# Joint Training Deep Boltzmann Machines for Classification

arXiv: https://arxiv.org/abs/1301.3568 · HTML: https://mlsanity.com/paper/1301.3568/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jan 2013.

## Built on by (most cited first, 2 of 2)

- [Training Deep Boltzmann Networks with Sparse Ising Machines](https://mlsanity.com/paper/2303.10728/) (2023)
- [Mode-Assisted Joint Training of Deep Boltzmann Machines](https://mlsanity.com/paper/2102.08562/) (2021)

## Abstract (arXiv)

We introduce a new method for training deep Boltzmann machines jointly. Prior methods of training DBMs require an initial learning pass that trains the model greedily, one layer at a time, or do not perform well on classification tasks. In our approach, we train all layers of the DBM simultaneously, using a novel training procedure called multi-prediction training. The resulting model can either be interpreted as a single generative model trained to maximize a variational approximation to the generalized pseudolikelihood, or as a family of recurrent networks that share parameters and may be approximately averaged together using a novel technique we call the multi-inference trick. We show that our approach performs competitively for classification and outperforms previous methods in terms of accuracy of approximate inference and classification with missing inputs.