📰 Paper reading club: recursing gradient descent, proving automatic differentiation

We come together to discuss advances in computer science, ground them down to applications, and see where to the wind is blowing. Read the papers at your own time and come discuss them with us.

1. Provably correct, asymptotically efficient, higher-order reverse-mode automatic differentiation

Reverse-Mode Automatic Differentiation for PyTorch programs? Sounds confusing! Let's start with Simply-Typed Lambda Calculus and Forward-Mode AD, and rederive from there... 😊

Check these slides for a connection with the second topic.

2. Gradient Descent: The Ultimate Optimizer

What if you didn't need to tune hyperparameters because you have AD, GD, and recursion? Stack towers of optimizers and scrap your Adam!

⏱ 19:00-21:00 Friday, 22 December
📍 F0RTHSP4CE, Khorava St, 18
💰 free/donation
🗣 @cad215, @gabrielfallen (🇬🇧/🇷🇺)
👮 @cad215