christopher-beckham.github.io
AboutBlogHome

Blog

  • (2023-04-15) Vicinal distributions as a statistical view on data augmentation

    An excerpt of my upcoming PhD thesis. I introduce data augmentation through the lens of vicinal distributions, and introduce mixup augmentation as a multi-sample generalisation of it.

  • (2023-03-20) Derivations for score-based generative models

    I write some math detailing the SBGM loss and how it can be simplified. I also demystify the official SBGM repository's implementation of the score matching loss.

  • (2023-01-27) Techniques for label conditioning in Gaussian denoising diffusion models

    I rigorously compare and discuss three recent conditioning techniques for Gaussian DDPMs from a theoretical point of view -- classifier-based guidance, classifier-free guidance, and the conditional ELBO.

  • (2022-09-24) Learning the conditional prior over classes for image diffusion

    My implementation of a conditional diffusion model for speech enhancement, demonstrated for images on the MNIST dataset. Unlike other conditional formulations which use classifier-style guidance, this proposes a conditional variant of the ELBO.

  • (2022-08-02) The obsession with SOTA needs to stop

  • (2022-07-24) Towards a more sane Mac OS user experience, and I am late to the party

  • (2022-07-11) My notes on discrete denoising diffusion models (D3PMs)

    My notes on D3PMs. It includes derivations for the two main equations presented in their work.

  • (2021-08-17) A somewhat mathematical introduction to Gaussian and Laplace autoencoders

  • (2021-06-28) Training GANs the right way

christopher-beckham.github.io

  • christopher-beckham.github.io
  • christopher.beckham(at)mila.quebec
  • christopher-beckham
  • chris_j_beckham

PhD candidate at MILA and Polytechnique Montreal. Interested in self-supervised learning, generative models, few-shot learning, and inverse graphics.