Explore >> Select a destination
|
You are here 
|
jingnanshi.com | ||
| | | | |
robotchinwag.com
|
|
| | | | | Deriving the gradients for the backward pass for matrix multiplication using tensor calculus | |
| | | | |
liorsinai.github.io
|
|
| | | | | A series on automatic differentiation in Julia. Part 1 provides an overview and defines explicit chain rules. | |
| | | | |
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 computat... | |
| | | | |
datadan.io
|
|
| | | Linear regression and gradient descent are techniques that form the basis of many other, more complicated, ML/AI techniques (e.g., deep learning models). They are, thus, building blocks that all ML/AI engineers need to understand. | ||
