arXiv research

Overparameterized ensembles don't offer generalization benefits over single large models.

Research reveals how diversity impacts ensemble generalization in classification tasks.

A framework preserves uncertainty in ensemble distillation.

Proposes a method to reduce ensemble size while maintaining accuracy.

This paper explores how diverse neural network ensembles improve prediction accuracy and robustness against deception.

Ensembles of deep neural networks significantly improve generalization accuracy. However, training neural network ensembles requires a large amount of computational resources and time. State-of-the-art approaches either train all networks from scratch leading to prohibitive training cost that allows only very small ens…

DASH improves ensemble generalizability by encouraging diverse, flat loss landscapes.

Fed-ensemble improves FL by averaging predictions from multiple models.

Transforms ensemble predictions to maintain interpretability.

Ensemble pruning, selecting a subset of individual learners from an original ensemble, alleviates the deficiencies of ensemble learning on the cost of time and space. Accuracy and diversity serve as two crucial factors while they usually conflict with each other. To balance both of them, we formalize the ensemble pruni…

New method improves ensemble diversity and generalization.

Ensemble of diverse CNNs detects and mitigates adversarial attacks.

Paper proposes a new method for probabilistic electricity price forecasting.

GNCL algorithm controls diversity in deep ensembles.

Diversity or complementarity of experts in ensemble pattern recognition and information processing systems is widely-observed by researchers to be crucial for achieving performance improvement upon fusion. Understanding this link between ensemble diversity and fusion performance is thus an important research question. …

Ensemble GP improves genetic programming by achieving better results with smaller models.

This paper studies recursive ensembles driven by Fibonacci updates, improving learning dynamics.

The motivation of this work is to improve the performance of standard stacking approaches or ensembles, which are composed of simple, heterogeneous base models, through the integration of the generation and selection stages for regression problems. We propose two extensions to the standard stacking approach. In the fir…

SharpBalance improves deep ensemble performance by balancing sharpness and diversity.

Improved Bayesian inference for neuronal ensemble inference reduces computational cost.

Optimizes ensemble weights and hyperparameters for better machine learning model predictions.

This paper tackles robustness of ensemble stumps and trees under general ℓ_p norm perturbations.

Self-paced ensemble learning improves audio classification models.

New ensemble method improves model stability exponentially.

Jointly tuning ensemble models improves performance and uncertainty calibration.

Paper analyzes ensemble Kalman updates for effective dimension and localization.

Ensemble of GANs improves performance on disconnected data.

Proposes using Wasserstein barycenters for model ensembling in multiclass/multilabel learning.

This study examines ensembling of diffusion models for improved generative quality.

Study on infinite neural networks for generalization.

ECV method optimizes ensemble parameters for randomized ensembles.

Study ridge ensembles in proportional feature-to-sample size regime, proving risk equivalence and GCV consistency.

This paper improves prediction rule ensembles using model-based data generation.

In this article supervised learning problems are solved using soft rule ensembles. We first review the importance sampling learning ensembles (ISLE) approach that is useful for generating hard rules. The soft rules are then obtained with logistic regression from the corresponding hard rules. In order to deal with the p…

Shallow trees in ensemble models make models more interpretable and sometimes better.

Ensembles dynamic models using random feature approximations.

CE improves climate uncertainty quantification using GCM ensembles and observational data.

Researchers test if larger margins lead to lower generalization error in ensemble methods.

Efficient facial feature learning with shared representations reduces redundancy and improves accuracy.

Random Hyperboxes is a simple yet effective ensemble classifier.

In this article, we propose a novel ensemble technique with a multi-scheme weighting based on a technique called coopetitive soft gating. This technique combines both, ensemble member competition and cooperation, in order to maximize the overall forecasting accuracy of the ensemble. The proposed algorithm combines the …

Improved regret bound for linear ensemble sampling.

This paper develops a new theory for ensemble learning beyond variance reduction.

Ensembles improve classifier performance by reducing bias, not variance.

New samplers improve MCMC efficiency in high dimensions.

Proposes a method to generate counterfactuals for ensemble models using entropic risk measures.

Corrects GCV for inconsistent risk estimation in finite ensembles of penalized estimators.

In this paper, we propose to provide a general ensemble learning framework based on deep learning models. Given a group of unit models, the proposed deep ensemble learning framework will effectively combine their learning results via a multilayered ensemble model. In the case when the unit model mathematical mappings a…