Robust Importance Sampling for Error Estimation in the Context of Optimal Bayesian Transfer Learning

09/05/2021
by   Omar Maddouri, et al.
0

Classification has been a major task for building intelligent systems as it enables decision-making under uncertainty. Classifier design aims at building models from training data for representing feature-label distributions–either explicitly or implicitly. In many scientific or clinical settings, training data are typically limited, which makes designing accurate classifiers and evaluating their classification error extremely challenging. While transfer learning (TL) can alleviate this issue by incorporating data from relevant source domains to improve learning in a different target domain, it has received little attention for performance assessment, notably in error estimation. In this paper, we fill this gap by investigating knowledge transferability in the context of classification error estimation within a Bayesian paradigm. We introduce a novel class of Bayesian minimum mean-square error (MMSE) estimators for optimal Bayesian transfer learning (OBTL), which enables rigorous evaluation of classification error under uncertainty in a small-sample setting. Using Monte Carlo importance sampling, we employ the proposed estimator to evaluate the classification accuracy of a broad family of classifiers that span diverse learning capabilities. Experimental results based on both synthetic data as well as real-world RNA sequencing (RNA-seq) data show that our proposed OBTL error estimation scheme clearly outperforms standard error estimators, especially in a small-sample setting, by tapping into the data from other relevant domains.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/02/2018

Optimal Bayesian Transfer Learning

Transfer learning has recently attracted significant research attention,...
research
10/05/2013

Moments and Root-Mean-Square Error of the Bayesian MMSE Estimator of Classification Error in the Gaussian Model

The most important aspect of any classifier is its error rate, because t...
research
09/24/2021

Sample Efficient Model Evaluation

Labelling data is a major practical bottleneck in training and testing c...
research
01/04/2021

Towards Network Traffic Monitoring Using Deep Transfer Learning

Network traffic is growing at an outpaced speed globally. The modern net...
research
10/23/2021

Generalized Resubstitution for Classification Error Estimation

We propose the family of generalized resubstitution classifier error est...
research
10/14/2019

Adaptive Transfer Learning of Multi-View Time Series Classification

Time Series Classification (TSC) has been an important and challenging t...
research
10/03/2022

Efficient Bayes Inference in Neural Networks through Adaptive Importance Sampling

Bayesian neural networks (BNNs) have received an increased interest in t...

Please sign up or login with your details

Forgot password? Click here to reset