Pivotal Auto-Encoder via Self-Normalizing ReLU

TL;DR

This paper introduces a novel auto-encoder architecture based on self-normalizing ReLU that remains effective across varying noise levels, enhancing robustness in real-world denoising applications.

Contribution

It formalizes sparse auto-encoders as a transform learning problem and develops a noise-invariant optimization algorithm inspired by square root lasso.

Findings

Significant improvement in noise robustness over traditional auto-encoders.

The new architecture is computationally efficient and generalizes well to different noise levels.

Experimental validation on denoising tasks shows enhanced stability against noise variations.

Abstract

Sparse auto-encoders are useful for extracting low-dimensional representations from high-dimensional data. However, their performance degrades sharply when the input noise at test time differs from the noise employed during training. This limitation hinders the applicability of auto-encoders in real-world scenarios where the level of noise in the input is unpredictable. In this paper, we formalize single hidden layer sparse auto-encoders as a transform learning problem. Leveraging the transform modeling interpretation, we propose an optimization problem that leads to a predictive model invariant to the noise level at test time. In other words, the same pre-trained model is able to generalize to different noise levels. The proposed optimization algorithm, derived from the square root lasso, is translated into a new, computationally efficient auto-encoding architecture. After proving that our new method is invariant to the noise level, we evaluate our approach by training networks using the proposed architecture for denoising tasks. Our experimental results demonstrate that the trained models yield a significant improvement in stability against varying types of noise compared to commonly used architectures.