arXiv research

Self-paced ensemble learning improves audio classification models.

A new framework boosts classifier performance on imbalanced data.

Proposes an ensemble framework for outlier detection with embedded feature selection.

Adversarial learning for mixture Hawkes processes improves performance.

Self-paced learning (SPL) mimics the cognitive process of humans, who generally learn from easy samples to hard ones. One key issue in SPL is the training process required for each instance weight depends on the other samples and thus cannot easily be run in a distributed manner in a large-scale dataset. In this paper,…

Proposes a self-paced multi-label learning method to handle diverse labels efficiently.

Partial label learning (PLL) aims to solve the problem where each training instance is associated with a set of candidate labels, one of which is the correct label. Most PLL algorithms try to disambiguate the candidate label set, by either simply treating each candidate label equally or iteratively identifying the true…

This paper introduces self-paced task selection to multitask learning, where instances from more closely related tasks are selected in a progression of easier-to-harder tasks, to emulate an effective human education strategy, but applied to multitask machine learning. We develop the mathematical foundation for the appr…

Principal Component Analysis (PCA) is a popular tool for dimensionality reduction and feature extraction in data analysis. There is a probabilistic version of PCA, known as Probabilistic PCA (PPCA). However, standard PCA and PPCA are not robust, as they are sensitive to outliers. To alleviate this problem, this paper i…

A new framework for deep learning from multiple experts tackles long-tailed data issues.

Tissue characterization has long been an important component of Computer Aided Diagnosis (CAD) systems for automatic lesion detection and further clinical planning. Motivated by the superior performance of deep learning methods on various computer vision problems, there has been increasing work applying deep learning t…

Selecting the most appropriate data examples to present a deep neural network (DNN) at different stages of training is an unsolved challenge. Though practitioners typically ignore this problem, a non-trivial data scheduling method may result in a significant improvement in both convergence and generalization performanc…

By simulating the easy-to-hard learning manners of humans/animals, the learning regimes called curriculum learning~(CL) and self-paced learning~(SPL) have been recently investigated and invoked broad interests. However, the intrinsic mechanism for analyzing why such learning regimes can work has not been comprehensivel…

Paper proposes IRL methods for limited interaction scenarios.

It is known that Boosting can be interpreted as a gradient descent technique to minimize an underlying loss function. Specifically, the underlying loss being minimized by the traditional AdaBoost is the exponential loss, which is proved to be very sensitive to random noise/outliers. Therefore, several Boosting algorith…

Multi-task clustering (MTC) has attracted a lot of research attentions in machine learning due to its ability in utilizing the relationship among different tasks. Despite the success of traditional MTC models, they are either easy to stuck into local optima, or sensitive to outliers and noisy data. To alleviate these p…

SPCA improves PCA by learning from simple to complex samples.

Self-paced learning and hard example mining re-weight training instances to improve learning accuracy. This paper presents two improved alternatives based on lightweight estimates of sample uncertainty in stochastic gradient descent (SGD): the variance in predicted probability of the correct class across iterations of …

Improves sample efficiency in reinforcement learning by controlling task distribution.

Automatically generates a deep RL curriculum for faster and more stable learning.

Multi-headed ensembles boost model performance with faster training.

This paper explores how diverse neural network ensembles improve prediction accuracy and robustness against deception.

Transforms ensemble predictions to maintain interpretability.

Overparameterized ensembles don't offer generalization benefits over single large models.

Stock trend prediction plays a critical role in seeking maximized profit from stock investment. However, precise trend prediction is very difficult since the highly volatile and non-stationary nature of stock market. Exploding information on Internet together with advancing development of natural language processing an…

New method creates diverse neural ensembles for better uncertainty estimation and robustness.

New method certifies joint adversarial robustness of model ensembles.

SelectNet selectively adds unlabelled data to balance imbalanced training data.

Embedded ensembles improve neural network performance efficiently.

A framework preserves uncertainty in ensemble distillation.

Study pitfalls of deep learning ensembles in uncertainty estimation.

New hyperparameter ensembles boost neural network performance and uncertainty.

Incremental learning suffers from two challenging problems; forgetting of old knowledge and intransigence on learning new knowledge. Prediction by the model incrementally learned with a subset of the dataset are thus uncertain and the uncertainty accumulates through the tasks by knowledge transfer. To prevent overfitti…

Proposes a method to reduce ensemble size while maintaining accuracy.

ECV method optimizes ensemble parameters for randomized ensembles.

The paper explores dynamic ensembles for multi-step forecasting.

Bayesian deep ensembles improve prediction accuracy in various settings.

RCAM-based ensemble combines binary classifiers using similarity and vote scheme.

Heterogeneous ensembles built from the predictions of a wide variety and large number of diverse base predictors represent a potent approach to building predictive models for problems where the ideal base/individual predictor may not be obvious. Ensemble selection is an especially promising approach here, not only for …

High-capacity neural network ensembles often benefit more from high-capacity models than from increased diversity.

New method reduces ensemble size for linear bandits, achieving near optimal regret.

Jointly tuning ensemble models improves performance and uncertainty calibration.

This paper reviews weighted clustering ensemble methods.

Proposes a new method for deep ensembles that improves accuracy and calibration.

Paper analyzes uncertainty metrics in ensemble learning for healthcare AI.

We propose and evaluate alternative ensemble schemes for a new instance based learning classifier, the Randomised Sphere Cover (RSC) classifier. RSC fuses instances into spheres, then bases classification on distance to spheres rather than distance to instances. The randomised nature of RSC makes it ideal for use in en…

Hydra distills ensemble models into a single model while preserving diversity and uncertainty.

A fast method estimates stability of ensemble feature selectors.