We propose the first learning scheme for functional differential equations (FDEs).FDEs play a fundamental role in physics, mathematics, and optimal control.However, the numerical analysis of FDEs has faced challenges due to its unrealistic computational costs and has been a long standing problem over decades.Thus, numerical approximations of FDEs have been developed, but they often oversimplify the solutions. To tackle these two issues, we propose a hybrid approach combining physics-informed neural networks (PINNs) with the *cylindrical approximation*. The cylindrical approximation expands functions and functional derivatives with an orthonormal basis and transforms FDEs into high-dimensional PDEs. To validate the reliability of the cylindrical approximation for FDE applications, we prove the convergence theorems of approximated functional derivatives and solutions.Then, the derived high-dimensional PDEs are numerically solved with PINNs.Through the capabilities of PINNs, our approach can handle a broader class of functional derivatives more efficiently than conventional discretization-based methods, improving the scalability of the cylindrical approximation.As a proof of concept, we conduct experiments on two FDEs and demonstrate that our model can successfully achieve typical $L^1$ relative error orders of PINNs $\sim 10^{-3}$.Overall, our work provides a strong backbone for physicists, mathematicians, and machine learning experts to analyze previously challenging FDEs, thereby democratizing their numerical analysis, which has received limited attention.

We show that accelerated optimization methods can be seen as particular instances of multi-step integration schemes from numerical analysis, applied to the gradient flow equation. Compared with recent advances in this vein, the differential equation considered here is the basic gradient flow, and we derive a class of multi-step schemes which includes accelerated algorithms, using classical conditions from numerical analysis. Multi-step schemes integrate the differential equation using larger step sizes, which intuitively explains the acceleration phenomenon.

We show that accelerated optimization methods can be seen as particular instances of multi-step integration schemes from numerical analysis, applied to the gradient flow equation. Compared with recent advances in this vein, the differential equation considered here is the basic gradient flow, and we derive a class of multi-step schemes which includes accelerated algorithms, using classical conditions from numerical analysis. Multi-step schemes integrate the differential equation using larger step sizes, which intuitively explains the acceleration phenomenon.

One major concern of AM is the heavier memory overhead compared with the fixed-point iteration.

We propose the first learning scheme for functional differential equations (FDEs).FDEs play a fundamental role in physics, mathematics, and optimal control.However, the numerical analysis of FDEs has faced challenges due to its unrealistic computational costs and has been a long standing problem over decades.Thus, numerical approximations of FDEs have been developed, but they often oversimplify the solutions. To tackle these two issues, we propose a hybrid approach combining physics-informed neural networks (PINNs) with the *cylindrical approximation*. The cylindrical approximation expands functions and functional derivatives with an orthonormal basis and transforms FDEs into high-dimensional PDEs. To validate the reliability of the cylindrical approximation for FDE applications, we prove the convergence theorems of approximated functional derivatives and solutions.Then, the derived high-dimensional PDEs are numerically solved with PINNs.Through the capabilities of PINNs, our approach can handle a broader class of functional derivatives more efficiently than conventional discretization-based methods, improving the scalability of the cylindrical approximation.As a proof of concept, we conduct experiments on two FDEs and demonstrate that our model can successfully achieve typical L 1 relative error orders of PINNs \sim 10 {-3} .Overall, our work provides a strong backbone for physicists, mathematicians, and machine learning experts to analyze previously challenging FDEs, thereby democratizing their numerical analysis, which has received limited attention.

The paper presents several "shadowing" results for gradient descent and the heavy ball method, under several conditions on the objective. In short, the authors provide conditions under which a discrete approximation of an ODE defines a trajectory that "stays close" to the actual trajectory of the ODE. This research is motivated by a by a recent paper by Su, Jordan, and Candes that models Nesterov's method via an ODE: this leads the authors to ask the question of when an ODE solution indeed well approximates a discrete algorithm, which is what would be implemented in practice. Although the interest and motivation is mostly on HB, the bulk of the results presented in the paper are for GD. The paper is well-written overall, and the results are interesting, if somewhat shallow.

In deep learning, the recently introduced state space models utilize HiPPO (High-order Polynomial Projection Operators) memory units to approximate continuous-time trajectories of input functions using ordinary differential equations (ODEs), and these techniques have shown empirical success in capturing long-range dependencies in long input sequences. However, the mathematical foundations of these ODEs, particularly the singular HiPPO-LegS (Legendre Scaled) ODE, and their corresponding numerical discretizations remain unexplored. In this work, we fill this gap by establishing that HiPPO-LegS ODE is well-posed despite its singularity, albeit without the freedom of arbitrary initial conditions, and by establishing convergence of the associated numerical discretization schemes for Riemann-integrable input functions.

Data from the real world is often subject to continuous changes known as concept drift [1, 2, 3]. Such can be caused by seasonal changes, changed demands, aging of sensors, etc. Concept drift not only poses a problem for maintaining high performance in learning models [2, 3] but also plays a crucial role in system monitoring [1]. In the latter case, the detection of concept drift is crucial as it enables the detection of anomalous behavior. Examples include machine malfunctions or failures, network security, environmental changes, and critical infrastructures. This is done by detecting irregular shifts [4, 1, 5]. In these contexts, the ability to robustly detect drift is essential. In addition to problems such as noise and sampling error, which challenge all statistical methods, drift detection faces a special kind of difficulty when the drift follows certain patterns that evade detection. In this work, we study those specific drifts that we will refer to as "drift adversarials". Similar to adversarial attacks, drift adversarials exploit weaknesses in the detection methods, and thus allow significant concept drift to occur without triggering alarms posing major issues for monitoring systems.