Hi I'm Litan. I'm interested in probabilistic machine learning and ML infrastructure.
Below you'll find posts related to things I'm currently learning.

Blog

Basic GPU Architecture

This post introduces basic GPU architecture concepts needed for writing CUDA kernels, such as physical hardware organization, logical organization/the CUDA compute model, and GPU memory hierarchy.

Structure Tensors and Coherence

Structure tensors are used in computer vision to measure the local similarity of gradient directions within a 2D image or 3D volume. These matrices are typically summarized into a scalar metric called the local coherence. Here I show how coherence is closely tied to pixel-wise principal component analysis.

Generative Sampling with Variational Autoencoders

Previously we derived the evidence lower bound (ELBO). The original variational autoencoder paper introduced a differentiable and unbiased estimator for the ELBO, and extends the idea of simple parametric forms to complex ones via feed-forward neural nets. We go through a complete walkthrough of how the VAE model architecture is defined and trained.

Latent Spaces and the ELBO

Derivation and several interpretations of the evidence lower bound (ELBO) used in variational inference.

Useful KL Divergence Results

The KL divergence of distribution $p$ from $q$ is a measure of dissimilarity, taken as the expectation of the log difference over the support of $p$. It's used a lot in Bayesian inference (specifically, the divergence of a posterior $p$ from some prior $q$), so we're listing some properties and closed-form equations here.

About

Cognite, 2024 - Now
Avathon, 2019 - 2024
CognitiveScale, 2018 - 2019
MS Computer Science, UT Austin
MS Petroleum Eng, UT Austin
BS Chemical Eng, UT Austin