Bayesian Approaches to Distribution Regression

05/11/2017
by   Ho Chung Leon Law, et al.
0

Distribution regression has recently attracted much interest as a generic solution to the problem of supervised learning where labels are available at the group level, rather than at the individual level. Current approaches, however, do not propagate the uncertainty in observations due to sampling variability in the groups. This effectively assumes that small and large groups are estimated equally well, and should have equal weight in the final regression. We account for this uncertainty with a Bayesian distribution regression formalism, improving the robustness and performance of the model when group sizes vary. We frame our models in a neural network style, allowing for simple MAP inference using backpropagation to learn the parameters, as well as MCMC-based inference which can fully propagate uncertainty. We demonstrate our approach on illustrative toy datasets, as well as on a challenging problem of predicting age from images.

READ FULL TEXT
research
06/27/2019

'In-Between' Uncertainty in Bayesian Neural Networks

We describe a limitation in the expressiveness of the predictive uncerta...
research
12/27/2018

Robustness to Out-of-Distribution Inputs via Task-Aware Generative Uncertainty

Deep learning provides a powerful tool for machine perception when the o...
research
10/28/2021

Selective Regression Under Fairness Criteria

Selective regression allows abstention from prediction if the confidence...
research
05/19/2022

Variational Inference for Bayesian Bridge Regression

We study the implementation of Automatic Differentiation Variational inf...
research
11/29/2018

Uncertainty propagation in neural networks for sparse coding

A novel method to propagate uncertainty through the soft-thresholding no...
research
07/22/2023

A New Bayesian Huberised Regularisation and Beyond

Robust regression has attracted a great amount of attention in the liter...
research
10/26/2020

Learning from Label Proportions by Optimizing Cluster Model Selection

In a supervised learning scenario, we learn a mapping from input to outp...

Please sign up or login with your details

Forgot password? Click here to reset