arXiv research

Generalizes PCA and ICA for continuous-time signals using neural networks.

Study on markets with insiders receiving private signals affecting asset prices and information flow.

Transformers can solve complex filtering problems for non-Gaussian signals.

Using integration by parts on Gaussian space we construct a Stein Unbiased Risk Estimator (SURE) for the drift of Gaussian processes using their local and occupation times. By almost-sure minimization of the SURE risk of shrinkage estimators we derive an estimation and de-noising procedure for an input signal perturbed…

Study local expansions of continuous-time processes using Ito signature properties.

Continuous-time mirror descent solves sparse phase retrieval efficiently.

A novel Gaussian process approach for deconvolution of missing data signals.

Study on estimating unstable open-loop matrices from state trajectories.

Neural RDEs extend CDEs to irregular time series.

Framework for continuous-time network data representation learning.

Estimates chirp signal frequencies using probabilistic models.

Zero-Copy Architecture Detects Cross-Company Financial Signals Instantly.

Reinforcement learning for continuous-time risk-sensitive asset allocation

New method for separating mixed signals with nonlinear functions.

Neural ODEs control graph dynamics with low energy feedback.

The study uses response theory to understand RNNs processing input signals.

DTW calculates the similarity or alignment between two signals, subject to temporal warping. However, its computational complexity grows exponentially with the number of time-series. Although there have been algorithms developed that are linear in the number of time-series, they are generally quadratic in time-series l…

We study the statistical properties of the iterates generated by gradient descent, applied to the fundamental problem of least squares regression. We take a continuous-time view, i.e., consider infinitesimal step sizes in gradient descent, in which case the iterates form a trajectory called gradient flow. Our primary f…

This paper extends a Kyle model to include price-responsive traders, revealing new dynamics and equilibria.

Study dynamic equilibrium with insider and general uninformed agent preferences.

Faster policy learning via continuous-time gradients.

Continuous time framework for discrete data denoising models.

This paper studies the equilibrium pricing of asset shares in the presence of dynamic private information. The market consists of a risk-neutral informed agent who observes the firm value, noise traders, and competitive market makers who set share prices using the total order flow as a noisy signal of the insider's inf…

Recent research has shown that performance in signal processing tasks can often be significantly improved by using signal models based on sparse representations, where a signal is approximated using a small number of elements from a fixed dictionary. Unfortunately, inference in this model involves solving non-smooth op…

Paper uses SciPhyRL for optimizing large institutional portfolios.

Develops DPG methods for continuous-time RL with deterministic policies.

First steps towards a mathematical theory of deep convolutional neural networks for feature extraction were made---for the continuous-time case---in Mallat, 2012, and Wiatowski and Bölcskei, 2015. This paper considers the discrete case, introduces new convolutional neural network architectures, and proposes a mathemati…

Study analyzes a new algorithm for complex optimization problems.

Continuous-time algorithms improve online learning performance.

Motion Code models time series dynamics with sparse approximations.

Paper develops a continuous-time framework for financial markets without stochastic calculus.

Stochastic gradient descent in continuous time (SGDCT) provides a computationally efficient method for the statistical learning of continuous-time models, which are widely used in science, engineering, and finance. The SGDCT algorithm follows a (noisy) descent direction along a continuous stream of data. SGDCT performs…

Consider power utility maximization of terminal wealth in a 1-dimensional continuous-time exponential Levy model with finite time horizon. We discretize the model by restricting portfolio adjustments to an equidistant discrete time grid. Under minimal assumptions we prove convergence of the optimal discrete-time strate…

Continuous-time MBRL framework tackles control systems with Bayesian ODEs.

Continuous-time model shows insider trading constraints impact market dynamics.

Continuous-time analysis shows SGD with noise prefers flat minima.

Framework combines random features with CDEs for efficient time-series learning.

This paper proposes a nonparametric Bayesian method for exploratory data analysis and feature construction in continuous time series. Our method focuses on understanding shared features in a set of time series that exhibit significant individual variability. Our method builds on the framework of latent Diricihlet alloc…

New RL framework models continuous-time dynamics using neural ODEs.

Continuous-time SGD converges under certain conditions, useful for deep learning.

Logarithmic regret achieved in continuous-time linear-quadratic reinforcement learning.

A new method for portfolio allocation in continuous-time markets.

Logarithmic regret for continuous-time reinforcement learning.

New SDE model for continuous-time reinforcement learning.

Study shows certainty equivalent policy minimizes regret in continuous-time systems.

VSDN models sporadic time series with neural SDEs.

We consider a family of learning strategies for online optimization problems that evolve in continuous time and we show that they lead to no regret. From a more traditional, discrete-time viewpoint, this continuous-time approach allows us to derive the no-regret properties of a large class of discrete-time algorithms i…

Study a continuous-time PA problem with private effort and consumption decisions.