Explore >> Select a destination
|
You are here 
|
akosiorek.github.io | ||
| | | | |
jxmo.io
|
|
| | | | | A primer on variational autoencoders (VAEs) culminating in a PyTorch implementation of a VAE with discrete latents. | |
| | | | |
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. | |
| | | | |
tiao.io
|
|
| | | | | An in-depth practical guide to variational encoders from a probabilistic perspective. | |
| | | | |
www.nicktasios.nl
|
|
| | | In the Latent Diffusion Series of blog posts, I'm going through all components needed to train a latent diffusion model to generate random digits from the MNIST dataset. In this first post, we will tr | ||
