English
Related papers

Related papers: Exponentially Fading Memory Signature

200 papers

We discuss how to construct reliably well "a lattice and an integer time" version of a super-diffusive continuous-space and -time fractional Brownian motion (fBm) -- an experimentally-relevant non-Markovian Gaussian stochastic process with…

Statistical Mechanics · Physics 2025-06-12 Enzo Marinari , Gleb Oshanin

The performance of deep learning models is critically dependent on sophisticated optimization strategies. While existing optimizers have shown promising results, many rely on first-order Exponential Moving Average (EMA) techniques, which…

Computer Vision and Pattern Recognition · Computer Science 2024-12-10 Roi Peleg , Yair Smadar , Teddy Lazebnik , Assaf Hoogi

This summary of the doctoral thesis provides a comprehensive formulation of the Extended Discrete Fourier Transform (EDFT), derived directly from the Fourier integral and its orthogonality properties. The method is obtained by solving…

Data Structures and Algorithms · Computer Science 2026-01-21 Vilnis Liepins

We derive the semiclassical approximation to Feynman's path integral representation of the energy Green function of a massless particle in the shadow region of an ideal obstacle in a medium. The wavelength of the particle is assumed to be…

Condensed Matter · Physics 2009-11-10 Martin Schaden , Larry Spruch

The endogenous grid method (EGM) accelerates dynamic programming by inverting the Euler equation, but it appears incompatible with Epstein-Zin preferences where the value function enters the Euler equation. This paper shows that a power…

General Economics · Economics 2026-01-09 Alan Lujan

Geometric features, robust to noise, of curves in Euclidean space are of great interest for various applications such as machine learning and image analysis. We apply the Fels-Olver's moving frame method (for geometric features) paired with…

Differential Geometry · Mathematics 2022-06-09 Joscha Diehl , Rosa Preiß , Michael Ruddy , Nikolas Tapia

The signature is a collection of iterated integrals describing the "shape" of a path. It appears naturally in the Taylor expansions of controlled differential equations and, as a consequence, is arguably the central object within rough path…

Numerical Analysis · Mathematics 2025-10-31 James Foster

Exponential-family harmoniums (EFHs), which extend restricted Boltzmann machines (RBMs) from Bernoulli random variables to other exponential families (Welling et al., 2005), are generative models that can be trained with…

Machine Learning · Computer Science 2016-05-20 Joseph G. Makin , Benjamin K. Dichter , Philip N. Sabes

Latent variable models have become instrumental in computational neuroscience for reasoning about neural computation. This has fostered the development of powerful offline algorithms for extracting latent neural trajectories from neural…

Machine Learning · Statistics 2023-05-22 Matthew Dowling , Yuan Zhao , Il Memming Park

Many finance, physics, and engineering phenomena are modeled by continuous-time dynamical systems driven by highly irregular (stochastic) inputs. A powerful tool to perform time series analysis in this context is rooted in rough path theory…

Machine Learning · Computer Science 2023-04-27 Enea Monzio Compagnoni , Anna Scampicchio , Luca Biggio , Antonio Orvieto , Thomas Hofmann , Josef Teichmann

In this paper we complete the analysis begun by two of the authors in a previous work on the discrete quantum walk on the line [J. Phys. A 36:8775-8795 (2003) quant-ph/0303105 ]. We obtain uniformly convergent asymptotics for the…

Quantum Physics · Physics 2009-11-11 Hilary A. Carteret , Bruce Richmond , Nico Temme

Empirical divergence maximization (EDM) refers to a recently proposed strategy for estimating f-divergences and likelihood ratio functions. This paper extends the idea to empirical vector quantization where one seeks to empirically derive…

Information Theory · Computer Science 2015-06-03 Michael A. Lexa

In this work we present different results concerning the signature and the cubature of fractional Brownian motion (fBm). The first result regards the rate of convergence of the expected signature of the linear piecewise approximation of the…

Probability · Mathematics 2017-11-20 Riccardo Passeggeri

Continually learning new classes from a few training examples without forgetting previous old classes demands a flexible architecture with an inevitably growing portion of storage, in which new examples and classes can be incrementally…

We propose \emph{Euler Mean Flows (EMF)}, a flow-based generative framework for one-step and few-step generation that enforces long-range trajectory consistency with minimal sampling cost. The key idea of EMF is to replace the trajectory…

Machine Learning · Computer Science 2026-02-04 Zhiqi Li , Yuchen Sun , Duowen Chen , Jinjin He , Bo Zhu

Factorial hidden Markov models (FHMMs) are powerful tools of modeling sequential data. Learning FHMMs yields a challenging simultaneous model selection issue, i.e., selecting the number of multiple Markov chains and the dimensionality of…

Machine Learning · Statistics 2015-06-29 Shaohua Li , Ryohei Fujimaki , Chunyan Miao

Modern vision generators transport a base distribution to data through time-indexed measures, implemented as deterministic flows (ODEs) or stochastic diffusions (SDEs). Despite strong empirical performance, standard flow-matching objectives…

Machine Learning · Computer Science 2026-02-27 Chika Maduabuchi

In this thesis, we extend the recently introduced theory of stochastic modified equations (SMEs) for stochastic gradient optimization algorithms. In Ch. 3 we study time-inhomogeneous SDEs driven by Brownian motion. For certain SDEs we prove…

Probability · Mathematics 2025-11-26 Stefan Perko

We present a plug-in replacement for batch normalization (BN) called exponential moving average normalization (EMAN), which improves the performance of existing student-teacher based self- and semi-supervised learning techniques. Unlike the…

Machine Learning · Computer Science 2021-06-21 Zhaowei Cai , Avinash Ravichandran , Subhransu Maji , Charless Fowlkes , Zhuowen Tu , Stefano Soatto

The Feynman path integral representation of quantum theory is used in a non--parametric Bayesian approach to determine quantum potentials from measurements on a canonical ensemble. This representation allows to study explicitly the…

Quantum Physics · Physics 2007-05-23 J. C. Lemm , J. Uhlig , A. Weiguny
‹ Prev 1 3 4 5 6 7 10 Next ›