Residual networks' depth is mathematically equivalent to expanding an implicit ensemble size.
problem Understanding why deep residual networks are effective.
method Formal analysis of residual networks as ensembles of shallow models.
result Increasing network depth is equivalent to expanding the size of an implicit ensemble, revealing a hierarchical structure.
Deep learning has become very popular for tasks such as predictive modeling and pattern recognition in handling big data. Deep learning is a powerful machine learning method that extracts lower level features and feeds them forward for the next layer to identify higher level features that improve performance. However, …
DHEN improves CVR prediction for ads with multitask learning and auxiliary loss.
problem Predicting conversion rates in ad-recommendation systems.
method DHEN integrates multiple feature-crossing modules and uses a multitask learning framework, ablation studies, and self-supervised auxiliary loss.
result DHEN achieves state-of-the-art performance in CVR prediction.
Long-lead forecasting for spatio-temporal systems can often entail complex nonlinear dynamics that are difficult to specify it a priori. Current statistical methodologies for modeling these processes are often highly parameterized and thus, challenging to implement from a computational perspective. One potential parsim…
Transformer models perform slower than convolutional networks in learning hierarchical language structures.
problem Understanding how neural networks learn hierarchical language structures.
method Theoretical scaling laws and empirical validation of neural network performance.
result Convolutional networks outperform transformers in learning hierarchical language structures.
Nowadays, deep neural networks (DNNs) have become the main instrument for machine learning tasks within a wide range of domains, including vision, NLP, and speech. Meanwhile, in an important case of heterogenous tabular data, the advantage of DNNs over shallow counterparts remains questionable. In particular, there is …
S2D efficiently trains models to estimate uncertainty without increasing resource costs.
problem Efficiently estimating uncertainty in deep learning models for safety-critical applications.
method Self-distribution distillation (S2D) approach to train a single model for uncertainty estimation.
result S2D models outperform standard models and Monte-Carlo dropout in uncertainty estimation.
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.
Proves deep networks can learn hierarchical structures efficiently.
problem Understanding how deep networks learn hierarchical structures in data.
method Random Hierarchy Models, gradient-based methods, layerwise training.
result Proves deep networks can efficiently learn hierarchical structures.
Deep learning has achieved impressive prediction accuracies in a variety of scientific and industrial domains. However, the nested non-linear feature of deep learning makes the learning highly non-transparent, i.e., it is still unknown how the learning coordinates a huge number of parameters to achieve a decision makin…
Graph-EFM models weather uncertainty with graph-based ensembles.
problem Accurately capturing forecast uncertainty in chaotic weather.
method Flexible latent-variable formulation with hierarchical graph construction.
result Graph-EFM ensembles achieve equivalent or lower errors than deterministic models.
Improved neural network regression uncertainty estimation.
problem Neural networks lack classical uncertainty due to finite data.
method Bootstrapped Deep Ensembles, incorporating parametric bootstrap.
result Significantly improved uncertainty estimation compared to standard Deep Ensembles.
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.
This work evaluates uncertainty in deep Gaussian processes.
problem Uncertainty quantification in deep Gaussian processes.
method Hierarchical deep Gaussian processes (DGPs) and Deep Sigma Point Processes (DSPPs) evaluated on regression and classification tasks.
result DSPPs provide strong in-distribution calibration but are less robust under distribution shift compared to ensembles.
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.
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.
EASIER-net uses sparse networks to improve prediction accuracy for high-dimensional data.
problem Limited use of neural networks in high-dimensional data with small samples.
method Ensemble by Averaging Sparse-Input Hierarchical networks (EASIER-net) with small modifications to neural network architecture and training procedure.
result EASIER-net achieves higher prediction accuracy than off-the-shelf methods on average.
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.
Deep neural networks have revolutionized many fields such as computer vision and natural language processing. Inspired by this recent success, deep learning started to show promising results for Time Series Classification (TSC). However, neural networks are still behind the state-of-the-art TSC algorithms, that are cur…
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.
Method detects neural network equivalence via matrix ensembles and spectral analysis.
problem Detecting equivalence among different deep learning architectures.
method Generating Mixed Matrix Ensembles (MMEs) and matching to conjugate circular ensembles.
result Empirical evidence shows vanishing differences in spectral densities with long tail decay rates.
Researchers improve deep ensemble forecast aggregation methods.
problem Aggregating forecast distributions from deep ensembles for better predictive performance.
method Comprehensive analysis of twelve benchmark data sets, comparing probability- and quantile-based aggregation methods for three neural network-based approaches.
result A general quantile aggregation framework for deep ensembles improves predictive performance in various settings.
Deep ensembles outperform deep ensembles of Bayesian neural networks on in-distribution data.
problem Improving model calibration and uncertainty quantification in Bayesian Neural Networks.
method Systematic investigation of deep ensembles of Bayesian Neural Networks across various datasets and architectures.
result Deep ensembles consistently outperform deep ensembles of Bayesian neural networks on in-distribution data.
Efficiently builds diverse sub-model ensembles for robust self-supervised learning.
problem Challenges in diversity and efficiency of deep ensembles for self-supervised representation learning.
method Ensemble of independent sub-networks with a new loss function for diversity.
result Significantly improves prediction reliability and model calibration.
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.
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.
The paper explains implicit regularization in hierarchical tensor factorization and deep CNNs.
problem Understanding implicit regularization in complex neural network architectures.
method Theoretical analysis using dynamical systems to overcome challenges in hierarchy.
result Established implicit regularization towards low hierarchical tensor rank, equivalent to locality in CNNs.
Improved neural network ensembles using Stein Variational Newton updates.
problem Lack of efficient second-order information in current ensemble methods.
method Proposes a novel approximate Bayesian inference method integrating Stein Variational Newton updates with scalable Hessian approximations.
result Significantly faster convergence and more accurate posterior distribution approximations.
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…
Convolutional networks outperform shallow classifiers on certain tasks due to hierarchical structure.
problem Understanding why convolutional networks outperform shallow classifiers on specific tasks.
method Approximation theory, visual tasks with deterministic scrambling, and network performance evaluation.
result Hierarchical structure is crucial for convolutional networks' performance on certain tasks, but not all.
Paper proposes a deep learning model to predict stock prices using sentiment analysis.
problem Predicting future stock movement using financial textual and numerical data.
method A blending ensemble deep learning model with two levels of RNNs, LSTM, and GRU followed by a fully connected neural network.
result The model improves prediction accuracy compared to traditional 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/mL−1, leading to significant error rate decreases. Bayesian deep ensembles improve prediction accuracy in various settings.
problem Improving prediction accuracy of deep ensembles in out-of-distribution settings.
method Introducing a randomised, untrainable function to each ensemble member, enabling a posterior predictive distribution interpretation.
result Bayesian deep ensembles make more conservative predictions and outperform standard ensembles in various tasks.
Auto-Ensemble automates deep learning model ensembling with adaptive learning rate scheduling.
problem Difficulty in collecting diverse and accurate deep learning models through single training.
method Auto-Ensemble collects model checkpoints and uses adaptive learning rate scheduling to ensemble them.
result Ensembled models converge to various local optima, improving performance on few-shot learning.
FoRDE uses input gradients to improve neural network ensembles.
problem Improving neural network ensembles for robustness and accuracy.
method Proposes FoRDE, an ensemble learning method based on ParVI, which repels function space by input gradients.
result FoRDE significantly outperforms DEs and other ensemble methods in accuracy and calibration.
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…
Several real problems ranging from text classification to computational biology are characterized by hierarchical multi-label classification tasks. Most of the methods presented in literature focused on tree-structured taxonomies, but only few on taxonomies structured according to a Directed Acyclic Graph (DAG). In thi…
Deep ensembles have been empirically shown to be a promising approach for improving accuracy, uncertainty and out-of-distribution robustness of deep learning models. While deep ensembles were theoretically motivated by the bootstrap, non-bootstrap ensembles trained with just random initialization also perform well in p…
Memory split advantage: thinner networks outperform a single wide network.
problem Optimizing deep learning models with limited memory.
method Investigated training a single wide network vs. an ensemble of thinner networks with the same total number of parameters.
result An ensemble of several thinner networks outperforms a single wide network for large memory budgets.
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.
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.
Combines Laplace approximations of deep networks for better uncertainty quantification.
problem Overconfident predictions on outliers in deep learning models.
method Gaussian mixture model posterior using weighted sum of Laplace approximations of pre-trained deep networks.
result Mitigates overconfidence 'far away' from training data.
This paper connects RND, deep ensembles, and Bayesian inference, providing a unified theoretical perspective.
problem Uncertainty quantification in deep learning models.
method Analysis of Random Network Distillation (RND) within the neural tangent kernel framework.
result The uncertainty signal from RND is equivalent to the predictive variance of a deep ensemble and can be made to mirror the centered posterior predictive distribution of Bayesian inference.
A new method reduces memory usage for deep neural networks ensembles.
problem Reducing memory footprint of ensemble methods for deep learning.
method Extract multiple sub-networks from a single neural network through end-to-end optimization.
result Achieves higher or comparable accuracy with significantly less memory usage.
Study on ensemble, distillation, and self-distillation in deep learning models.
problem Improving test accuracy in deep learning models using ensemble and distillation methods.
method Formal study of ensemble and distillation, considering multi-view data structure.
result Proven that ensemble and distillation can improve test accuracy in deep learning models, and the superior performance can be distilled into a single model.
Paper introduces WWAggr for ensemble CPD, improving accuracy and decision threshold selection.
problem Challenges in detecting abrupt distribution shifts in high-dimensional data streams.
method Introduces WWAggr, a novel task-specific ensemble aggregation method based on Wasserstein distance.
result Demonstrates WWAggr outperforms standard aggregation techniques and decision threshold selection.
Fast estimates of model uncertainty are required for many robust robotics applications. Deep Ensembles provides state of the art uncertainty without requiring Bayesian methods, but still it is computationally expensive. In this paper we propose deep sub-ensembles, an approximation to deep ensembles where the core idea …
Single model estimates ensemble uncertainty efficiently.
problem Efficient uncertainty quantification in deep learning models.
method Contextual similarity distillation, approximating ensemble variance with a single model.
result Single model estimates predictive variance with a single forward pass.