arXiv research

Ens-CGP synthesizes ensemble-based inference with Gaussian processes.

Enhances model OOD detection by diversifying feature representation.

New technique prevents Q-learning collapse by maximizing diversity among ensembles.

Temporal networks are ubiquitous and evolve over time by the addition, deletion, and changing of links, nodes, and attributes. Although many relational datasets contain temporal information, the majority of existing techniques in relational learning focus on static snapshots and ignore the temporal dynamics. We propose…

Efficiently builds diverse sub-model ensembles for robust self-supervised learning.

Ensemble++ uses shared-factor ensembles to scale Thompson Sampling for linear and nonlinear bandits.

Paper proposes FVC for functional data classification.

New method reduces bias in NLI models using ensemble adversarial training.

Shallow trees in ensemble models make models more interpretable and sometimes better.

TREX explains tree ensembles by identifying key training examples.

An ensemble of randomized NNs improves time series forecasting accuracy.

Paper tackles overestimation bias in continuous control, improving performance by 25%.

The success of deep learning in medical imaging is mostly achieved at the cost of a large labeled data set. Semi-supervised learning (SSL) provides a promising solution by leveraging the structure of unlabeled data to improve learning from a small set of labeled data. Self-ensembling is a simple approach used in SSL to…

Diverse projection ensembles improve distributional reinforcement learning.

This paper improves SSL methods using ensemble techniques with data-dependent weighted losses.

Deep learning ensemble detects social media rumors faster.

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 …

RST improves environmental time series classification accuracy using randomized B-spline trees.

One of the promising methods for the treatment of complex diseases such as cancer is combinational therapy. Due to the combinatorial complexity, machine learning models can be useful in this field, where significant improvements have recently been achieved in determination of synergistic combinations. In this study, we…

In this study we examined the question of how error correction occurs in an ensemble of deep convolutional networks, trained for an important applied problem: segmentation of Electrocardiograms(ECG). We also explore the possibility of using the information about ensemble errors to evaluate a quality of data representat…

Study forecasts monthly electricity demand using pattern similarity-based methods.

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…

Representation learning on graphs has been gaining attention due to its wide applicability in predicting missing links, and classifying and recommending nodes. Most embedding methods aim to preserve certain properties of the original graph in the low dimensional space. However, real world graphs have a combination of s…

New research shows deep models learn sparse features, limiting transfer learning; ensembling improves performance.

BI-EqNO improves Bayesian inference with flexible neural operators.

Paper proposes a new method for probabilistic electricity price forecasting.

Gestalt combines two models to improve SQuAD2.0 performance.

A test assesses the calibration of set-based epistemic uncertainty representations.

A new semi-supervised ensemble algorithm called XGBOD (Extreme Gradient Boosting Outlier Detection) is proposed, described and demonstrated for the enhanced detection of outliers from normal observations in various practical datasets. The proposed framework combines the strengths of both supervised and unsupervised mac…

The paper extends calibration to sets of probabilistic classifiers, finding many ensembles are poorly calibrated.

Evolutionary algorithms improve decision tree ensembles.

Fibonacci Ensembles use Fibonacci weights to improve ensemble learning, inspired by natural growth patterns.

Representation learning, especially which by using deep learning, has been widely applied in classification. However, how to use limited size of labeled data to achieve good classification performance with deep neural network, and how can the learned features further improve classification remain indefinite. In this pa…

In multiple instance learning, objects are sets (bags) of feature vectors (instances) rather than individual feature vectors. In this paper we address the problem of how these bags can best be represented. Two standard approaches are to use (dis)similarities between bags and prototype bags, or between bags and prototyp…

ES reduces high-probability regret in stochastic linear bandits.

A simple approach to obtaining uncertainty-aware neural networks for regression is to do Bayesian linear regression (BLR) on the representation from the last hidden layer. Recent work [Riquelme et al., 2018, Azizzadenesheli et al., 2018] indicates that the method is promising, though it has been limited to homoscedasti…

Complete construction for Lie groups of types F4, E6, E7, E8.

Paper introduces EnDKF for more accurate pose tracking.

Deep learning improves chaotic dynamics filtering without ensemble.

Bayesian EnKF improves sentence comprehension uncertainty modeling.

There are now a broad range of time series classification (TSC) algorithms designed to exploit different representations of the data. These have been evaluated on a range of problems hosted at the UCR-UEA TSC Archive (www.timeseriesclassification.com), and there have been extensive comparative studies. However, our und…

This paper explores online learning of dynamics and state using ensemble Kalman filters.

Offline Signature Verification (OSV) is a challenging pattern recognition task, especially in presence of skilled forgeries that are not available during training. This study aims to tackle its challenges and meet the substantial need for generalization for OSV by examining different loss functions for Convolutional Ne…

Ensemble methods, traditionally built with independently trained de-correlated models, have proven to be efficient methods for reducing the remaining residual generalization error, which results in robust and accurate methods for real-world applications. In the context of deep learning, however, training an ensemble of…

Existing information-theoretic frameworks based on maximum entropy network ensembles are not able to explain the emergence of heterogeneity in complex networks. Here, we fill this gap of knowledge by developing a classical framework for networks based on finding an optimal trade-off between the information content of a…

Unified representation for tree ensembles indexed by nodes

Improved anti-cancer drug sensitivity prediction using REFINED CNN ensemble learning.

DVE uses GPs on DNN outputs to provide UQ without retraining.