# Multi-Task Dynamical Systems

arXiv: https://arxiv.org/abs/2210.04023 · HTML: https://mlsanity.com/paper/2210.04023/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 102 references that are in the map.
- First posted on arXiv 8 Oct 2022.

## Builds on (most cited first, 30 of 31)

- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks](https://mlsanity.com/paper/1704.04110/) (2017)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [MoCoGAN: Decomposing Motion and Content for Video Generation](https://mlsanity.com/paper/1707.04993/) (2017)
- [Importance Weighted Autoencoders](https://mlsanity.com/paper/1509.00519/) (2015)
- [On human motion prediction using recurrent neural networks](https://mlsanity.com/paper/1705.02445/) (2017)
- [Variational Lossy Autoencoder](https://mlsanity.com/paper/1611.02731/) (2016)
- [Decomposing Motion and Content for Natural Video Sequence Prediction](https://mlsanity.com/paper/1706.08033/) (2017)
- [Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data](https://mlsanity.com/paper/1605.06432/) (2016)
- [Unsupervised Learning of Disentangled Representations from Video](https://mlsanity.com/paper/1705.10915/) (2017)
- [Learning to Decompose and Disentangle Representations for Video Prediction](https://mlsanity.com/paper/1806.04166/) (2018)
- [Disentangled Sequential Autoencoder](https://mlsanity.com/paper/1803.02991/) (2018)
- [QuaterNet: A Quaternion-based Recurrent Model for Human Motion](https://mlsanity.com/paper/1805.06485/) (2018)
- [Variational Sequential Monte Carlo](https://mlsanity.com/paper/1705.11140/) (2017)
- [Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Data](https://mlsanity.com/paper/1709.07902/) (2017)
- [Filtering Variational Objectives](https://mlsanity.com/paper/1705.09279/) (2017)
- [Recurrent Environment Simulators](https://mlsanity.com/paper/1704.02254/) (2017)
- [Learning Human Motion Models for Long-term Predictions](https://mlsanity.com/paper/1704.02827/) (2017)
- [Auto-Encoding Sequential Monte Carlo](https://mlsanity.com/paper/1705.10306/) (2017)
- [Variational Recurrent Auto-Encoders](https://mlsanity.com/paper/1412.6581/) (2014)
- [Z-Forcing: Training Stochastic Recurrent Networks](https://mlsanity.com/paper/1711.05411/) (2017)
- [Personalized Risk Scoring for Critical Care Prognosis using Mixtures of Gaussian Processes](https://mlsanity.com/paper/1610.08853/) (2016)
- [Disentangled State Space Representations](https://mlsanity.com/paper/1906.03255/) (2019)
- [A Framework for Individualizing Predictions of Disease Trajectories by Exploiting Multi-Resolution Structure](https://mlsanity.com/paper/1601.04674/) (2016)
- [Patient-Specific Effects of Medication Using Latent Force Models with Gaussian Processes](https://mlsanity.com/paper/1906.00226/) (2019)
- [Treatment-Response Models for Counterfactual Reasoning with Continuous-time, Continuous-valued Interventions](https://mlsanity.com/paper/1704.02038/) (2017)
- [Clustering Time Series with Nonlinear Dynamics: A Bayesian Non-Parametric and Particle-Based Approach](https://mlsanity.com/paper/1810.09920/) (2018)
- [Multi-Task Time Series Analysis applied to Drug Response Modelling](https://mlsanity.com/paper/1903.08970/) (2019)
- [Input-Output Non-Linear Dynamical Systems applied to Physiological Condition Monitoring](https://mlsanity.com/paper/1608.00242/) (2016)

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

- [Reconciling Shared versus Context-Specific Information in a Neural Network Model of Latent Causes](https://mlsanity.com/paper/2312.08519/) (2023)

## Abstract (arXiv)

Time series datasets are often composed of a variety of sequences from the same domain, but from different entities, such as individuals, products, or organizations. We are interested in how time series models can be specialized to individual sequences (capturing the specific characteristics) while still retaining statistical power by sharing commonalities across the sequences. This paper describes the multi-task dynamical system (MTDS); a general methodology for extending multi-task learning (MTL) to time series models. Our approach endows dynamical systems with a set of hierarchical latent variables which can modulate all model parameters. To our knowledge, this is a novel development of MTL, and applies to time series both with and without control inputs. We apply the MTDS to motion-capture data of people walking in various styles using a multi-task recurrent neural network (RNN), and to patient drug-response data using a multi-task pharmacodynamic model.