Spike-and-Slab Sparse Coding for Unsupervised Feature Discovery

TL;DR

This paper introduces the spike-and-slab sparse coding (S3C) model, a scalable unsupervised feature learning method that leverages GPU-optimized variational inference to improve classification performance on image datasets.

Contribution

The paper develops a GPU-compatible variational inference algorithm for S3C, enabling large-scale training and demonstrating superior classification and transfer learning results.

Findings

Improved supervised learning on CIFAR-10.

State-of-the-art self-taught learning on STL-10.

Won the NIPS 2011 Transfer Learning Challenge.

Abstract

We consider the problem of using a factor model we call {\em spike-and-slab sparse coding} (S3C) to learn features for a classification task. The S3C model resembles both the spike-and-slab RBM and sparse coding. Since exact inference in this model is intractable, we derive a structured variational inference procedure and employ a variational EM training algorithm. Prior work on approximate inference for this model has not prioritized the ability to exploit parallel architectures and scale to enormous problem sizes. We present an inference procedure appropriate for use with GPUs which allows us to dramatically increase both the training set size and the amount of latent factors. We demonstrate that this approach improves upon the supervised learning capabilities of both sparse coding and the ssRBM on the CIFAR-10 dataset. We evaluate our approach's potential for semi-supervised learning on subsets of CIFAR-10. We demonstrate state-of-the art self-taught learning performance on the STL-10 dataset and use our method to win the NIPS 2011 Workshop on Challenges In Learning Hierarchical Models' Transfer Learning Challenge.