Hanxiao Liu

@arunmallya I agree with your points. Several people asked about this, but I haven't got the chance to try it myself. @JaminFong An alternative approach is to further reduce the...

You may follow the official [migration guide](https://pytorch.org/2018/04/22/0_4_0-migration-guide.html) and/or refer to several forks of this repository where people have adapted the code for pytorch 4.0. It's primarily about getting rid of...

You probably need to adjust the hyperparameters for the final evaluation. The default hyperparameters were tuned wrt the provided genotype but are likely suboptimal for the new architectures.

Make sure you've adjusted the strides for all operations, including those in `FactorizedReduce`.

Thanks a lot for the code! I'm running `ptb_final.sh` without any modification (i.e. using the provided RNN cell and hyperparameters). At epoch 1150, the training ppl is 11.83 and the...

Thanks, @hyhieu! I also got similar test-set ppl using the latest code. Interestingly, the corresponding validation ppl is around `67`. Is this also what you have observed in the experiments?

@hyhieu Cool, thanks for the clarifications!

You're right that it can be viewed as the hybrid of DistMult and ComplEx. Let's assume the relational matrix in ANALOGY consists of $a$ real scalars and $b$ 2x2 blocks,...