WASH trains ensembles with shuffled weights to improve accuracy and reduce communication.
problem Training ensembles for weight averaging leads to models converging to different loss basins.
method WASH randomly shuffles a small percentage of weights during training to keep models within the same basin.
result WASH achieves state-of-the-art image classification accuracy with lower communication costs.
Proposes a new method for deep ensembles that improves accuracy and calibration.
problem Improving accuracy and calibration of deep ensembles.
method Estimates confusion matrices of ensemble members and weighs them according to their inferred performance.
result Empirically shows superiority of soft Dawid Skene over ensemble averaging.
Dropout and similar stochastic neural network regularization methods are often interpreted as implicitly averaging over a large ensemble of models. We propose STE (stochastically trained ensemble) layers, which enhance the averaging properties of such methods by training an ensemble of weight matrices with stochastic r…
New findings suggest no ensemble averaging for certain black hole observables.
problem Mystery in AdS/CFT correspondence regarding ensemble averaging of black hole amplitudes.
method Exploring sub-threshold observables in D=3 and proving novel results about hyperbolic geometry. result Connected solutions of Einstein's equations with disconnected boundary never contribute to sub-threshold observables.
Ensemble learning is a method of combining multiple trained models to improve model accuracy. We propose the usage of such methods, specifically ensemble average, inside Convolutional Neural Network (CNN) architectures by replacing the single convolutional layers with Inner Average Ensembles (IEA) of multiple convoluti…
We study the price dynamics of stocks traded in the NASDAQ market by considering the statistical properties of an ensemble of stocks traded simultaneously. For each trading day of our database, we study the ensemble return distribution by extracting its first two central moments. According to previous results obtained …
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.
Fed-ensemble improves FL by averaging predictions from multiple models.
problem Improving generalization in federated learning.
method Random permutations to update K models, averaging predictions.
result Predictions from all K models have the same predictive posterior distribution.
Revises Bayesian model averaging for foundation models.
problem Ensemble pre-trained and lightly-finetuned foundation models for improved classification performance.
method Introduces trainable linear classifiers and computationally cheaper model averaging scheme (OMA).
result Ensembled models can better predict on various datasets.
Geometric Brownian motion (GBM) is a model for systems as varied as financial instruments and populations. The statistical properties of GBM are complicated by non-ergodicity, which can lead to ensemble averages exhibiting exponential growth while any individual trajectory collapses according to its time-average. A com…
Deep ensembles mimic Bayesian averaging with learned priors.
problem Quantifying uncertainty in neural networks.
method Showed deep ensembles perform exact Bayesian averaging with an implicitly learned data-dependent prior.
result Deep ensembles are Bayesian and provide an explanation for their strong empirical performance.
Proposes SWA for adversarial training to improve model robustness.
problem Overfitting in adversarial training due to insufficient sample complexity.
method Adversarial training with Stochastic Weight Average (SWA).
result Improves model robustness on CIFAR-10, CIFAR-100, and SVHN datasets.
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.
We develop ensemble Convolutional Neural Networks (CNNs) to classify the transportation mode of trip data collected as part of a large-scale smartphone travel survey in Montreal, Canada. Our proposed ensemble library is composed of a series of CNN models with different hyper-parameter values and CNN architectures. In o…
In modern portfolio theory, the balancing of expected returns on investments against uncertainties in those returns is aided by the use of utility functions. The Kelly criterion offers another approach, rooted in information theory, that always implies logarithmic utility. The two approaches seem incompatible, too loos…
Two new ensemble methods improve CATE estimation across various scenarios.
problem Estimating CATE in clinical trials to understand treatment effects heterogeneity.
method Proposed two ensemble methods: Stacked X-Learner and Consensus Based Averaging (CBA).
result Ensemble methods achieve good performance across diverse scenarios.
Aggregating multiple learners through an ensemble of models aim to make better predictions by capturing the underlying distribution of the data more accurately. Different ensembling methods, such as bagging, boosting, and stacking/blending, have been studied and adopted extensively in research and practice. While baggi…
Gas demand is made of three components: Residential, Industrial, and Thermoelectric Gas Demand. Herein, the one-day-ahead prediction of each component is studied, using Italian data as a case study. Statistical properties and relationships with temperature are discussed, as a preliminary step for an effective feature s…
We consider random vectors drawn from a multivariate normal distribution and compute the sample statistics in the presence of non-stationary correlations. For this purpose, we construct an ensemble of random correlation matrices and average the normal distribution over this ensemble. The resulting distribution contains…
clusterBMA combines clustering results from multiple models using Bayesian model averaging.
problem Uncertainty in model selection for clustering.
method Bayesian model averaging to combine results from multiple clustering algorithms.
result ClusterBMA offers probabilistic cluster allocations and quantifies model-based uncertainty.
The recently proposed Temporal Ensembling has achieved state-of-the-art results in several semi-supervised learning benchmarks. It maintains an exponential moving average of label predictions on each training example, and penalizes predictions that are inconsistent with this target. However, because the targets change …
Study on Gaussian ensemble of matrix products with mixed moments computed.
problem Understanding the statistical properties of matrix products of Gaussian matrices.
method Analysis of a multi-Wishart ensemble and enumeration of non-crossing pairings.
result Mixed moments of the product matrix are computed and found to be weighted by Fuss-Catalan numbers at large N. Vision impairment due to pathological damage of the retina can largely be prevented through periodic screening using fundus color imaging. However the challenge with large scale screening is the inability to exhaustively detect fine blood vessels crucial to disease diagnosis. In this work we present a computational ima…
This paper improves deep learning model consistency through ensemble methods.
problem Consistency and correct-consistency issues in deep learning models.
method Formal definition of consistency and correct-consistency, proving ensemble improvement, proposing dynamic snapshot ensemble method.
result Ensemble methods can improve correct-consistency of deep learning models.
TabSurv adapts tabular neural networks for survival analysis.
problem Survival analysis on tabular data using deep learning methods.
method Adapts modern tabular architectures to survival analysis using Weibull distribution or non-parametric prediction. Optimizes SurvHL histogram loss function.
result TabSurv consistently outperforms classical and deep learning baselines on 10 real-world survival datasets.
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…
This work studies a unified approach to ensemble aggregation using likelihood perspective.
problem Density aggregation in machine learning, focusing on improving ensemble predictions.
method Normalized generalized mean of order r in the log-likelihood framework.
result The optimal range for r is [0,1], providing a principled justification for linear and geometric pooling.
Simple mode exploration methods do not improve performance in neural networks.
problem Improving predictive probabilities in neural networks.
method Exploring local regions around diverse solutions using simple methods.
result Simple mode exploration methods do not improve performance.
The paper addresses model averaging and ensembling, providing theoretical and practical insights.
problem Combining least squares estimators from multiple candidate models for improved predictive accuracy.
method Establishes oracle inequalities for Mallows' Cp criterion, proposes a novel Mallows-type MA procedure. result Demonstrates the effectiveness of the proposed Mallows-type MA estimator through numerical experiments.
Logifold improves ensemble machine learning by identifying fuzzy domains.
problem Improving ensemble machine learning accuracy.
method Formulating logifold structure and interpreting local charts of datasets.
result Logifold improves accuracy compared to averaging model outputs.
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.
CNN improves medium-range temperature forecasts with limited resources.
problem Limited computational resources for high-resolution temperature forecasts.
method CNN post-processing with ensemble NWP models for bias correction and spatial downscaling.
result High-resolution (5-km) surface temperature forecasts with lead times up to 5.5 days.
A fast method for Lasso and Logistic Lasso problems.
problem Solving Lasso and Logistic Lasso regression problems efficiently.
method Iterative active set approach using solver updates.
result 31.41 times faster on average for compressed sensing.
We propose an algorithm to enhance certified robustness of a deep model ensemble by optimally weighting each base model. Unlike previous works on using ensembles to empirically improve robustness, our algorithm is based on optimizing a guaranteed robustness certificate of neural networks. Our proposed ensemble framewor…
Ensemble models improve prediction calibration for mismatched distributions.
problem Calibration issues in deep neural networks with mismatched train and test distributions.
method Simple data augmentation and mixing techniques for ensemble models.
result Improves calibration and accuracy on CIFAR10 and CIFAR100 benchmarks.
New method creates diverse neural ensembles for better uncertainty estimation and robustness.
problem Creating more robust neural networks for uncertainty estimation and dataset shift.
method Automatically constructing ensembles with varying architectures.
result Ensembles with varying architectures outperform deep ensembles in accuracy, uncertainty calibration, and robustness.
The paper explores dynamic ensembles for multi-step forecasting.
problem Lack of research on dynamic ensembles for multi-step forecasting.
method Extensive experiments with 3568 time series and an ensemble of 30 multi-output models.
result Dynamic ensembles based on arbitrating and windowing perform best.
Suppose some classifiers are selected from a set of hypothesis classifiers to form an equally-weighted ensemble that selects a member classifier at random for each input example. Then the ensemble has an error bound consisting of the average error bound for the member classifiers, a term for selectivity that varies fro…
CDST improves ensemble prediction by adjusting model weights based on covariates.
problem Improving ensemble prediction accuracy in complex scenarios.
method Covariate-dependent stacking (CDST) with flexible model weights estimated via cross-validation.
result CDST consistently outperforms conventional model averaging methods in complex datasets.
Inverse depth scaling found in LLMs due to similar layers averaging error.
problem Understanding how depth affects loss in large language models.
method Analysis of LLMs and toy residual networks.
result Loss scales inversely proportional to depth in LLMs.
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.
Automates zero-shot classification by scoring and weighting prompts.
problem Improving zero-shot accuracy through prompt ensembling.
method Automatic prompt scoring and weighting method.
result Method outperforms existing techniques on various benchmarks.
Ensembles of models have been empirically shown to improve predictive performance and to yield robust measures of uncertainty. However, they are expensive in computation and memory. Therefore, recent research has focused on distilling ensembles into a single compact model, reducing the computational and memory burden o…
New method predicts spatio-temporal data with short and long-range dependence.
problem Uncertainty in predicting the distribution of mixed moving average fields.
method Theory-guided machine learning approach using generalized Bayesian algorithm.
result Fixed-time and any-time PAC Bayesian bounds for ensemble forecasts.
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.
Extends spectral number variance convergence to random matrix ensembles for twisted Laplacians.
problem Spectral number variance convergence for twisted Laplacians and Dirac operators.
method Extends Rudnick's approach to Gaussian ensembles for twisted Laplacians and Dirac operators.
result Convergence to Gaussian ensembles for twisted Laplacians and Dirac operators.
We analyze the question whether sliding window time averages applied to stationary increment processes converge to a limit in probability. The question centers on averages, correlations, and densities constructed via time averages of the increment x(t,T)=x(t+T)-x(t)and the assumption is that the increment is distribute…
MAC combines models without locking them, improving ensemble performance.
problem Improving ensemble learning performance with flexibility.
method Model agnostic combination technique that dynamically combines models.
result MAC outperforms classical methods and competitive to boosting.