Deep Generative Models for Molecular Simulation

  • * Register (or log in) to the Neural Network to add this session to your agenda or watch the replay

  • Date
    2 October 2024
    Timeframe
    17:00 - 18:30 CEST Geneva
    Duration
    90 minutes (including 30 minutes networking)
    Share this session

    This session will explore advanced methods in deep generative modeling for molecular simulations, focusing on a novel approach to improve the accuracy and efficiency of normalizing flows in approximating complex target distributions, such as Boltzmann  distributions of physical systems. Traditional methods for training flows often struggle with mode-seeking behavior, use samples from the target generated beforehand by expensive MCMC methods, or use stochastic losses that have high variance. reliance on costly MCMC-generated samples, or high-variance stochastic losses.  

    We will introduce Flow AIS Bootstrap (FAB), a new technique that integrates annealed importance sampling (AIS) to overcome these limitations. By minimizing the mass-covering α-divergence with α=2, FAB reduces importance weight variance and generates samples in regions where the flow poorly approximates the target, aiding in the discovery of new modes.  

    The session will highlight how FAB accurately approximates multimodal targets, outperforming previous methods. To the best of our knowledge, we are the first to learn the Boltzmann distribution of the alanine dipeptide molecule using only the unnormalized target density, without access to samples generated via Molecular Dynamics (MD) simulations: FAB produces better results than training via maximum likelihood on MD samples while using 100 times fewer target evaluations. After reweighting the samples, we obtain unbiased histograms of dihedral angles that are almost identical to the ground truth.

  • Share this session
    Discover more from programme stream
    Remote sensing and machine learning for environmental monitoring: Opportunities and...

    Remote sensing and machine learning for environmental monitoring: Opportunities and...

    26 February 2025 - 17:00 to 18:00

    Adapting machine learning for atmosphere-biosphere coupling in earth system models

    Adapting machine learning for atmosphere-biosphere coupling in earth system models

    12 February 2025 - 17:00 to 18:00

    Advancing earth observation and climate research through self-supervised learning: from...

    Advancing earth observation and climate research through self-supervised learning: from...

    29 January 2025 - 17:00 to 18:00

    Causality in Dynamical systems

    Causality in Dynamical systems

    27 January 2025 - 16:00 to 17:00

    How deep learning improves weather forecasts and reduces energy demands

    How deep learning improves weather forecasts and reduces energy demands

    15 January 2025 - 17:00 to 18:00

    Are you sure you want to remove this speaker?