We apply Fourier neural operators (FNOs), a state-of-the-art operator
le...
Thompson Sampling (TS) is an efficient method for decision-making under
...
Learning a dynamical system requires stabilizing the unknown dynamics to...
Despite perfectly interpolating the training data, deep neural networks
...
Current state-of-the-art model-based reinforcement learning algorithms u...
Autoregressive exogenous (ARX) systems are the general class of input-ou...
We consider the infinite-horizon, discrete-time full-information control...
Linear time-varying (LTV) systems are widely used for modeling real-worl...
In many computational tasks and dynamical systems, asynchrony and
random...
Stabilizing the unknown dynamics of a control system and minimizing regr...
We study the problem of adaptive control in partially observable linear
...
We study the problem of adaptive control in partially observable linear
...
We study the problem of regret minimization in partially observable line...
Most modern learning problems are highly overparameterized, meaning that...
High-dimensional representations often have a lower dimensional underlyi...