Convolutional Conditional Neural Process

Convolutional Conditional Neural Processes (ConvCNPs) are probabilistic models using neural networks to efficiently learn complex relationships from limited data, producing well-calibrated uncertainty estimates. Research focuses on improving their efficiency and accuracy through architectural innovations like spectral convolutions for capturing long-range dependencies and incorporating techniques like meta-learning and differential privacy for enhanced performance and privacy preservation in applications with noisy or sensitive data. These advancements are significant for various fields, enabling more robust and reliable predictions in areas such as environmental modeling, healthcare, and other domains where data scarcity or privacy concerns are paramount.

Papers

August 18, 2024

Convolutional Conditional Neural Processes
Wessel P. Bruinsma
Neural Process Conditional Neural Process Convolutional Neural Process Convolutional Conditional Neural Process

July 1, 2024

Neural Conditional Probability for Inference
Vladimir R. Kostic, Karim Lounici, Gregoire Pacreau, Pietro Novelli, Giacomo Turri, Massimiliano Pontil
Scientific Inference Efficient Inference Conditional Distribution Inference Task Confidence Region Convolutional Conditional Neural Process

June 12, 2024

Noise-Aware Differentially Private Regression via Meta-Learning
Ossi Räisä, Stratis Markou, Matthew Ashman, Wessel P. Bruinsma, Marlon Tobaben, Antti Honkela, Richard E. Turner
Differential Privacy Convolutional Conditional Neural Process

April 19, 2024

Spectral Convolutional Conditional Neural Processes
Peiman Mohseni, Nick Duffield
Direct Convolution Fourier Neural Operator Conditional Neural Process Convolutional Conditional Neural Process

October 30, 2023

Sim2Real for Environmental Neural Processes
Jonas Scholz, Tom R. Andersson, Anna Vaughan, James Requeima, Richard E. Turner
Data Assimilation Neural Process Reanalysis Data Convolutional Conditional Neural Process

March 20, 2023

Memorization Capacity of Neural Networks with Conditional Computation
Erdem Koyuncu
Neural Network Rectified Linear Unit Conditional Network Memorization Capacity Conditional Computation Convolutional Conditional Neural Process

June 17, 2022

Reframed GES with a Neural Conditional Dependence Measure
Xinwei Shen, Shengyu Zhu, Jiji Zhang, Shoubo Hu, Zhitang Chen
Causal Inference Causal Discovery Causal Structure Underlying Causal Convolutional Conditional Neural Process Greedy Equivalence Search