Skip to content
Amol Kelkar
Say hello
All projects

Part of AGI experiments

Quantized Distribution Learning

Learning latent-variable probability distributions directly, as histograms over quantized bins.

Status
archived
Started
2020
Focus
Research
Topics
machine learning, deep learning, research

Can a model learn latent-variable probability distributions directly, instead of assuming a parametric form? The Quantized Distribution Auto-Encoder represents each value as a histogram over quantized bins and learns the distribution end to end. Representing values this way sidesteps the precision-weighting machinery that explicit Gaussian latents require - the spread of the histogram already encodes uncertainty - and it became a recurring building block across the AGI experiments.