arXiv research

Bayesian inference using stochastic neural networks ensembles.

Enhances neural network regularization with no extra cost.

In this article, we advocate the ensemble approach for variable selection. We point out that the stochastic mechanism used to generate the variable-selection ensemble (VSE) must be picked with care. We construct a VSE using a stochastic stepwise algorithm, and compare its performance with numerous state-of-the-art algo…

New method reduces ensemble size for linear bandits, achieving near optimal regret.

Deep ensembles effectively capture epistemic uncertainty through training stochasticity, providing a frequentist perspective.

A new stochastic method handles ensemble creation with cost constraints.

A new batch ensemble method reduces regret in stochastic bandits.

This work improves SSL by leveraging disentangled latent space for better self-ensembling.

Proposes a new method to enhance neural learning by maximizing information gain.

ES reduces high-probability regret in stochastic linear bandits.

Proposes SWA for adversarial training to improve model robustness.

Ensembling DNNs improves minority group performance, leading to fairness.

Stochastic mirror descent improves performance on ensemble models.

Statistical estimates can often be improved by fusion of data from several different sources. One example is so-called ensemble methods which have been successfully applied in areas such as machine learning for classification and clustering. In this paper, we present an ensemble method to improve community detection by…

Paper introduces XBART for nonlinear regression, outperforming XGBoost.

SETrLUSI combines diverse knowledge from multiple domains for faster convergence.

The question why deep learning algorithms generalize so well has attracted increasing research interest. However, most of the well-established approaches, such as hypothesis capacity, stability or sparseness, have not provided complete explanations (Zhang et al., 2016; Kawaguchi et al., 2017). In this work, we focus on…

This study shows how social insects and machine learning methods share a common mathematical framework.

SPEQ improves quantized neural networks by stochastic precision sharing and cosine similarity loss.

Ensemble models provide more accurate feature importance estimates than single models.

This paper uses Bayesian optimization to efficiently identify stochastic dynamical systems.

ENN uses covariance matrices for gradient-free optimization in neural networks.

New algorithm reduces overfitting in neural networks.

The superior performance of ensemble methods with infinite models are well known. Most of these methods are based on optimization problems in infinite-dimensional spaces with some regularization, for instance, boosting methods and convex neural networks use $L^1$-regularization with the non-negative constraint. However…

EnsLoss combines multiple loss functions to prevent overfitting in classification.

AER method improves classifier ensemble for imbalanced data.

We select n stocks traded in the New York Stock Exchange and we form a statistical ensemble of daily stock returns for each of the k trading days of our database from the stock price time series. We analyze each ensemble of stock returns by extracting its first four central moments. We observe that these moments are fl…

An ensemble method enhances cryptocurrency trading strategies using deep reinforcement learning.

Generative adversarial networks generate realistic, time-evolving high-resolution atmospheric fields.

GER learns particle dynamics from unpaired snapshots using physics-informed GANs.

TOO optimizes stochastic epidemiological models by finding both parameter settings and random seeds.

The specificty and sensitivity of resting state functional MRI (rs-fMRI) measurements depend on pre-processing choices, such as the parcellation scheme used to define regions of interest (ROIs). In this study, we critically evaluate the effect of brain parcellations on machine learning models applied to rs-fMRI data. O…

A new framework combines multiple loss reserving models for better predictive performance.

REBEC improves robustness of wind wave models using evolutionary techniques.

Artificial neural networks have been successfully applied to a variety of machine learning tasks, including image recognition, semantic segmentation, and machine translation. However, few studies fully investigated ensembles of artificial neural networks. In this work, we investigated multiple widely used ensemble meth…

Stein variational neural network ensembles improve diversity and uncertainty estimation.

BI-EqNO improves Bayesian inference with flexible neural operators.

The standard probabilistic perspective on machine learning gives rise to empirical risk-minimization tasks that are frequently solved by stochastic gradient descent (SGD) and variants thereof. We present a formulation of these tasks as classical inverse or filtering problems and, furthermore, we propose an efficient, g…

New algorithms split deep learning tasks into representation and uncertainty estimation.

We study the price dynamics of stocks traded in a financial market by considering the statistical properties both of a single time series and of an ensemble of stocks traded simultaneously. We use the $n$ stocks traded in the New York Stock Exchange to form a statistical ensemble of daily stock returns. For each tradin…

Bayesian optimization uses BNNs as efficient surrogate models for expensive function evaluations.

Bayesian learning made scalable with posteriors library.

A new Bayesian MBRL method improves performance in robotics tasks.

We prove that a Gaussian ensemble of smooth random sections of a real vector bundle over compact manifold canonically defines a metric on the bundle together with a connection compatible with it. Additionally, we prove a refined Gauss-Bonnet-Chern theorem stating that if the bundle and the manifold are oriented, then t…

Many deep learning algorithms can be easily fooled with simple adversarial examples. To address the limitations of existing defenses, we devised a probabilistic framework that can generate an exponentially large ensemble of models from a single model with just a linear cost. This framework takes advantage of neural net…

Simple mode exploration methods do not improve performance in neural networks.

Novel filtering method for high-dimensional chaotic systems.

A new method synthesizes expressions from characteristics using GAN for healthcare.