Kamer Ali Yuksel

Hello, I've implemented a Siamese architecture model for contrastive-learning (by pair-wise ranking of the stock returns). It can be utilized for ranking the models. The accuracy in predicting the sell-offs...

I think an alternative could be first getting eigenvectors or independent components (via Fast ICA), then using meta-map-elites to optimize their weights, rather than optimizing a large portfolio of assets....

I came here as I have suffered the same problem, it doesn't support binary targets. Also, it would be great if it could be calculated simultaneously for a batch of...

@k4ntz It performed better than Mish in my case (also RL-like)

Any tips on how to active? I used kaiming_uniform_ for Linear layers.

@k4ntz I can provide the learning curves using both but I am unable to provide a draft publication yet as it is patent-pending. Thanks for suggesting the initialization function, I...

@k4ntz FYI, my case is an adversarial setting so it is important that it re-adapt itself continuously. Thus, having also adaptable activation functions (besides the network itself) may be good...

@jiangtaoxie GAP is frequently used also in SoA architectures for 1D data, hence I want to try iSQRT-COV.

@jiangtoxie Please check the following issue. It seems possible to get this into PyTorch, maybe if you create a pull request. https://github.com/pytorch/pytorch/issues/17169

I would also investigate how it can help enabling the "Super Convergence": https://arxiv.org/abs/1708.07120