# Adaptive Latent Space Tuning for Non-Stationary Distributions

arXiv: https://arxiv.org/abs/2105.03584 · HTML: https://mlsanity.com/paper/2105.03584/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 89 references that are in the map.
- First posted on arXiv 8 May 2021.

## Builds on (most cited first, 17 of 17)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems](https://mlsanity.com/paper/1603.04467/) (2016)
- [Deep Neural Networks as Gaussian Processes](https://mlsanity.com/paper/1711.00165/) (2017)
- [Deep learning for universal linear embeddings of nonlinear dynamics](https://mlsanity.com/paper/1712.09707/) (2017)
- [AdapterHub: A Framework for Adapting Transformers](https://mlsanity.com/paper/2007.07779/) (2020)
- [Machine Learning for Fluid Mechanics](https://mlsanity.com/paper/1905.11075/) (2019)
- [Caffe: Convolutional Architecture for Fast Feature Embedding](https://mlsanity.com/paper/1408.5093/) (2014)
- [Theano: A Python framework for fast computation of mathematical expressions](https://mlsanity.com/paper/1605.02688/) (2016)
- [Machine learning meets network science: dimensionality reduction for fast and efficient embedding of networks in the hyperbolic space](https://mlsanity.com/paper/1602.06522/) (2016)
- [A general-purpose deep learning approach to model time-varying audio effects](https://mlsanity.com/paper/1905.06148/) (2019)
- [Adaptive 3D convolutional neural network-based reconstruction method for 3D coherent diffraction imaging](https://mlsanity.com/paper/2008.10094/) (2020)
- [Complex-valued neural networks for machine learning on non-stationary physical data](https://mlsanity.com/paper/1905.12321/) (2019)
- [Accurate and confident prediction of electron beam longitudinal properties using spectral virtual diagnostics](https://mlsanity.com/paper/2009.12835/) (2020)
- [Extraction of instantaneous frequencies and amplitudes in nonstationary time-series data](https://mlsanity.com/paper/2104.01293/) (2021)
- [Combining Machine Learning and Physics to Understand Glassy Systems](https://mlsanity.com/paper/1709.08015/) (2017)

## Built on by (most cited first, 1 of 1)

- [Adaptive Machine Learning for Time-Varying Systems: Low Dimensional Latent Space Tuning](https://mlsanity.com/paper/2107.06207/) (2021)

## Abstract (arXiv)

Powerful deep learning tools, such as convolutional neural networks (CNN), are able to learn the input-output relationships of large complicated systems directly from data. Encoder-decoder deep CNNs are able to extract features directly from images, mix them with scalar inputs within a general low-dimensional latent space, and then generate new complex 2D outputs which represent complex physical phenomenon. One important challenge faced by deep learning methods is large non-stationary systems whose characteristics change quickly with time for which re-training is not feasible. In this paper we present a method for adaptive tuning of the low-dimensional latent space of deep encoder-decoder style CNNs based on real-time feedback to quickly compensate for unknown and fast distribution shifts. We demonstrate our approach for predicting the properties of a time-varying charged particle beam in a particle accelerator whose components (accelerating electric fields and focusing magnetic fields) are also quickly changing with time.