Ensembling smaller models can outperform larger models in terms of accuracy and efficiency.
problem The inefficiency of training larger models for boosting performance.
method Training ensembles of smaller models and comparing their performance to single larger models.
result Ensembles of smaller models outperform single larger models in accuracy and efficiency, especially as models grow large.
AEA dynamically aggregates ensemble targets for actor-critic learning.
problem Static ensemble aggregation methods struggle with overestimation bias and variance.
method Adaptive Ensemble Aggregation (AEA) dynamically constructs ensemble-based targets.
result AEA converges to optimal variance reduction and maximal Fisher information.
BatchEnsemble reduces ensemble costs by 3X in training and testing.
problem High costs for training and testing ensembles of neural networks.
method Defines each weight matrix as a Hadamard product of a shared matrix and a rank-one matrix per member.
result Achieves 3X speedup and 3X memory reduction in test time for ensembles of size 4.
New theory shows how multi-head attention reduces variance and decorrelates outputs.
problem Understanding and optimizing multi-head attention in neural networks.
method Developed a statistical theory linking multi-head attention to ensemble Nadaraya-Watson estimators.
result MHA variance reduction depends on head decorrelation, not just head count.
This paper develops a new theory for ensemble learning beyond variance reduction.
problem Ensemble learning's effectiveness for stable estimators is not fully explained by variance reduction.
method Develops a general weighting theory for ensemble learning, formalizing ensembles as linear operators and introducing geometric and spectral constraints.
result Structured weights can outperform uniform averaging by reshaping approximation geometry and redistributing spectral complexity.
Ensemble learning has had many successes in supervised learning, but it has been rare in unsupervised learning and dimensionality reduction. This study explores dimensionality reduction ensembles, using principal component analysis and manifold learning techniques to capture linear, nonlinear, local, and global feature…
A new method using energy distance for ensemble and scenario reduction.
problem Solving complex dynamic and stochastic programs, especially in energy systems.
method Proposes a new method based on energy distance for ensemble and scenario reduction.
result Reduced scenario sets exhibit better statistical properties for energy distance than Wasserstein distance.
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.
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.
Deep neural networks improve ensemble weather forecasts.
problem Improving accuracy and efficiency of ensemble weather forecasts.
method Mixed model combining subset of trajectories with deep neural networks for post-processing.
result Achieved over 14% relative improvement in ensemble forecast skill.
Study ridge ensembles in proportional feature-to-sample size regime, proving risk equivalence and GCV consistency.
problem Characterizing and optimizing ridge ensembles in proportional feature-to-sample size regimes.
method Proportional asymptotics analysis, GCV for tuning, proving risk equivalence.
result Risk of optimal full ridgeless ensemble matches optimal ridge predictor's risk.
ECV method optimizes ensemble parameters for randomized ensembles.
problem Efficient tuning of ensemble parameters in randomized ensembles.
method ECV (Extrapolated Cross-Validation) method for tuning ensemble and subsample sizes.
result ECV yields δ-optimal ensembles for squared prediction risk.
Bagging reduces variance in LID estimation by preserving local distribution of NN distances.
problem High estimation variance from limited data in small neighborhoods.
method Subbagging to preserve local distribution of NN distances, combined with ensemble size.
result Bagging significantly reduces variance and MSE in LID estimation.
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.
New method reduces ensemble size for linear bandits, achieving near optimal regret.
problem Achieving near optimal regret in linear bandits with limited ensemble size.
method Ensemble sampling with a size of order d log T d \log T d log T for a d d d -dimensional stochastic linear bandit. result Regret is at most ( d log T ) 5 / 2 T (d \log T)^{5/2} \sqrt{T} ( d log T ) 5/2 T , improving over linear scaling with T T T . The paper analyzes the risk of bagging regularized M-estimators under proportional asymptotics.
problem Characterizing the risk of ensemble estimators trained with subsamples and regularizers.
method Developed a consistent estimator for the risk of ensemble estimators under proportional asymptotics.
result Optimal subsample size k ⋆ k^\star k ⋆ tends to be in the overparameterized regime for the full-ensemble estimator. Ant colonies and boosting algorithms both reduce bias and variance through adaptive mechanisms.
problem Understanding the mathematical principles behind ensemble learning and ant colony behavior.
method Developed a formal mapping between AdaBoost's adaptive reweighting and ant recruitment dynamics.
result Proved that the fundamental theorem of weak learnability has a direct analog in colony decision-making.
Bayesian Neural Networks improve geophysical model ensembles with reduced uncertainty.
problem Improving geophysical model projections and uncertainty quantification.
method Developed a Bayesian Neural Network ensemble strategy for geophysical models.
result Bayesian Neural Network ensemble outperforms existing methods in ozone prediction.
Study compares under-bagging with other methods for imbalanced data.
problem Comparing under-bagging with other methods for imbalanced data.
method Replica analysis of under-bagging, comparing with under-sampling and simple weighting.
result Under-bagging improves performance by increasing the majority class size.
Unified neural network for linear and nonlinear dimension reduction.
problem Efficiently perform linear and nonlinear sufficient dimension reduction.
method Belted and Ensembled Neural Network (BENN) framework.
result Unified framework for both linear and nonlinear dimension reduction.
JUCAL jointly calibrates aleatoric and epistemic uncertainties in classifier ensembles.
problem Misrepresentation of predictive uncertainty due to unbalanced aleatoric and epistemic uncertainties.
method Joint Uncertainty Calibration (JUCAL) that jointly calibrates two constants to weight and scale uncertainties.
result Significantly outperforms state-of-the-art calibration methods across various text classification tasks.
We propose a new randomized ensemble technique with a provable security guarantee against black-box transfer attacks. Our proof constructs a new security problem for random binary classifiers which is easier to empirically verify and a reduction from the security of this new model to the security of the ensemble classi…
In this work a novel method to quantify spectral ergodicity for random matrices is presented. The new methodology combines approaches rooted in the metrics of Thirumalai-Mountain (TM) and Kullbach-Leibler (KL) divergence. The method is applied to a general study of deep and recurrent neural networks via the analysis of…
Paper proposes a multi-phase pruning pipeline for deep ensemble learning on IIoT devices.
problem Computational limitations of IoT devices for deep learning models.
method Generates diverse pruned models, applies integer quantization, and uses clustering-based pruning.
result Significant reduction in model size (up to 90%) and improved performance (up to 7%) on IIoT devices.
Develops efficient time series prediction intervals.
problem Constructing reliable prediction intervals for time series data.
method Introduces exttt{EnbPI} algorithm for time series data.
result Demonstrates superior performance compared to existing methods.
IENs reduce neural network variance without increasing complexity.
problem Reducing variance in neural networks without increasing model complexity.
method IENs use ensemble parameters during training to reduce variance, removing them during testing.
result IENs reduce network variance by a factor of 1 / m L − 1 1/m^{L-1} 1/ m L − 1 , leading to significant error rate decreases. Paper analyzes ensemble Kalman updates for effective dimension and localization.
problem Why small ensemble sizes work well in inverse problems and data assimilation.
method Non-asymptotic analysis of ensemble Kalman updates, focusing on effective dimension and localization.
result Rigorously explains why a small ensemble size is sufficient when prior covariance has moderate effective dimension.
ForestPrune optimizes tree ensemble pruning for compactness and speed.
problem Large tree ensembles in predictive models consume excessive memory and reduce interpretability.
method Developed a specialized optimization algorithm to efficiently prune tree ensembles by depth layers.
result ForestPrune produces compact, high-performing models that outperform existing post-processing methods.
Paper explains how tree ensembles improve predictions by smoothing and regulating smoothness.
problem Understanding why tree ensembles perform well despite their complexity.
method Interpreting tree ensembles as adaptive and self-regularizing smoothers.
result Ensemble trees make more smooth predictions than individual trees and adjust smoothness based on input dissimilarity.
Paper reduces vocabulary losslessly for language model cooperation.
problem Language models struggle to cooperate with different tokenizations.
method Established a theoretical framework for lossless vocabulary reduction.
result Efficiently converts models with different tokenizations to cooperate with maximal common vocabulary.
Ensemble++ uses shared-factor ensembles to scale Thompson Sampling for linear and nonlinear bandits.
problem Computational challenges in Thompson Sampling for large-scale or non-conjugate settings.
method Ensemble++ with shared-factor architecture and random linear combinations.
result Ensemble++ achieves comparable regret to exact Thompson Sampling with significantly smaller ensemble sizes.
The paper develops a stationary-distribution theory for Random Forest ensemble size selection.
problem Determining the optimal number of trees in Random Forests.
method Modeling the ensemble size as a birth-death Markov chain and deriving its stationary distribution.
result The stationary ensemble size B ∗ B_* B ∗ scales as O ( ε − 2 ) O(\varepsilon^{-2}) O ( ε − 2 ) as ε ↓ 0 \varepsilon\downarrow 0 ε ↓ 0 . A new ensemble learning method called Residual Likelihood Forests improves performance and reduces model size.
problem Improving machine learning classification performance with compact models.
method Sequential optimization of conditional likelihoods in a boosting-like framework, combining multiplicatively.
result Significant performance improvements and reduced model size compared to other ensemble methods.
The number of component classifiers chosen for an ensemble greatly impacts the prediction ability. In this paper, we use a geometric framework for a priori determining the ensemble size, which is applicable to most of existing batch and online ensemble classifiers. There are only a limited number of studies on the ense…
Improved regret bound for linear ensemble sampling.
problem Closing the gap between theory and practice in linear ensemble sampling.
method General regret analysis framework for linear bandit algorithms, revealing a relationship with LinPHE.
result Achieves a frequentist regret bound of i l d e O ( d 3 / 2 T ) ilde{O}(d^{3/2}\sqrt{T}) i l d e O ( d 3/2 T ) for linear ensemble sampling. Adapts DR objectives for both sample and feature size reduction.
problem Simultaneously reduce sample and feature sizes.
method Semi-relaxed Gromov-Wasserstein optimal transport.
result OT plan delivers competitive hard clustering.
A new ML-based filter improves data assimilation for nonlinear systems.
problem Improving data assimilation for nonlinear systems using ensemble methods.
method Developed a machine learning-based conditional mean filter (ML-EnCMF) integrating ANN and linear functions.
result ML-EnCMF outperforms EnKF and likelihood-based EnCMF in nonlinear systems.
Meta-learning predicts optimal ensemble size and methods for time series forecasting.
problem Finding the best ensemble of time series forecasting methods.
method Two-step approach using meta-learning to predict ensemble size and methods.
result Meta-learning outperformed benchmarks in forecasting errors for all data types and horizons.
Paper improves DNS typo-squatting detection with ensemble model.
problem Detecting and preventing DNS typo-squatting attacks.
method Ensemble-based feature selection and bagging classification model.
result The proposed framework achieves high accuracy and precision in identifying typo-squatting domains.
Enhanced ensemble filters use machine learning to improve accuracy in filtering models.
problem Accuracy limitations of traditional ensemble Kalman filters.
method Introduces a measure neural mapping (MNM) to map joint predicted state and observation to updated state estimates.
result Superior root-mean-square-error performance compared to leading methods in filtering models.
Dictionary based classifiers are a family of algorithms for time series classification (TSC), that focus on capturing the frequency of pattern occurrences in a time series. The ensemble based Bag of Symbolic Fourier Approximation Symbols (BOSS) was found to be a top performing TSC algorithm in a recent evaluation, as w…
Analog methods improve forecast accuracy in complex models.
problem Improving forecast accuracy in complex models like Lorenz-96.
method Constructing analogs using variational autoencoders for ensemble data assimilation.
result Constructed analogs perform as well as a full ensemble square root filter.
Adaptive XGBoost improves accuracy on evolving data streams by updating the ensemble dynamically.
problem Concept drift in evolving data streams.
method Adapts XGB to update the ensemble with new data, maintaining consistency with current concept.
result Improves classification accuracy on evolving data streams compared to other methods.
EnKBS smoothes complex systems with future observations for causal inference.
problem Improving state estimation in complex systems with rapid dynamics.
method Continuous-time ensemble Kalman-Bucy smoother for nonlinear dynamical systems.
result EnKBS provides derivative-free framework with high skill in various scientific problems.
A new framework for dimension reduction using ensemble of random projections.
problem High-dimensional regression problems with limited data.
method Aggregating an ensemble of carefully chosen random projections, retaining based on empirical performance, and selecting singular vectors.
result The proposed method stabilizes error as the number of projection groups increases.
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…
Efficient method for vertex embedding and community detection.
problem Vertex embedding and community detection.
method Normalized one-hot graph encoder and rank-based cluster size measure.
result Excellent numerical performance of graph encoder ensemble algorithm.
Probabilistic graphical models are graphical representations of probability distributions. Graphical models have applications in many fields including biology, social sciences, linguistic, neuroscience. In this paper, we propose directed acyclic graphs (DAGs) learning via bootstrap aggregating. The proposed procedure i…