A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Jointly estimates flow fields and particle properties from Lagrangian data.
A computer vision approach improves neutral particle detection in particle flow algorithms.
Deep FPF approximates gain function for high-dimensional particle filtering.
We present the particle stochastic approximation EM (PSAEM) algorithm for learning of dynamical systems. The method builds on the EM algorithm, an iterative procedure for maximum likelihood inference in latent variable models. By combining stochastic approximation EM and particle Gibbs with ancestor sampling (PGAS), PS…
The excluded area between a pair of two-dimensional hard particles with given relative orientation is the region in which one particle cannot be located due to the presence of the other particle. The magnitude of the excluded area as a function of the relative particle orientation plays a major role in the determinatio…
This paper studies when particle filtering is efficient for planning in partially observed systems.
We report a statistical analysis of the Island ECN (NASDAQ) order book. We determine the static and dynamic properties of this system, and then analyze them from a physicist's viewpoint using an equivalent particle system obtained by treating orders as massive particles and price as position. We identify the fundamenta…
We consider the combined use of resampling and partial rejection control in sequential Monte Carlo methods, also known as particle filters. While the variance reducing properties of rejection control are known, there has not been (to the best of our knowledge) any work on unbiased estimation of the marginal likelihood …
The Lorentz force equations provide a partial description of the geodesic motion of a charged particle on a four-manifold. Under the hypothesis that Maxwell's equations express symmetry properties of the Ricci tensor, the full electromagnetic connection is determined. From this connection, the fourth equation of the ge…
MPM-ParVI uses particle sampling for variational inference.
The explanation of the photoelectric effect by Einstein and Maxwell's field theory of electromagnetism have motivated De Broglie to make the hypothesis that matter exhibits both waves and particles like-properties. These representations of matter are enlightened by string theory which represents particles with stringli…
We establish geometric properties of Stiefel and Grassmann manifolds which arise in relation to Slater type variational spaces in many-particle Hartree-Fock theory and beyond. In particular, we prove that they are analytic homogeneous spaces and submanifolds of the space of bounded operators on the single-particle Hilb…
SPH-ParVI uses fluid dynamics to sample unknown densities efficiently.
Paper explores SVGD for Bayesian inference, linking deterministic and stochastic dynamics.
Improves SVGD for high-dimensional Bayesian inference by reducing variance collapse.
Improved volatility estimation using SV-PF-RNN.
We provide a bridge between generative modeling in the Machine Learning community and simulated physical processes in High Energy Particle Physics by applying a novel Generative Adversarial Network (GAN) architecture to the production of jet images -- 2D representations of energy depositions from particles interacting …
New particle-based VI algorithm expands function class and improves scalability.
KSD Descent uses KSD to sample from a target distribution efficiently.
Stochastic gradient Markov chain Monte Carlo (SG-MCMC) has been increasingly popular in Bayesian learning due to its ability to deal with large data. A standard SG-MCMC algorithm simulates samples from a discretized-time Markov chain to approximate a target distribution. However, the samples are typically highly correl…
New methods combine MALA and mGRAD for scalable Bayesian inference in high-dimensional state-space models.
New method models dewetting of anisotropic particles using numerical techniques.
There has been recent interest in developing scalable Bayesian sampling methods such as stochastic gradient MCMC (SG-MCMC) and Stein variational gradient descent (SVGD) for big-data analysis. A standard SG-MCMC algorithm simulates samples from a discrete-time Markov chain to approximate a target distribution, thus samp…
Poyiadjis et al. (2011) show how particle methods can be used to estimate both the score and the observed information matrix for state space models. These methods either suffer from a computational cost that is quadratic in the number of particles, or produce estimates whose variance increases quadratically with the am…
TomOpt optimizes muon detector designs using differentiable programming.
We characterize the collective phenomena of a liquid market. By interpreting the behavior of a no-arbitrage N asset market in terms of a particle system scenario, (thermo)dynamical-like properties can be extracted from the asset kinetics. In this scheme the mechanisms of the particle interaction can be widely investiga…
New gradient flows improve high-dimensional sampling.
Neural model predicts object states and physical parameters from visual observations.
ATPF combines PF and EnKF for better inference in complex systems.
Physicists at the Large Hadron Collider (LHC) rely on detailed simulations of particle collisions to build expectations of what experimental data may look like under different theory modeling assumptions. Petabytes of simulated data are needed to develop analysis techniques, though they are expensive to generate using …
Adaptive tuning of latent space for non-stationary data.
Framework preserves emergent physics in non-equilibrium systems from particle trajectories.
FAT-GAN simulates electron-proton scattering without theoretical assumptions.
New sampling-based approach for filtering problems using multiplicative Gaussian functions.
Gaussian-SVGD dynamics converge to Gaussian distributions under certain conditions.
We prove that for any convex globally hyperbolic maximal (GHM) anti-de Sitter (AdS) 3-dimensional space-time with particles (cone singularities of angles less than along time-like curves), the complement of the convex core in admits a unique foliation by constant Gauss curvature surfaces. This extends, and …
New coin sampling method for Bayesian inference without learning rates.
Accelerates sampling from Gibbs distributions using ARWP method.
Proposes methods to include distributional information in MV-SDEs for better modeling of interacting particle systems.
Online VSMC efficiently learns SSM parameters in streaming data.
The precise modeling of subatomic particle interactions and propagation through matter is paramount for the advancement of nuclear and particle physics searches and precision measurements. The most computationally expensive step in the simulation pipeline of a typical experiment at the Large Hadron Collider (LHC) is th…
Study shows polynomial-width neural networks can closely approximate infinite-width networks in polynomial time.
Estimates log-likelihood of interacting particle systems using virtual particles.
Bayesian inference for expensive likelihoods using Langevin Monte Carlo with NF.
The use of sequential Monte Carlo within simulation for path-dependent option pricing is proposed and evaluated. Recently, it was shown that explicit solutions and importance sampling are valuable for efficient simulation of spot price and volatility, especially for purposes of path-dependent option pricing. The result…
Gaussian process state-space models (GP-SSMs) are a very flexible family of models of nonlinear dynamical systems. They comprise a Bayesian nonparametric representation of the dynamics of the system and additional (hyper-)parameters governing the properties of this nonparametric representation. The Bayesian formalism e…
This paper optimizes functions of probability measures using particle gradient descent for displacement convex functions.
New AD methods improve likelihood estimation for partially observed systems.