neural network training.
Math isn't well rendered in the documentation. For instance: http://openo.pt/chop/generated/chop.constraints.html#module-chop.constraints.
`@chop.utils.closure` is used to batch problems for deterministic optimizers and is not required for stochastic optimizers, but it would be useful to output a warning if `@chop.utils.closure` is accidentally used...
Cf https://arxiv.org/abs/2008.02883
... to specify which dimensions are batch dims, and which are data dims.
We'd like to have a tensor LMO for tensor nuclear norm constraints. Therefore, an implementation of https://hal.archives-ouvertes.fr/hal-01385538/file/SeROAP_final.pdf (or some other rank 1 tensor decomposition algorithm) would be nice. Our NuclearNormBall.lmo...
Stochastic version of PR #52
- [ ] Universal Adv Examples doesn't need to run on the full CIFAR 10 dataset - [ ] Remove dependency to ImageNet -- find a small but high resoluton...