DeepAI AI Chat
Log In Sign Up

Meta-Learning PAC-Bayes Priors in Model Averaging

12/24/2019
by   Huang Yimin, et al.
HUAWEI Technologies Co., Ltd.
0

Nowadays model uncertainty has become one of the most important problems in both academia and industry. In this paper, we mainly consider the scenario in which we have a common model set used for model averaging instead of selecting a single final model via a model selection procedure to account for this model's uncertainty to improve reliability and accuracy of inferences. Here one main challenge is to learn the prior over the model set. To tackle this problem, we propose two data-based algorithms to get proper priors for model averaging. One is for meta-learner, the analysts should use historical similar tasks to extract the information about the prior. The other one is for base-learner, a subsampling method is used to deal with the data step by step. Theoretically, an upper bound of risk for our algorithm is presented to guarantee the performance of the worst situation. In practice, both methods perform well in simulations and real data studies, especially with poor quality data.

READ FULL TEXT

page 1

page 2

page 3

page 4

02/07/2021

PAC-Bayes Bounds for Meta-learning with Data-Dependent Prior

By leveraging experience from previous tasks, meta-learning algorithms c...
05/14/2014

Credal Model Averaging for classification: representing prior ignorance and expert opinions

Bayesian model averaging (BMA) is the state of the art approach for over...
05/28/2018

Model averaging for robust extrapolation in evidence synthesis

Extrapolation from a source to a target, e.g., from adults to children, ...
02/23/2023

Bayes meets Bernstein at the Meta Level: an Analysis of Fast Rates in Meta-Learning with PAC-Bayes

Bernstein's condition is a key assumption that guarantees fast rates in ...
11/14/2022

PAC-Bayesian Meta-Learning: From Theory to Practice

Meta-Learning aims to accelerate the learning on new tasks by acquiring ...
05/27/2021

Model Selection for Production System via Automated Online Experiments

A challenge that machine learning practitioners in the industry face is ...
04/18/2020

Accumulator Bet Selection Through Stochastic Diffusion Search

An accumulator is a bet that presents a rather unique payout structure, ...