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.
The paper connects neural network ensembles to Bayesian inference using variational methods.
problem Explaining the behavior of ensemble methods in neural networks.
method Deriving conditions for ensemble optimization to reduce divergence to the posterior distribution.
result Ensemble methods can be a valid alternative to approximate Bayesian inference.
Ensemble sampling approximates Thompson sampling for complex models.
problem Computational intractability of exact posterior distributions.
method Thompson sampling approximation with information-theoretic concepts.
result Established a first rigorous regret bound for ensemble sampling.
This paper introduces TNTK to study infinite soft tree ensembles.
problem Understanding the behavior of infinite soft tree ensembles.
method Introduced Tree Neural Tangent Kernel (TNTK) to analyze infinite soft tree ensembles.
result Identified several non-trivial properties of infinite soft tree ensembles.
New method uses SHapley Additive Explanations to identify anomaly detectors with complementary behaviors.
problem Challenges in unsupervised anomaly detection due to diverse data distributions and lack of labels.
method Characterize anomaly detectors using SHapley Additive Explanations to measure feature importance and similarity.
result Detectors with similar explanations produce correlated anomaly scores, while those with divergent explanations are complementary.
Diverse projection ensembles improve distributional reinforcement learning.
problem Learning the distribution of returns in reinforcement learning.
method Combining multiple projection methods to improve model diversity and exploration.
result Diverse projection ensembles lead to significant performance improvements in exploration tasks.
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.
Study analyzes player churn and purchasing behavior in games.
problem Retaining players and predicting churn in video games.
method Deep behavioral analysis and ensemble learning models.
result Discarding certain churners improves prediction models.
CrescendoNet is a simple deep CNN outperforming others on benchmark datasets.
problem Improving performance of deep neural networks without residual connections.
method Stacking simple blocks with independent convolution paths, increasing depth linearly.
result CrescendoNet with 15 layers and 4.1M parameters outperforms DenseNet-BC with 250 layers and 15.3M parameters.
Unified model predicts disease spread using EMD and ensemble learning.
problem Predicting fluctuating disease spread and individual behavior.
method SEIS-A framework, EMD decomposition, ensemble learning, on-line query data.
result The method outperforms other methods in predicting HFMD consultation rates.
We study dynamical behavior of the Chinese stock markets by investigating the statistical properties of daily ensemble returns and varieties defined respectively as the mean and the standard deviation of the ensemble daily price returns of a portfolio of stocks traded in China's stock markets on a given day. The distri…
We select the 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 study the ensemble return distribution for each trading day and we find that the symmetry properties of the ensem…
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.
The combination of multiple classifiers using ensemble methods is increasingly important for making progress in a variety of difficult prediction problems. We present a comparative analysis of several ensemble methods through two case studies in genomics, namely the prediction of genetic interactions and protein functi…
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.
The paper improves QD policy ensembles using distribution ratio estimators.
problem Training diverse and high-quality reinforcement learning agents.
method Using Stein variational gradient descent and distribution ratio estimators.
result The method generates diverse and high-quality reinforcement learning agents.
We formalize the notion of a pseudo-ensemble, a (possibly infinite) collection of child models spawned from a parent model by perturbing it according to some noise process. E.g., dropout (Hinton et. al, 2012) in a deep neural network trains a pseudo-ensemble of child subnetworks generated by randomly masking nodes in t…
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.
A new method creates simpler, more interpretable decision trees from complex ensembles.
problem Complex tree ensembles reduce interpretability and control over machine learning models.
method Dynamic-programming based algorithm for finding a minimum-size decision tree.
result Optimal born-again trees are simpler and more interpretable than original ensembles.
New nonlinear smoothers improve state estimation in chaotic systems.
problem Improving state estimation in chaotic dynamical systems with non-Gaussian behavior.
method Developed nonlinear backward ensemble transport smoothers with parameterization and regularization of transport maps.
result Nonlinear smoothers yield lower estimation error than conventional methods for comparable model evaluations.
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.
Enhanced recommender system using ensemble learning and graph embedding.
problem Challenges in selecting relevant data for users from large datasets.
method Group classification, ensemble learning, fuzzy rules, decision tree, graph embedding.
result High efficiency of the presented method on MovieLens datasets.
We consider different levels of complexity which are observed in the empirical investigation of financial time series. We discuss recent empirical and theoretical work showing that statistical properties of financial time series are rather complex under several ways. Specifically, they are complex with respect to their…
Hypermodels improve exploration efficiency and accuracy.
problem Efficiently approximating Thompson sampling with large ensembles.
method Introducing hypermodels as a generalization of ensembles, including linear and neural network hypermodels.
result Hypermodels enable more accurate exploration and performance gains over Thompson sampling.
Investigates financial portfolios using quantum system analogies and clustering properties.
problem Understanding the behavior and clustering of correlated financial assets.
method Analogy with quantum systems, development of eigenportfolios, and use of metrics for participation matrix.
result Shows localized states in the correlation matrix of digital currencies, indicating clustering behavior.
Paper tackles RL in real environments using model ensembles.
problem Learning optimal policies in real environments with inaccurate simulators.
method Approximates real environment using linear combination of pre-trained models, learns near-optimal policies with polynomial sample complexity.
result Provably efficient algorithm with polynomial sample complexity in number of unknown parameters.
Paper analyzes soft tree ensembles using NTK, finding only leaf count matters.
problem Understanding impact of various tree architectures in ensemble learning.
method Formulated and analyzed Neural Tangent Kernel (NTK) for soft tree ensembles.
result Only the number of leaves at each depth is relevant for tree architecture in ensemble learning.
New method grows many trees in parallel and selects a compact subset for optimization.
problem Creating interpretable and compact tree ensembles.
method Growing a large pool of trees in parallel with loss optimization on a subset.
result Compact tree ensemble achieves lower loss and misclassification error.
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…
Anti-Distillation improves reproducibility of deep networks by making ensemble predictions more diverse.
problem Deep networks are prone to high prediction differences, making them less reproducible.
method Anti-Distillation uses ensembles to force predictions to be more different and diverse.
result Anti-Distillation reduces prediction differences by making ensemble predictions more diverse.
Study improves detection of cryptocurrency pump-and-dump schemes.
problem Class imbalance in P&D detection due to rare events.
method Synthetic Minority Oversampling Technique (SMOTE) and ensemble learning models.
result XGBoost and LightGBM achieved high recall rates (94.87% and 93.59%) with strong F1-scores.
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.
This research improves neural network uncertainty estimates and reliability.
problem Lack of inherent uncertainty estimates and variability in softmax scores.
method Ensemble-based Dirichlet modeling with method of moments estimator.
result Improved stability and predictive uncertainty estimates.
The paper analyzes an ensemble of randomly projected linear discriminants for high-dimensional data.
problem Classification issues in small samples of high-dimensional data.
method Asymptotic analysis using random matrix theory.
result The ensemble offers a performance advantage under certain conditions.
Deep learning agents negotiate contracts with prosocial or selfish behaviors.
problem Training agents to negotiate contracts with varying behaviors.
method Multi-Agent Reinforcement Learning, modeling prosocial and selfish behaviors, training a meta agent.
result Trained agents hold their own against human players and emulate human behavior.
Tree ensemble method tackles multi-objective constrained optimization in energy systems.
problem Complex, multi-objective, and constrained optimization problems in energy systems.
method Data-driven tree ensemble approach for black-box problems with heterogeneous variable spaces.
result Competitive performance and sampling efficiency compared to state-of-the-art tools.
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⋆ tends to be in the overparameterized regime for the full-ensemble estimator. New method handles uncertainty in adversarial attacks using ensemble noise simulation.
problem Uncertainty in adversarial attacks on neural networks.
method Simulates attacker's noisy perturbation using various gradient-based attack algorithms and a pre-processing Denoising Autoencoder (DAE) defense.
result Significant improvements in post-attack accuracy with the proposed ensemble-trained defense.
We consider the problem of estimating the support of a vector β∗∈Rp based on observations contaminated by noise. A significant body of work has studied behavior of ℓ1-relaxations when applied to measurement matrices drawn from standard dense ensembles (e.g., Gaussian, Bernoulli). In this paper,…
We investigate the variety of a portfolio of stocks in normal and extreme days of market activity. We show that the variety carries information about the market activity which is not present in the single-index model and we observe that the variety time evolution is not time reversal around the crash days. We obtain th…
The paper introduces eigen-portfolios using PCA to improve portfolio construction in finance.
problem Overfitting and poor generalization in selecting a single eigen-portfolio.
method Principal Component Analysis (PCA) to derive eigen-portfolios from asset return correlation matrices.
result An ensemble strategy combining multiple top-performing eigen-portfolios significantly improves out-of-sample performance.
Study explores cyberbullying datasets and classifier generalization.
problem Cyberbullying detection across different online communities.
method Analysis of various cyberbullying datasets and classifier generalization.
result Insight into classifier generalization power and interaction.
Meta-DES uses meta-learning to dynamically select competent classifiers for ensemble learning.
problem Dynamic selection of classifiers based on limited training data.
method Meta-learning approach to estimate competence of classifiers using multiple meta-features.
result Meta-DES significantly improves classification accuracy compared to existing techniques.
Bayesian EnKF improves sentence comprehension uncertainty modeling.
problem Uncertainty in human language comprehension, especially with ambiguous inputs.
method Bayesian framework using ensemble Kalman filter (EnKF) for uncertainty quantification.
result Enhanced model's ability to approximate human cognitive processing with linguistic ambiguities.
Neurons in cortical circuits exhibit coordinated spiking activity, and can produce correlated synchronous spikes during behavior and cognition. We recently developed a method for estimating the dynamics of correlated ensemble activity by combining a model of simultaneous neuronal interactions (e.g., a spin-glass model)…
New insights into how randomization affects greedy model selection.
problem Understanding the impact of feature subsampling on greedy model selection.
method Investigated greedy forward selection with feature subsampling, proving effects on bias and variance.
result Ensembling with feature subsampling reduces both bias and variance, unlike convex base learners.
The paper proposes a method to verify tree ensembles by reasoning about potential instances.
problem Understanding how tree ensembles extrapolate to unseen data.
method Prunes input space and uses divide and conquer approach for incremental answers.
result Shows the approach's usefulness on various use cases.
EBQL reduces bias in Q-learning for improved performance.
problem Over- and under-estimation biases in Q-learning degrade performance.
method Ensemble Bootstrapping to reduce both over- and under-estimation biases.
result EBQL outperforms other Q-learning methods in Atari games.