Multi-headed ensembles boost model performance with faster training.
problem Limited computational resources hinder ensemble search performance.
method Extend NES to multi-headed ensembles, leveraging end-to-end training and one-shot NAS methods.
result Multi-headed ensemble search finds robust ensembles 3 times faster with comparable performance.
High-capacity neural network ensembles often benefit more from high-capacity models than from increased diversity.
problem The performance of high-capacity neural network ensembles is often harmed by interventions that promote predictive diversity.
method A large-scale study of nearly 600 neural network classification ensembles, examining various interventions and architectures.
result Discouraging predictive diversity can be benign in large-network ensembles, and higher-capacity models often yield better performance than diverse architectures.
Jointly tuning ensemble models improves performance and uncertainty calibration.
problem Improving both predictive performance and uncertainty calibration in deep ensembles.
method Investigated the impact of jointly tuning weight decay, temperature scaling, and early stopping.
result Jointly tuning ensemble models generally matches or improves performance, with significant variation across tasks.
Embedded ensembles improve neural network performance efficiently.
problem Improving neural network performance with fewer resources.
method Analyzing the wide network limit of gradient descent dynamics using Neural-Tangent-Kernel.
result Embedded ensembles exhibit two regimes: independent and collective, affecting performance.
A framework preserves uncertainty in ensemble distillation.
problem Preserving uncertainty decomposition in ensemble distillation.
method General framework for distilling both regression and classification ensembles, preserving natural uncertainty decomposition.
result Framework maintains decomposition of predictive uncertainty.
Study pitfalls of deep learning ensembles in uncertainty estimation.
problem Pitfalls in in-domain uncertainty estimation and ensembling in deep learning.
method Exploration of standards for uncertainty quantification and broad study of ensembling techniques.
result Many sophisticated ensembling techniques are equivalent to a simple ensemble of few networks.
Transforms ensemble predictions to maintain interpretability.
problem Loss of interpretability in deep ensembles.
method Proposes transformation ensembles that aggregate predictions while preserving interpretability.
result Transformation ensembles yield better predictions than individual models and maintain interpretability.
Paper proposes ECOC for deep neural network ensembles to improve performance.
problem Designing an ensemble of deep networks is time-consuming and often not beneficial.
method ECOC framework applied to deep networks, with design strategies to balance accuracy and complexity.
result Proposed combinatory technique achieves highest classification performance.
New hyperparameter ensembles boost neural network performance and uncertainty.
problem Improving neural network robustness and uncertainty quantification.
method Designing ensembles over both weights and hyperparameters, stratified across random initializations.
result Hyper-deep and hyper-batch ensembles outperform deep and batch ensembles on various architectures.
Ensembling DNNs improves minority group performance, leading to fairness.
problem Improving subgroup performances in DNN classifiers.
method Simple homogeneous ensembling of DNNs.
result Fairness naturally emerges from ensembling, improving minority group performance.
EnD2 distills ensemble diversity into a single model.
problem Loss of ensemble diversity information in distillation.
method Prior Networks for distilling ensemble distribution into a single model.
result EnD2 retains both ensemble performance and diversity information. Paper proposes GP-NAS-ensemble for fast neural architecture performance prediction.
problem Estimating neural network performance without training time-consuming evaluations.
method GP-NAS-ensemble framework using ensemble learning improvements.
result Ranked second in a NAS performance prediction challenge.
Repulsive deep ensembles improve diversity and Bayesian inference.
problem Challenges in maintaining diversity among ensemble members trained independently.
method Introducing a repulsive term in the update rule of deep ensembles.
result Training dynamics of repulsive ensembles follow a Wasserstein gradient flow of KL divergence with the true posterior.
Optimal survival trees ensemble reduces tree count and improves predictive performance.
problem Improving predictive performance in survival analysis.
method Grows a forest of optimal survival trees by ranking and selecting the best trees based on out-of-bag error.
result Reduces the number of trees in the ensemble while improving predictive performance.
This paper explores how diverse neural network ensembles improve prediction accuracy and robustness against deception.
problem Improving prediction accuracy and robustness of neural networks against adversarial attacks.
method Examines and measures ensemble diversity, develops algorithms for creating and combining diverse ensembles.
result Greater diversity in neural network ensembles leads to higher accuracy and robustness against deception.
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. …
Ensembling improves performance when classifiers disagree more than average.
problem When do ensembles provide significant performance improvements in classification tasks?
method Theoretical and empirical analysis of ensemble improvement rate and disagreement-error ratio.
result Ensembling improves performance significantly when the disagreement rate is large relative to the average error rate.
Ensemble of GANs improves performance on disconnected data.
problem Disconnected datasets in computer vision cannot be represented by continuous GANs.
method Construct an optimization problem to relate single GAN, ensemble of GANs, conditional GANs, and Gaussian Mixture GANs.
result Ensemble of GANs outperforms single GANs with fewer parameters.
This work investigates power laws in deep neural network ensembles and predicts their performance.
problem Understanding the performance of deep neural network ensembles and their optimal structure.
method Investigated the behavior of negative log-likelihood (CNLL) of a deep ensemble as a function of ensemble size and member network size, identifying power law dependencies.
result One large network may perform worse than an ensemble of several medium-size networks, known as a memory split.
Ensembles of random-feature models can't outperform a single large model.
problem Finding the optimal balance between model size and ensemble size.
method Deterministic equivalent risk estimates and scaling laws analysis.
result Ensembles of random-feature models achieve near-optimal performance only under specific conditions.
Regression Prior Networks improve ensemble performance on regression tasks.
problem Improving ensemble performance on regression tasks.
method Extending Prior Networks and Ensemble Distribution Distillation (EnD2) to regression tasks using the Normal-Wishart distribution. result Regression Prior Networks yield performance competitive with ensemble approaches on regression tasks.
Efficient neural network ensembles improve image classification reliability and uncertainty quantification.
problem Uncertainty in neural network predictions for industrial image classification.
method Investigated efficient neural network ensembles (snapshot, batch, multi-input multi-output) for image classification reliability and uncertainty quantification.
result Batch ensemble is a cost-effective and competitive alternative to deep ensembles, offering savings in training and test time.
Ensembles improve classifier performance by reducing bias, not variance.
problem Improving classifier performance through ensemble methods.
method Extended bias-variance decomposition for classification tasks, introducing dual reparameterization.
result Ensembling reduces bias in classifiers, contrary to the traditional view.
Deep neural networks outperform traditional ensemble methods in time series classification.
problem Deep learning models struggle to match traditional ensemble methods in time series classification.
method Developed an ensemble of 60 deep learning models to improve time series classification performance.
result The proposed Neural Network Ensemble (NNE) outperforms current state-of-the-art methods.
Packed-Ensembles improve uncertainty estimation in constrained hardware.
problem Hardware limitations restrict the size of ensembles and network capacity, degrading performance.
method Packed-Ensembles (PE) design and train lightweight structured ensembles by modulating encoding space and parallelizing into a single backbone.
result PE accurately preserves diversity and maintains performance on key metrics like accuracy, calibration, and out-of-distribution detection.
Heterogeneous ensembles built from the predictions of a wide variety and large number of diverse base predictors represent a potent approach to building predictive models for problems where the ideal base/individual predictor may not be obvious. Ensemble selection is an especially promising approach here, not only for …
We propose and evaluate alternative ensemble schemes for a new instance based learning classifier, the Randomised Sphere Cover (RSC) classifier. RSC fuses instances into spheres, then bases classification on distance to spheres rather than distance to instances. The randomised nature of RSC makes it ideal for use in en…
SAEP prunes sub-architectures to reduce search cost while maintaining performance.
problem Redundancy in ensemble sub-architectures leads to high computational cost.
method SAEP leverages diversity to prune sub-architectures, reducing ensemble size.
result SAEP reduces the number of sub-architectures without degrading performance.
SharpBalance improves deep ensemble performance by balancing sharpness and diversity.
problem Improving deep ensemble performance in both in-distribution and out-of-distribution scenarios.
method Introducing SharpBalance, a novel training approach that balances sharpness and diversity within ensembles.
result SharpBalance effectively improves the sharpness-diversity trade-off and ensemble performance in ID and OOD scenarios.
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…
Ensembles of neural networks learn better by sharing information.
problem Improving performance of neural networks through collective learning.
method Modeling neural networks as socially interacting agents aiming to maximize their own performance and functional relations to others.
result Optimal collective performance emerges from local interactions between networks, leading to specialization and higher confidence.
Shallow trees in ensemble models make models more interpretable and sometimes better.
problem Lack of transparency in high-performing tree ensemble models.
method Developed an interpretation algorithm to convert tree ensembles into functional ANOVA representations. Proposed strategies to enhance interpretability.
result Shallow trees in ensemble models can lead to better generalization performance and improved interpretability.
Proposes a new method for ensembling neural subnetworks.
problem Computational expense and limited flexibility of traditional deep ensembles.
method Sequential Bayesian neural subnetwork ensembling.
result Outperforms traditional ensembles in various metrics.
Bayesian Quadrature improves ensembling for neural networks with dispersed likelihood peaks.
problem Ensembling neural networks struggles with dispersed, narrow peaks in likelihood surfaces.
method Uses Bayesian Quadrature to construct weighted ensembles of architectures.
result Empirically outperforms state-of-the-art baselines in test likelihood, accuracy, and expected calibration error.
Single neural networks can match deep ensembles' benefits without the complexity.
problem The effectiveness and necessity of deep ensembles in neural network models.
method Demonstrated limitations of ensemble diversity and OOD performance in deep ensembles compared to a single larger model.
result A single neural network can replicate deep ensembles' benefits in uncertainty quantification and robustness.
Proposes a method to reduce ensemble size while maintaining accuracy.
problem Complexity and computational burden of ensemble models in large-scale data.
method Optimizes margin distribution to reduce ensemble size while increasing diversity.
result Pruned ensemble uses only a fraction of original classifiers with improved or similar generalization performance.
Enhanced reinforcement learning using ensemble methods.
problem Improving reinforcement learning performance.
method Distributional reinforcement learning with ensemble group-aided training.
result Ensemble methods lead to more robust and efficient learning.
E3 combines sparse MoEs and ensembles to improve model efficiency and performance.
problem Improving model efficiency and performance in machine learning.
method Combining sparse mixture of experts and ensembles, presenting Efficient Ensemble of Experts (E3). result E3 achieves better accuracy, log-likelihood, few-shot learning, robustness, and uncertainty estimates than baselines. Gestalt combines two models to improve SQuAD2.0 performance.
problem Improving the accuracy of answering questions in context paragraphs.
method A stacking ensemble of ALBERT and RoBERTa models, combined with a CNN-based meta-model.
result Best ensemble achieved 87.117 EM and 90.306 F1 scores, improving baseline by 0.55% and 0.61% respectively.
Tree ensembles, such as random forests and boosted trees, are renowned for their high prediction performance. However, their interpretability is critically limited due to the enormous complexity. In this study, we present a method to make a complex tree ensemble interpretable by simplifying the model. Specifically, we …
An ensemble method enhances cryptocurrency trading strategies using deep reinforcement learning.
problem Improving generalization performance in stochastic cryptocurrency trading environments.
method Model selection and mixture distribution policy to ensemble deep reinforcement learning models.
result Improved out-of-sample performance compared to benchmarks.
Ensemble quantile classifier improves performance on high-dimensional data.
problem Discriminating high-dimensional data with heavy-tailed or skewed inputs.
method Regularized quantile classifier that assigns variable weights.
result Consistently estimates minimal population loss and is Bayes optimal.
Hydra distills ensemble models into a single model while preserving diversity and uncertainty.
problem Loss of ensemble diversity and uncertainty in distilled models.
method Single multi-headed neural network with shared body network.
result Hydra improves distillation performance and preserves ensemble diversity and uncertainty.
Models obtained by decision tree induction techniques excel in being interpretable.However, they can be prone to overfitting, which results in a low predictive performance. Ensemble techniques are able to achieve a higher accuracy. However, this comes at a cost of losing interpretability of the resulting model. This ma…
MOD improves ensemble-based uncertainty estimates by encouraging larger diversity.
problem Improving model uncertainty estimates for inputs not seen during training.
method Maximize Overall Diversity (MOD) approach to encourage larger diversity in ensemble predictions.
result Significantly improves predictive performance for out-of-distribution test examples.
Boosting meta-trees improve decision tree performance.
problem Overfitting in decision trees.
method Boosting approach to construct multiple meta-trees.
result Ensembles of meta-trees prevent overfitting.
A new method selects models for ensemble learning to maximize mutual information, outperforming existing approaches.
problem Selecting models for ensemble learning to improve performance and reduce correlation issues.
method Formulate budgeted ensemble selection as maximizing mutual information, use Gaussian-copula to model correlated errors, propose a greedy mutual-information selection algorithm.
result Our method consistently outperforms strong baselines across multiple datasets.
Researchers test if larger margins lead to lower generalization error in ensemble methods.
problem Explaining why ensembles perform better than individual classifiers.
method Empirical testing of techniques to evaluate the relationship between margins and generalization error.
result Current research holds true: larger margins generally lead to lower generalization error.