Search Results for author:
Found 13 papers, 10 papers with code
Denoising Diffusion Probabilistic Models in Six Simple Steps
Denoising Diffusion Probabilistic Models (DDPMs) are a very popular class of deep generative model that have been successfully applied to a diverse range of problems including image and video generation, protein and material synthesis, weather forecasting, and neural surrogates of partial differential equations.
Improved motif-scaffolding with SE(3) flow matching
The first is motif amortization, in which FrameFlow is trained with the motif as input using a data augmentation strategy.
Fast protein backbone generation with SE(3) flow matching
We present FrameFlow, a method for fast protein backbone generation using SE(3) flow matching.
Autoregressive Conditional Neural Processes
Our work provides an example of how ideas from neural distribution estimation can benefit neural processes, and motivates research into the AR deployment of other neural process models.
Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamics
Molecular dynamics (MD) simulation is a widely used technique to simulate molecular systems, most commonly at the all-atom resolution where equations of motion are integrated with timesteps on the order of femtoseconds ($1\textrm{fs}=10^{-15}\textrm{s}$).
A Note on the Chernoff Bound for Random Variables in the Unit Interval
The Chernoff bound is a well-known tool for obtaining a high probability bound on the expectation of a Bernoulli random variable in terms of its sample average.
How Tight Can PAC-Bayes be in the Small Data Regime?
Interestingly, this lower bound recovers the Chernoff test set bound if the posterior is equal to the prior.
The Gaussian Neural Process
Neural Processes (NPs; Garnelo et al., 2018a, b) are a rich class of models for meta-learning that map data sets directly to predictive stochastic processes.
Structured Weight Priors for Convolutional Neural Networks
This paper explores the benefits of adding structure to weight priors.
Meta-Learning Stationary Stochastic Process Prediction with Convolutional Neural Processes
Stationary stochastic processes (SPs) are a key component of many probabilistic models, such as those for off-the-grid spatio-temporal data.
Convolutional Conditional Neural Processes
We introduce the Convolutional Conditional Neural Process (ConvCNP), a new member of the Neural Process family that models translation equivariance in the data.
On the Expressiveness of Approximate Inference in Bayesian Neural Networks
While Bayesian neural networks (BNNs) hold the promise of being flexible, well-calibrated statistical models, inference often requires approximations whose consequences are poorly understood.
'In-Between' Uncertainty in Bayesian Neural Networks
We describe a limitation in the expressiveness of the predictive uncertainty estimate given by mean-field variational inference (MFVI), a popular approximate inference method for Bayesian neural networks.
