More Like this

1. PHYSICS-INFORMED NEURAL NETWORKS FOR INFORMED VACCINE DISTRIBUTION INMETA-POPULATIONS

   https://doi.org/10.1615/JMachLearnModelComput.2023047642  

   Arulandu, Alvan Caleb; Seshaiyer, Padmanabhan (January 2023, Journal of Machine Learning for Modeling and Computing)

   Accurate numerical and physical models play an important role in modeling the spread of infectious disease as well as informing policy decisions. Vaccination programs rely on the estimation of disease parameters from limited, error-prone reported data. Using physics-informed neural networks (PINNs) as universal function approximators of the susceptible-infected-recovered (SIR) compartmentalized differential equation model, we create a data-driven framework that uses reported data to estimate disease spread and approximate corresponding disease parameters. We apply this to datafrom a London boarding school, demonstrating the framework's ability to produce accurate disease and parameter estimations despite noisy data. However, real-world populations contain sub-populations, each exhibiting different levels of risk and activity. Thus, we expand our framework to model meta-populations of preferentially-mixed subgroups with various contact rates, introducing a new substitution to decrease the number of parameters. Optimal parameters are estimated throughPINNs which are then used in a negative gradient approach to calculate an optimal vaccine distribution plan for informed policy decisions. We also manipulate a new hyperparameter in the loss function of the PINNs network to expedite training. Together, our work creates a data-driven tool for future infectious disease vaccination efforts in heterogeneously mixed populations. 

   more » « less
2. Community informed experimental design

   https://doi.org/10.1007/s10260-022-00679-6  

   Mathews, Heather; Volfovsky, Alexander (January 2023, Statistical Methods & Applications)
3. Hessian Informed Mirror Descent

   https://doi.org/10.1007/s10915-022-01933-5  

   Wang, Li; Yan, Ming (September 2022, Journal of Scientific Computing)
4. Learning Task Informed Abstractions

   Fu, Xiang; Yang, Ge; Agrawal, Pulkit; Jaakkola, Tommi (January 2021, Proceedings of the 38th International Conference on Machine Learning)

   null (Ed.)

   Current model-based reinforcement learning methods struggle when operating from complex visual scenes due to their inability to prioritize task-relevant features. To mitigate this prob- lem, we propose learning Task Informed Ab- stractions (TIA) that explicitly separates reward- correlated visual features from distractors. For learning TIA, we introduce the formalism of Task Informed MDP (TiMDP) that is realized by train- ing two models that learn visual features via coop- erative reconstruction, but one model is adversari- ally dissociated from the reward signal. Empirical evaluation shows that TIA leads to significant per- formance gains over state-of-the-art methods on many visual control tasks where natural and un- constrained visual distractions pose a formidable challenge. Project page: https://xiangfu.co/tia 

   more » « less
5. Learning Task Informed Abstractions

   Fu, Xiang; Yang, Ge; Agrawal, Pulkit; Jaakkola, Tommi (July 2021, Proceedings of the 38 th International Conference on Machine Learning)