posts tags

Bayesian inference (2) chemistry (1) deep learning (2) diffusion model (1) foundations (2) generative modelling (1) mathematics (1) molecular design (1) normalising flows (1) reinforcement learning (1) theory (3)

  • 24 November 2021 Natural-Gradient Variational Inference 2: ImageNet-scale

    By Siddharth Swaroop
    Having derived a natural-gradient variational inference algorithm, we now turn our attention to scaling it all the way to ImageNet. By borrowing tricks developed for Adam, we can get fast convergence, good performance, and reasonable uncertainties.

  • 21 July 2021 Bayesian Deep Learning via Subnetwork Inference

    By Erik Daxberger, Eric Nalisnick
    Bayesian inference has the potential to address shortcomings of deep neural networks (DNNs) such as poor calibration. However, scaling Bayesian methods to modern DNNs is challenging. This blog post describes subnetwork inference, a method that tackles this issue by doing inference over only a small, carefully selected subset of the DNN weights.

  • 30 April 2021 Reinforcement Learning for 3D Molecular Design

    By Robert Pinsler, Gregor N. C. Simm
    Automating the design of molecules with desirable properties can greatly accelerate the search for novel drugs and materials. However, to make further progress we need to go beyond graph-based approaches. In this blog post, we use ideas from reinforcement learning and quantum chemistry to make a first step towards 3D molecular design.

  • 24 November 2021 Natural-Gradient Variational Inference 2: ImageNet-scale

    By Siddharth Swaroop
    Having derived a natural-gradient variational inference algorithm, we now turn our attention to scaling it all the way to ImageNet. By borrowing tricks developed for Adam, we can get fast convergence, good performance, and reasonable uncertainties.

  • 21 July 2021 Bayesian Deep Learning via Subnetwork Inference

    By Erik Daxberger, Eric Nalisnick
    Bayesian inference has the potential to address shortcomings of deep neural networks (DNNs) such as poor calibration. However, scaling Bayesian methods to modern DNNs is challenging. This blog post describes subnetwork inference, a method that tackles this issue by doing inference over only a small, carefully selected subset of the DNN weights.

  • 20 January 2024 An introduction to Flow Matching

    By Tor Fjelde, Emile Mathieu, Vincent Dutordoir
    Flow matching (FM) is a new generative modelling paradigm which is rapidly gaining popularity in the deep learning community. Flow matching combines aspects from Continuous Normalising Flows (CNFs) and Diffusion Models (DMs), alleviating key issues both methods have. In this blogpost we’ll cover the main ideas and unique properties of FM models starting from the basics.

  • 31 March 2021 What Keeps a Bayesian Awake At Night? Part 2: Night Time

    By Wessel Bruinsma, Andrew Y. K. Foong, Richard E. Turner
    The theory of subjective probability describes ideally consistent behaviour and ought not, therefore, be taken too literally.
    — Leonard Jimmie Savage (1917–1971)

  • 31 March 2021 What Keeps a Bayesian Awake At Night? Part 1: Day Time

    By Wessel Bruinsma, Andrew Y. K. Foong, Richard E. Turner
    The theory of probabilities is at bottom nothing but common sense reduced to calculus; it enables us to appreciate with exactness that which accurate minds feel with a sort of instinct for which ofttimes they are unable to account.
    — Pierre-Simon Laplace (1749–1827)

  • 20 January 2024 An introduction to Flow Matching

    By Tor Fjelde, Emile Mathieu, Vincent Dutordoir
    Flow matching (FM) is a new generative modelling paradigm which is rapidly gaining popularity in the deep learning community. Flow matching combines aspects from Continuous Normalising Flows (CNFs) and Diffusion Models (DMs), alleviating key issues both methods have. In this blogpost we’ll cover the main ideas and unique properties of FM models starting from the basics.

  • 13 April 2021 Natural-Gradient Variational Inference 1: The Maths

    By Siddharth Swaroop
    What does it mean to combine variational inference with natural gradients? Can this scale to neural networks? What kind of approximations do we need to make? We take a detailed look at the mathematical derivations of such algorithms.

  • 30 April 2021 Reinforcement Learning for 3D Molecular Design

    By Robert Pinsler, Gregor N. C. Simm
    Automating the design of molecules with desirable properties can greatly accelerate the search for novel drugs and materials. However, to make further progress we need to go beyond graph-based approaches. In this blog post, we use ideas from reinforcement learning and quantum chemistry to make a first step towards 3D molecular design.

  • 20 January 2024 An introduction to Flow Matching

    By Tor Fjelde, Emile Mathieu, Vincent Dutordoir
    Flow matching (FM) is a new generative modelling paradigm which is rapidly gaining popularity in the deep learning community. Flow matching combines aspects from Continuous Normalising Flows (CNFs) and Diffusion Models (DMs), alleviating key issues both methods have. In this blogpost we’ll cover the main ideas and unique properties of FM models starting from the basics.

  • 30 April 2021 Reinforcement Learning for 3D Molecular Design

    By Robert Pinsler, Gregor N. C. Simm
    Automating the design of molecules with desirable properties can greatly accelerate the search for novel drugs and materials. However, to make further progress we need to go beyond graph-based approaches. In this blog post, we use ideas from reinforcement learning and quantum chemistry to make a first step towards 3D molecular design.

  • 13 April 2021 Natural-Gradient Variational Inference 1: The Maths

    By Siddharth Swaroop
    What does it mean to combine variational inference with natural gradients? Can this scale to neural networks? What kind of approximations do we need to make? We take a detailed look at the mathematical derivations of such algorithms.

  • 31 March 2021 What Keeps a Bayesian Awake At Night? Part 2: Night Time

    By Wessel Bruinsma, Andrew Y. K. Foong, Richard E. Turner
    The theory of subjective probability describes ideally consistent behaviour and ought not, therefore, be taken too literally.
    — Leonard Jimmie Savage (1917–1971)

  • 31 March 2021 What Keeps a Bayesian Awake At Night? Part 1: Day Time

    By Wessel Bruinsma, Andrew Y. K. Foong, Richard E. Turner
    The theory of probabilities is at bottom nothing but common sense reduced to calculus; it enables us to appreciate with exactness that which accurate minds feel with a sort of instinct for which ofttimes they are unable to account.
    — Pierre-Simon Laplace (1749–1827)