On-device research index

arXiv research

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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

3 results for “Q-EP”

Deep Q-Exponential Processesstat.ML

Deep Q-EP improves image modeling by stacking Q-EP layers.

problem Inhomogeneous subjects like images with edges are poorly modeled by standard Gaussian processes.

method Introducing shallow Q-EP as a latent variable model, stacking multiple layers, and applying sparse approximation and scalable variational strategy.

result Deep Q-EP outperforms state-of-the-art deep probabilistic models in image modeling.

Deep Q-EP Q-EP Gaussian process image modeling sparse approximation

2024-10-29abs ↗pdf ↗

Bayesian Learning via Q-Exponential Processstat.ME

This work introduces a new probabilistic process for regularization in machine learning.

problem Developing a probabilistic framework for

L_q

regularization.

method Generalizing

q

-exponential distribution to

Q

-exponential (Q-EP) process.

result Q-EP process provides a flexible prior for functions with sharper penalties.

Bayesian learning Regularization Q-Exponential Process Stochastic Processes Machine Learning

2022-10-14abs ↗pdf ↗

Spatiotemporal Besov Priors for Bayesian Inverse Problemsstat.ME

New spatiotemporal Besov process improves CT image reconstruction and other inverse problems.

problem Handling abrupt changes and sharp contrasts in spatiotemporal data.

method Generalized Besov process (STBP) with Q-exponential process for temporal correlation.

result STBP outperforms traditional methods in dynamic reconstruction and inverse problems.

Besov process spatiotemporal CT reconstruction Bayesian inverse problems Q-exponential process

2023-06-28abs ↗pdf ↗