Latest

Wasserstein Convergence of SGMs

Can we establish upper convergence bounds for Score-based Generative Models under Semiconvexity and Discontinuous Gradient conditions? The paper titled “Wasserstein Convergence of Score-based Generative Models under Semiconvexity and Discontinuous Gradients” by Bruno and Sabanis (2025) addresses this question. This article provides the detailed derivation of one of the results from...

Why ensemble models perform better than individual models?

A single model is known to make errors. If we make models that make different errors, the models can complement each other, and the error can be reduced. So, instead of training one model for the given problem, we can train multiple of them. But how do we build models...

Generation using Energy-Based Models

We are given a set of samples from some (unknown) distribution. How can we generate more samples from this unknown distribution? This is a classical problem in generative modelling. This post shows how to solve this problem using energy-based models with Langevin Monte Carlo (LMC) sampling algorithm.