# Machine learning at the mesoscale: a computation-dissipation bottleneck

arXiv: https://arxiv.org/abs/2307.02379 · HTML: https://mlsanity.com/paper/2307.02379/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 70 references that are in the map.
- First posted on arXiv 5 Jul 2023.

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

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Large Associative Memory Problem in Neurobiology and Machine Learning](https://mlsanity.com/paper/2008.06996/) (2020)
- [Satisficing in Time-Sensitive Bandit Learning](https://mlsanity.com/paper/1803.02855/) (2018)
- [A unifying framework for mean-field theories of asymmetric kinetic Ising systems](https://mlsanity.com/paper/2002.04309/) (2020)
- [Correlations and functional connections in a population of grid cells](https://mlsanity.com/paper/1405.0044/) (2014)

## Abstract (arXiv)

The cost of information processing in physical systems calls for a trade-off between performance and energetic expenditure. Here we formulate and study a computation-dissipation bottleneck in mesoscopic systems used as input-output devices. Using both real datasets and synthetic tasks, we show how non-equilibrium leads to enhanced performance. Our framework sheds light on a crucial compromise between information compression, input-output computation and dynamic irreversibility induced by non-reciprocal interactions.