Equivariant Conditional Neural Processes

11/25/2020
by   Peter Holderrieth, et al.
10

We introduce Equivariant Conditional Neural Processes (EquivCNPs), a new member of the Neural Process family that models vector-valued data in an equivariant manner with respect to isometries of ℝ^n. In addition, we look at multi-dimensional Gaussian Processes (GPs) under the perspective of equivariance and find the sufficient and necessary constraints to ensure a GP over ℝ^n is equivariant. We test EquivCNPs on the inference of vector fields using Gaussian process samples and real-world weather data. We observe that our model significantly improves the performance of previous models. By imposing equivariance as constraints, the parameter and data efficiency of these models are increased. Moreover, we find that EquivCNPs are more robust against overfitting to local conditions of the training data.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

06/09/2021

GP-ConvCNP: Better Generalization for Convolutional Conditional Neural Processes on Time Series Data

Neural Processes (NPs) are a family of conditional generative models tha...
02/28/2019

Gaussian Process Modulated Cox Processes under Linear Inequality Constraints

Gaussian process (GP) modulated Cox processes are widely used to model p...
05/27/2021

Deconditional Downscaling with Gaussian Processes

Refining low-resolution (LR) spatial fields with high-resolution (HR) in...
02/07/2015

Discriminative training for Convolved Multiple-Output Gaussian processes

Multi-output Gaussian processes (MOGP) are probability distributions ove...
02/13/2014

Gaussian Process Volatility Model

The accurate prediction of time-changing variances is an important task ...
02/22/2018

Identifying Sources and Sinks in the Presence of Multiple Agents with Gaussian Process Vector Calculus

In systems of multiple agents, identifying the cause of observed agent d...
02/25/2018

Conditionally Independent Multiresolution Gaussian Processes

We propose a multiresolution Gaussian process (GP) model which assumes c...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.