Recent literature has made much progress in understanding online LQR: a modern learning-theoretic take on the classical control problem where a learner attempts to optimally control an unknown linear dynamical system with fully observed state, perturbed by i.i.d.

The spread of many infectious diseases is modeled using variants of the SIR compartmental model, which is a coupled differential equation. The coefficients of the SIR model determine the spread trajectories of disease, on whose basis proactive measures can be taken. Hence, the coefficient estimates must be both fast and accurate. Shaier et al. in the paper "Disease Informed Neural Networks" used Physics Informed Neural Networks (PINNs) to estimate the parameters of the SIR model. There are two drawbacks to this approach. First, the training time for PINNs is high, with certain diseases taking close to 90 hrs to train. Second, PINNs don't generalize for a new SIDR trajectory, and learning its corresponding SIR parameters requires retraining the PINN from scratch. In this work, we aim to eliminate both of these drawbacks. We generate a dataset between the parameters of ODE and the spread trajectories by solving the forward problem for a large distribution of parameters using the LSODA algorithm. We then use a neural network to learn the mapping between spread trajectories and coefficients of SIDR in an offline manner. This allows us to learn the parameters of a new spread trajectory without having to retrain, enabling generalization at test time. We observe a speed-up of 3-4 orders of magnitude with accuracy comparable to that of PINNs for 11 highly infectious diseases. Further finetuning of neural network inferred ODE coefficients using PINN further leads to 2-3 orders improvement of estimated coefficients.

Recent literature has made much progress in understanding \emph{online LQR}: a modern learning-theoretic take on the classical control problem in which a learner attempts to optimally control an unknown linear dynamical system with fully observed state, perturbed by i.i.d. Gaussian noise. It is now understood that the optimal regret on time horizon $T$ against the optimal control law scales as $\widetilde{\Theta}(\sqrt{T})$. In this paper, we show that the same regret rate (against a suitable benchmark) is attainable even in the considerably more general non-stochastic control model, where the system is driven by \emph{arbitrary adversarial} noise (Agarwal et al. 2019). In other words, \emph{stochasticity confers little benefit in online LQR}. We attain the optimal $\widetilde{\mathcal{O}}(\sqrt{T})$ regret when the dynamics are unknown to the learner, and $\mathrm{poly}(\log T)$ regret when known, provided that the cost functions are strongly convex (as in LQR). Our algorithm is based on a novel variant of online Newton step (Hazan et al. 2007), which adapts to the geometry induced by possibly adversarial disturbances, and our analysis hinges on generic "policy regret" bounds for certain structured losses in the OCO-with-memory framework (Anava et al. 2015). Moreover, our results accomodate the full generality of the non-stochastic control setting: adversarially chosen (possibly non-quadratic) costs, partial state observation, and fully adversarial process and observation noise.