Blog

2020

• Dynamical Systems and a Suitably Abstract View of Autoregressive Transformers

  December 8 - 19 minute read

• Autoregressive Transformers and Lessons From Enactivism

  December 6 - 21 minute read

2018

• Fine-tuned Noise

  April 18 - 9 minute read

• Meta-Learning and Optimization

  February 19 - 11 minute read

2017

• First-order Methods Almost Always Avoid Saddle Points

  November 17 - 14 minute read