# Mode-Assisted Joint Training of Deep Boltzmann Machines

arXiv: https://arxiv.org/abs/2102.08562 · HTML: https://mlsanity.com/paper/2102.08562/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 35 references that are in the map.
- First posted on arXiv 17 Feb 2021.

## Builds on (most cited first, 5 of 5)

- [Accelerating Deep Learning with Memcomputing](https://mlsanity.com/paper/1801.00512/) (2018)
- [Memcomputing: Leveraging memory and physics to compute efficiently](https://mlsanity.com/paper/1802.06928/) (2018)
- [Efficient Solution of Boolean Satisfiability Problems with Digital MemComputing](https://mlsanity.com/paper/2011.06551/) (2020)
- [Joint Training Deep Boltzmann Machines for Classification](https://mlsanity.com/paper/1301.3568/) (2013)
- [Mode-Assisted Unsupervised Learning of Restricted Boltzmann Machines](https://mlsanity.com/paper/2001.05559/) (2020)

## Abstract (arXiv)

The deep extension of the restricted Boltzmann machine (RBM), known as the deep Boltzmann machine (DBM), is an expressive family of machine learning models which can serve as compact representations of complex probability distributions. However, jointly training DBMs in the unsupervised setting has proven to be a formidable task. A recent technique we have proposed, called mode-assisted training, has shown great success in improving the unsupervised training of RBMs. Here, we show that the performance gains of the mode-assisted training are even more dramatic for DBMs. In fact, DBMs jointly trained with the mode-assisted algorithm can represent the same data set with orders of magnitude lower number of total parameters compared to state-of-the-art training procedures and even with respect to RBMs, provided a fan-in network topology is also introduced. This substantial saving in number of parameters makes this training method very appealing also for hardware implementations.