Todd Morrill

Maximum Likelihood Exercise 1

1

I think there might be a typo in [exercise 1 for the maximum likelihood chapter](https://d2l.ai/chapter_appendix-mathematics-for-deep-learning/maximum-likelihood.html#exercises). If you work out the calculations as it is, you'll get -1/3 for alpha, which...

initial skorch hyperparam opt implementation

11

Hey guys, I want to get the conversation started on this. I have a v1 implementation of an example using PyTorch + Skorch for a text classification problem. I'm then...

Comments on paper

3

First - nicely done. This must have been a herculean effort to review all of these papers. Here are some ideas: 1. It would be nice to include more information...

## 📚 Documentation @HamidShojanazeri, I'm following your [FSDP example](https://github.com/pytorch/examples/tree/main/distributed/FSDP) and swapped in a bigger model, `google/flan-t5-xxl`, and am a little unclear on what happens when the script starts up. I'm...

Here are a few reactions to your initial post in the series, "Structure." Feel free to disregard these comments if you think they detract from the article. - Is it...

Optax with multiple optimizers

3

Optax has a function [`multi_transform`](https://optax.readthedocs.io/en/latest/api/combining_optimizers.html#optax.multi_transform), which is nice for using multiple optimizers. [See here](https://colab.research.google.com/drive/1-qLk5l09bq1NxZwwbu_yDk4W7da5TnFx?usp=sharing) for a working example. How should Equinox interact with `multi_transform`? Suppose, for instance, I want to...