The paper proposes a test to assess rater accuracy while accounting for rater covariates.
problem Assessing the accuracy of raters in medical imaging and forensic studies.
method Covariate-adjusted homogeneity test to determine differences in accuracy among multiple rater groups.
result The proposed test identifies statistically significant differences among five participant groups in a face recognition study.
Neural network accuracy improves with denser training samples.
problem Improving neural network accuracy on unseen test samples.
method Bounding empirical training error smoothed across activation regions and using it to discard high-risk test samples.
result Discarding high-risk test samples based on error bounds improves prediction accuracy by up to 20%.
The article explains how to estimate confusion matrices for classifiers using unlabeled data.
problem Estimating sensitivity and specificity of binary medical diagnostic tests without gold standard tests.
method Modifying diagnostic test solutions to estimate confusion matrices for classifiers on unlabeled data.
result The approach can be used to estimate accuracy statistics for supervised or unsupervised binary classifiers on unlabeled data.
We build new test sets for the CIFAR-10 and ImageNet datasets. Both benchmarks have been the focus of intense research for almost a decade, raising the danger of overfitting to excessively re-used test sets. By closely following the original dataset creation processes, we test to what extent current classification mode…
TARP tests accuracy of generative posterior estimators.
problem Assessing the accuracy of posterior estimators from generative models.
method TARP coverage testing method.
result TARP can detect inaccurate inferences in high-dimensional spaces.
Enhances image quality to improve test-time adaptation accuracy.
problem Reducing accuracy loss due to distribution shift in deep networks.
method Integrates image enhancement with TTA methods to reduce prediction uncertainty.
result TECA method increases accuracy of TTA methods without hyperparameters.
Test log-likelihood comparisons can be misleading.
problem Misinterpretation of test log-likelihood in model comparison.
method Simple examples of model comparison and forecast accuracy.
result Test log-likelihood does not always correlate with model accuracy.
Regularizing for or against class selectivity in DNNs improves test accuracy.
problem The necessity and sufficiency of class selectivity in DNNs.
method Direct regularization of class selectivity in convolutional neural networks.
result Reducing class selectivity improves test accuracy, while increasing it decreases it.
SGD with large learning rates can achieve better test accuracy than expected.
problem SGD with large learning rates often outperforms expected convergence bounds.
method Proved that SGD with small learning rates stays close to gradient flow path on modified loss.
result Explicitly adding an implicit regularizer to the loss improves test accuracy.
Single tree outperforms random forest in testing accuracy.
problem The challenge of improving single decision tree performance.
method Gradient-based entire tree optimization framework, scaled sigmoid approximation, numerical stability algorithm, subtree polish strategy.
result Optimized single tree outperforms classic random forest by 2.03% on average.
We study efficient deep learning training algorithms that process received wireless signals, if a test Signal to Noise Ratio (SNR) estimate is available. We focus on two tasks that facilitate source identification: 1- Identifying the modulation type, 2- Identifying the wireless technology and channel in the 2.4 GHz ISM…
New group testing method uses Belief Propagation for accurate screening.
problem Efficiently identifying infected samples in large groups with minimal tests.
method Belief Propagation algorithm for inference in group testing schemes.
result Significantly increased accuracy of infection identification with fewer tests.
This technical report describes a practical field test on word-image classification in a very large collection of more than 300 diverse handwritten historical manuscripts, with 1.6 million unique labeled images and more than 11 million images used in testing. Results indicate that several deep-learning tests completely…
A machine learning configuration refers to a combination of preprocessor, learner, and hyperparameters. Given a set of configurations and a large dataset randomly split into training and testing set, we study how to efficiently select the best configuration with approximately the highest testing accuracy when trained f…
Research proposes an ensemble learning model for efficient software defect prediction.
problem Efficient and cost-effective software testing to minimize project resources.
method Machine learning analysis on different datasets using KNN, Decision Tree, SVM, and Naïve Bayes.
result Ensemble learning model outperforms other techniques in accuracy, precision, recall, and F1-score.
Improved deep kernel machine achieves 94.5% test accuracy on CIFAR-10.
problem Achieving high accuracy on complex tasks like image classification.
method Stochastic kernel regularisation to add noise to learned Gram matrices.
result 94.5% test accuracy on CIFAR-10.
This paper presents a comparison of six machine learning (ML) algorithms: GRU-SVM (Agarap, 2017), Linear Regression, Multilayer Perceptron (MLP), Nearest Neighbor (NN) search, Softmax Regression, and Support Vector Machine (SVM) on the Wisconsin Diagnostic Breast Cancer (WDBC) dataset (Wolberg, Street, & Mangasarian, 1…
Optimizes test set size for accurate diagnosis using machine learning.
problem Determining the minimum test set size for accurate diagnosis.
method Proposes machine learning methods (LASSO and SVM) to predict optimal test set size.
result SVM achieves 90.4% accuracy with a reduced test set by 35.24%.
New measure assesses neural network models' functional similarity.
problem Measuring functional similarity between similar-performing neural networks.
method Robust nonparametric hypothesis testing framework.
result Proposed measure assesses neural networks' functional similarity.
Machine learning is currently dominated by largely experimental work focused on improvements in a few key tasks. However, the impressive accuracy numbers of the best performing models are questionable because the same test sets have been used to select these models for multiple years now. To understand the danger of ov…
Proposes a new method to improve Bayesian computation accuracy using flexible classification.
problem Bayesian computations accuracy check using rank-based simulation-based calibration has limitations.
method Replaces marginal rank test with a flexible classification approach that learns from data.
result Improves statistical power and provides an interpretable divergence measure of miscalibration.
Effective medical test suggestions benefit both patients and physicians to conserve time and improve diagnosis accuracy. In this work, we show that an agent can learn to suggest effective medical tests. We formulate the problem as a stage-wise Markov decision process and propose a reinforcement learning method to train…
When a feed-forward neural network (FNN) is trained for source ranging in an ocean waveguide, it is difficult evaluating the range accuracy of the FNN on unlabeled test data. A fitting-based early stopping (FEAST) method is introduced to evaluate the range error of the FNN on test data where the distance of source is u…
SliceOut speeds up deep learning training without sacrificing accuracy.
problem Frequent model re-training and large model training workloads in deep learning.
method SliceOut uses dropout-inspired scheme to drop contiguous sets of units at random, leveraging GPU memory layout.
result 10-40% speedups and memory reduction with minimal accuracy loss.
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.
Statistical test detects model degradations in optimized language models.
problem Detecting model degradations in optimized language models.
method Statistical hypothesis testing framework based on McNemar's test.
result Even small accuracy degradations (0.3%) can be attributed to actual degradations, not noise.
FL's early training phase significantly impacts final test accuracy.
problem Understanding how early phases affect FL's final test accuracy.
method Generalized Fisher Information Matrix (FedFIM) to FL.
result FL exhibits critical learning periods where small errors can have large impacts.
In this paper we propose strategies for estimating performance of a classifier when labels cannot be obtained for the whole test set. The number of test instances which can be labeled is very small compared to the whole test data size. The goal then is to obtain a precise estimate of classifier performance using as lit…
Paper shows adversarial training can be fooled by new type of noise.
problem Adversarial training can be fooled by new types of noise.
method Designing ADVIN, a new type of inducing noise.
result ADVIN can degrade adversarial training robustness by 99.9%.
Convolutional neural networks (CNNs) are commonly trained using a fixed spatial image size predetermined for a given model. Although trained on images of aspecific size, it is well established that CNNs can be used to evaluate a wide range of image sizes at test time, by adjusting the size of intermediate feature maps.…
In this study, a novel sparsity-driven weighted ensemble classifier (SDWEC) that improves classification accuracy and minimizes the number of classifiers is proposed. Using pre-trained classifiers, an ensemble in which base classifiers votes according to assigned weights is formed. These assigned weights directly affec…
FastForest boosts Random Forest speed by 24%.
problem Efficiency in processing speed for Random Forest.
method Subsample Aggregating, Logarithmic Split-Point Sampling, Dynamic Restricted Subspacing.
result Average 24% increase in processing speed with accuracy maintained.
Paper improves power of conditional randomization tests.
problem Improving power of conditional randomization tests.
method Introducing a new cost function to maximize test statistic power.
result Consistently increases the number of correct discoveries.
Recent works on adversarial perturbations show that there is an inherent trade-off between standard test accuracy and adversarial accuracy. Specifically, they show that no classifier can simultaneously be robust to adversarial perturbations and achieve high standard test accuracy. However, this is contrary to the stand…
A new test evaluates risk estimation accuracy using probability integral transform.
problem Measuring the accuracy of financial market risk estimations.
method Probability Integral Transform (PIT) of ex post realized returns against ex ante probability distributions.
result The new test shows the importance of capturing the dynamic of financial markets.
Many mathematical imaging problems are posed as non-convex optimization problems. When numerically tractable global optimization procedures are not available, one is often interested in testing ex post facto whether or not a locally convergent algorithm has found the globally optimal solution. When the problem is formu…
Usually one compares the accuracy of two competing classifiers via null hypothesis significance tests (nhst). Yet the nhst tests suffer from important shortcomings, which can be overcome by switching to Bayesian hypothesis testing. We propose a Bayesian hierarchical model which jointly analyzes the cross-validation res…
A new test statistic counts tree co-occurrences to detect edge correlation between networks.
problem Detecting edge correlation between networks using latent vertex correspondence.
method The test statistic is based on counting co-occurrences of signed trees for a family of non-isomorphic trees.
result The test runs in n2+o(1) time and succeeds with high probability for large n. Study evaluates neural networks based on random graph structures and finds key performance indicators.
problem Understanding and optimizing neural network architectures using graph theory.
method Evaluation of neural networks with random graph structures, focusing on structural and numerical properties.
result A new numerical graph characteristic selects a set of quasi-1-dimensional graphs that perform well.
It is common practice to decay the learning rate. Here we show one can usually obtain the same learning curve on both training and test sets by instead increasing the batch size during training. This procedure is successful for stochastic gradient descent (SGD), SGD with momentum, Nesterov momentum, and Adam. It reache…
MNIST and Fashion MNIST are extremely popular for testing in the machine learning space. Fashion MNIST improves on MNIST by introducing a harder problem, increasing the diversity of testing sets, and more accurately representing a modern computer vision task. In order to increase the data quality of FashionMNIST, this …
In this paper, we propose a new method called ProfWeight for transferring information from a pre-trained deep neural network that has a high test accuracy to a simpler interpretable model or a very shallow network of low complexity and a priori low test accuracy. We are motivated by applications in interpretability and…
New method learns models to adapt to domain shifts at test time.
problem Learning models robust to distribution shifts in practical applications.
method Adaptive Risk Minimization (ARM) framework.
result Performance gains of 1-4% on image classification problems.
We develop a new method for regularising neural networks. We learn a probability distribution over the activations of all layers of the model and then insert imputed values into the network during training. We obtain a posterior for an arbitrary subset of activations conditioned on the remainder. This is a generalisati…
Paper introduces a method to control early classification accuracy gaps.
problem Maintaining accuracy in early classification without full input processing.
method Statistical framework for a calibrated stopping rule.
result Reduces up to 94% of timesteps while controlling accuracy gaps.
Convolutional neural networks (CNNs) are similar to "ordinary" neural networks in the sense that they are made up of hidden layers consisting of neurons with "learnable" parameters. These neurons receive inputs, performs a dot product, and then follows it with a non-linearity. The whole network expresses the mapping be…
Normalization effects on deep neural networks impact output variance and test accuracy.
problem The impact of normalization on deep neural networks' statistical behavior and test accuracy.
method Asymptotic expansion analysis of neural network's output for different γi values. result Equal γi values (one) provide the best statistical behavior and test accuracy. Neural Network classifiers have been used successfully in a wide range of applications. However, their underlying assumption of attack free environment has been defied by adversarial examples. Researchers tried to develop defenses; however, existing approaches are still far from providing effective solutions to this ev…