Distance-Based Regularisation of Deep Networks for Fine-Tuning

TL;DR

This paper introduces a distance-based regularisation method for fine-tuning deep neural networks, providing theoretical generalisation bounds and demonstrating improved empirical performance over existing methods.

Contribution

It proposes a novel regularisation approach that constrains weight updates during fine-tuning, backed by theoretical bounds and superior empirical results.

Findings

The proposed method achieves better generalisation bounds.

Empirical results show improved fine-tuning performance.

Outperforms state-of-the-art fine-tuning techniques.

Abstract

We investigate approaches to regularisation during fine-tuning of deep neural networks. First we provide a neural network generalisation bound based on Rademacher complexity that uses the distance the weights have moved from their initial values. This bound has no direct dependence on the number of weights and compares favourably to other bounds when applied to convolutional networks. Our bound is highly relevant for fine-tuning, because providing a network with a good initialisation based on transfer learning means that learning can modify the weights less, and hence achieve tighter generalisation. Inspired by this, we develop a simple yet effective fine-tuning algorithm that constrains the hypothesis class to a small sphere centred on the initial pre-trained weights, thus obtaining provably better generalisation performance than conventional transfer learning. Empirical evaluation shows that our algorithm works well, corroborating our theoretical results. It outperforms both state of the art fine-tuning competitors, and penalty-based alternatives that we show do not directly constrain the radius of the search space.