# Humble your Overconfident Networks: Unlearning Overfitting via Sequential Monte Carlo Tempered Deep Ensembles

Source: [Humble your Overconfident Networks: Unlearning Overfitting via Sequential Monte Carlo Tempered Deep Ensembles](<https://www.sota2.com/research/paper/68fa78971e209131cea792b1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:52:53.434Z

Authors: Andrew Millard, Zheng Zhao, Joshua Murphy, Simon Maskell

Published: 2025-05-16T20:10:04.000Z

## Abstract

Sequential Monte Carlo (SMC) methods offer a principled approach to Bayesian uncertainty quantification but are traditionally limited by the need for full-batch gradient evaluations. We introduce a scalable variant by incorporating Stochastic Gradient Hamiltonian Monte Carlo (SGHMC) proposals into SMC, enabling efficient mini-batch based sampling. Our resulting SMCSGHMC algorithm outperforms standard stochastic gradient descent (SGD) and deep ensembles across image classification, out-of-distribution (OOD) detection, and transfer learning tasks. We further show that SMCSGHMC mitigates overfitting and improves calibration, providing a flexible, scalable pathway for converting pretrained neural networks into well-calibrated Bayesian models.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2505.11671>)

[PDF](<https://arxiv.org/pdf/2505.11671.pdf>)