Explore >> Select a destination
|
You are here 
|
liorsinai.github.io | ||
| | | | |
jingnanshi.com
|
|
| | | | | Tutorial on automatic differentiation | |
| | | | |
windowsontheory.org
|
|
| | | | | (Updated and expanded 12/17/2021) I am teaching deep learning this week in Harvard's CS 182 (Artificial Intelligence) course. As I'm preparing the back-propagation lecture, Preetum Nakkiran told me about Andrej Karpathy's awesome micrograd package which implements automatic differentiation for scalar variables in very few lines of code. I couldn't resist using this to show how... | |
| | | | |
iclr-blogposts.github.io
|
|
| | | | | The product between the Hessian of a function and a vector, the Hessian-vector product (HVP), is a fundamental quantity to study the variation of a function. It is ubiquitous in traditional optimization and machine learning. However, the computation of HVPs is often considered prohibitive in the context of deep learning, driving practitioners to use proxy quantities to evaluate the loss geometry. Standard automatic differentiation theory predicts that the computational complexity of an HVP is of the same order of magnitude as the complexity of computing a gradient. The goal of this blog post is to provide a practical counterpart to this theoretical result, showing that modern automatic differentiation frameworks, JAX and PyTorch, allow for efficient computation of these HVPs in standard deep learning cost functions. | |
| | | | |
www.paepper.com
|
|
| | | When you have a big data set and a complicated machine learning problem, chances are that training your model takes a couple of days even on a modern GPU. However, it is well-known that the cycle of having a new idea, implementing it and then verifying it should be as quick as possible. This is to ensure that you can efficiently test out new ideas. If you need to wait for a whole week for your training run, this becomes very inefficient. | ||
