This paper considers the challenge of evaluating a set of classifiers, as done in shared task evaluations like the KDD Cup or NIST TREC, without expert labels. While expert labels provide the traditional cornerstone for evaluating statistical learners, limited or expensive access to experts represents a practical bottl…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,051 papers · 148 categories
Trend · papers per month
48 results for “Classifier evaluation”
New IRT method identifies useful datasets for ML classifier evaluation.
problem Lack of standard evaluation strategy for ML benchmarks.
method Applied Item Response Theory (IRT) to OpenML-CC18 benchmark.
result Not all datasets are useful for evaluating classifiers.
Paper develops streaming algorithms to estimate classifier accuracy on unlabeled data.
problem Estimating classifier accuracy on unlabeled data with noisy decisions.
method Two algebraic evaluators: majority voting and a novel method to handle correlated classifiers.
result The novel method can be as accurate as 1% when handling small amounts of correlation.
Paper introduces a method to evaluate abstaining classifiers by considering missing predictions as counterfactuals.
problem Lack of a principled approach to evaluate and compare abstaining classifiers, especially when missing predictions are important.
method Develops a novel approach to treat abstentions as missing data, defining counterfactual scores and using causal inference methods to estimate them.
result Shows that under certain conditions, counterfactual scores can be identified and estimated efficiently, improving evaluation of abstaining classifiers.
This work evaluates and improves calibration of probabilistic classifiers.
problem Ensuring probabilistic classifiers output consistent probabilities with empirical frequencies.
method Develops a theoretical framework grounded in probability theory and proposes new evaluation techniques.
result Refined interpretations and new ways to quantify and visualize miscalibration.
We introduce a new metric to evaluate corruption robustness of ML classifiers.
problem Evaluating corruption robustness of machine learning classifiers.
method We propose a test data augmentation method using minimal class separation distance to derive a robustness distance ε and a metric MSCR.
result The MSCR metric allows interpretable comparison of classifier robustness on different datasets.
The use of alternative measures to evaluate classifier performance is gaining attention, specially for imbalanced problems. However, the use of these measures in the classifier design process is still unsolved. In this work we propose a classifier designed specifically to optimize one of these alternative measures, nam…
The study evaluates 62 classifiers for detecting online toxic comments.
problem Identifying and classifying toxic online commentary.
method Systematic evaluation of 62 classifiers representing 19 algorithmic families on the Jigsaw dataset.
result Simple bad word lists are most predictive of offensive commentary.
Proposes a method to evaluate classifiers with missing labels using multiple imputation.
problem Missing labels during model evaluation can introduce bias, especially in Missing Not At Random (MNAR) data.
method Develops a multiple imputation technique to estimate and provide predictive distributions for metrics like precision, recall, and ROC-AUC.
result The predictive distribution's location and shape are generally correct, even in the MNAR regime.
New neural network approach using mutual information.
problem Training neural networks for imbalanced datasets.
method Converts neural network classifiers to mutual information evaluators.
result New form of softmax leads to better classification accuracy, especially for imbalanced datasets.
Develops rough set classifiers using confusion matrices.
problem Evaluating classifier quality in machine learning.
method Combines rough set theory with confusion matrices.
result Defines indices and classifiers based on rough confusion matrices.
EAST aligns neural network classifiers with user-defined evaluation metrics.
problem Mismatch between neural network training and evaluation metrics leads to suboptimal performance.
method EAST uses dynamic thresholding, soft-set confusion matrix, and annealing to align neural network predictions with target evaluation metrics.
result EAST improves alignment between training objectives and evaluation metrics, outperforming existing methods.
This paper reviews PU learning evaluation methods and provides practical recommendations.
problem Evaluating PU learning methods when only positive and unlabelled data are available.
method Critical review of 51 articles proposing PU classifiers and alternative predictive accuracy measures.
result Practical recommendations for improving PU learning evaluation.
This work addresses fairness in ML models by training and evaluating attribute classifiers under uncertain and incomplete data.
problem Challenges in fairness metrics due to uncertain and incomplete data.
method Developed a theoretical and empirical analysis to understand and improve bias estimation in the data-scarce regime.
result The test accuracy of the attribute classifier is not always correlated with its effectiveness in bias estimation.
This work introduces significativity indices for agreement values between classifiers.
problem Evaluating the quality of agreement measures between classifiers.
method Proposes general approach and two specific indices for evaluation.
result Introduces two new significativity indices for evaluating agreement values.
Improves classifier evaluation by aligning with Total Classification Cost.
problem Lack of consensus on evaluation metrics and class imbalance issues.
method Introduces Weighted Accuracy (WA) and a reweighting framework for cost-sensitive scenarios.
result WA aligns with Total Classification Cost (TCC) minimization under realistic conditions.
New robustness metric helps select reliable classifiers.
problem Evaluating reliability of classifier predictions.
method Proposed new robustness metric for any classifier and feature type.
result Demonstrated ability to distinguish reliable from unreliable predictions.
Proposes MCC-F1 curve for better binary classification evaluation.
problem Misleading performance evaluations with ROC and PR curves for imbalanced data.
method Introduces MCC-F1 curve combining MCC and F1 score.
result MCC-F1 curve provides clearer classifier differentiation.
Study adversarial attacks on cost-sensitive classifiers.
problem Safety-critical classification problems with cost-sensitive predictions.
method Used state-of-the-art adversarially-resistant neural networks and analyzed as a two-player zero-sum game.
result Introduced a new cost-sensitive attack that performs better than targeted attacks in some cases.
The paper extends calibration to sets of probabilistic classifiers, finding many ensembles are poorly calibrated.
problem Evaluating the validity of epistemic uncertainty in sets of probabilistic classifiers.
method Proposed a novel nonparametric calibration test for sets of probabilistic classifiers.
result Ensembles of deep neural networks are often not well calibrated.
Proposes an IRT-based ensemble method to improve machine learning accuracy.
problem Improving the accuracy of machine learning models, especially for hard-to-classify instances.
method Introduces Item Response Theory (IRT) to evaluate sample difficulty and classifier ability, creating three models with different assumptions.
result The proposed IRT ensemble model outperforms other methods on 19 datasets.
Defines explanations for classifier outcomes using causal concepts.
problem Understanding classifier outcomes in a causal context.
method Proposes a new definition of explanation based on causality, compares it with existing notions, and evaluates it experimentally.
result Experimental evaluation shows the new definition's effectiveness on financial datasets.
Enhances mixture models with classifier-defined weights.
problem Density evaluation and sampling in mixture models.
method Introduces Classifier Weighted Mixtures (CWM) with functional weights.
result Improves expressivity in variational estimation without increasing complexity.
Temporal cross-validation impacts multivariate time series subsequence anomaly detection evaluationstat.ML
Study examines how different time series cross-validation methods affect anomaly detection in multivariate time series.
problem Evaluating anomaly detection in multivariate time series requires preserving temporal dependencies, especially for subsequence anomalies.
method Systematically investigates walk-forward and sliding window methods across various validation configurations and classifier types.
result Sliding window method consistently yields higher precision-recall scores and reduced fold-to-fold performance variance, particularly for deep learning models.
Revisit Time Series Classification Benchmark: The Impact of Temporal Information for Classificationcs.LG
Temporal information impacts only a fraction of time series datasets, skewing benchmark evaluations.
problem Temporal information's impact on time series classification is often overestimated.
method Permutation tests on UCR archive to identify datasets where temporal info is irrelevant.
result Many tabular datasets perform well without temporal info, skewing benchmark evaluations.
PolyGraph Discrepancy improves graph generative model evaluation.
problem Inability of existing metrics to provide an absolute performance measure and comparability across different graph descriptors.
method Approximates Jensen-Shannon distance using binary classifiers trained to distinguish between real and generated graphs.
result PGD provides a more robust and insightful evaluation compared to MMD metrics.
We present a method to stop the evaluation of a prediction process when the result of the full evaluation is obvious. This trait is highly desirable in prediction tasks where a predictor evaluates all its features for every example in large datasets. We observe that some examples are easier to classify than others, a p…
We present a method to stop the evaluation of a decision making process when the result of the full evaluation is obvious. This trait is highly desirable for online margin-based machine learning algorithms where a classifier traditionally evaluates all the features for every example. We observe that some examples are e…
Generative text classifiers are most vulnerable to membership inference attacks.
problem Privacy threat from Membership Inference Attacks on generative text classifiers.
method Comprehensive empirical evaluation of generative, discriminative, and pseudo-generative classifiers across various datasets.
result Generative classifiers explicitly modeling are most vulnerable to membership leakage.
Unsupervised classification methods learn a discriminative classifier from unlabeled data, which has been proven to be an effective way of simultaneously clustering the data and training a classifier from the data. Various unsupervised classification methods obtain appealing results by the classifiers learned in an uns…
Unified approach optimizes neural network training for various metrics.
problem Training and evaluation of neural network binary classifiers often use different metrics.
method Combines differentiable approximation and probabilistic soft sets.
result Effective in optimizing for metrics like F1-Score across various domains.
Develops a framework to copy any machine learning classifier without prior knowledge.
problem Copying machine learning classifiers without access to their parameters or training data.
method Theory and framework development, synthetic set generation, loss identification, and evaluation metrics.
result Copies can enhance existing solutions and add new features.
Activates speech DNNs to generate understandable examples.
problem Difficulty in understanding DNN classifications for speech.
method Activation maximization to generate speech samples.
result Activation maximization can generate understandable speech samples.
Given a classifier ensemble and a set of examples to be classified, many examples may be confidently and accurately classified after only a subset of the base models in the ensemble are evaluated. This can reduce both mean latency and CPU while maintaining the high accuracy of the original ensemble. To achieve such gai…
Improves off-policy evaluation weights for balanced state-action pair distribution.
problem Imbalance in importance sampling weights for off-policy evaluation of contextual bandits.
method Balanced Off-Policy Evaluation (B-OPE) method that minimizes imbalance to desired counterfactual distribution of state-action pairs.
result Experimental evidence shows B-OPE improves offline policy evaluation in both discrete and continuous action spaces.
LEEP measures transferability of learned representations efficiently.
problem Evaluating the transferability of learned representations in machine learning.
method LEEP: Log Expected Empirical Prediction, a simple measure requiring one pass through the target data set.
result LEEP predicts transfer and meta-transfer learning performance and convergence speed, outperforming existing measures.
This paper introduces metrics to evaluate robustness of neural networks to natural adversarial examples.
problem Measuring robustness of neural networks to natural adversarial examples.
method Proposes latent space performance metrics based on generative models.
result Latent adversarial perturbations are often perceptually small and associated with classifier accuracy.
Study improves image classifier robustness to random p-norm corruptions.
problem Improving robustness of image classifiers to real-world imperceptible corruptions.
method Training and testing with random p-norm corruptions, evaluating robustness against different p-norms.
result Training with a combination of p-norm corruptions significantly improves robustness.
Proposes and evaluates three diagnostic graphics for probabilistic classifiers.
problem Evaluating and comparing probabilistic classifiers.
method Triptych of diagnostic graphics: reliability diagram, ROC curve, Murphy diagram.
result Visual diagnostics reveal distinct aspects of forecast performance.
Suitability filter detects model performance degradation in real-world deployment.
problem Ensuring model reliability in safety-critical domains without access to ground truth labels.
method Uses suitability signals to evaluate classifier performance on unlabeled user data.
result The suitability filter reliably detects performance deviations due to covariate shift.
The study analyzes performance indices for class-imbalanced data and identifies conditions they must meet.
problem Distortions in performance indices under class imbalance.
method Identified two conditions for performance indices and analyzed four binary and five multi-class indices.
result Recommended appropriate indices for evaluating classifiers in class-imbalanced scenarios.
Study evaluates when splitting classifiers can improve performance despite disparate treatment.
problem Impact of disparate treatment in classification models.
method Comparison of split classifiers and group-blind classifiers, quantifying performance improvement.
result Proves an equivalent expression for the benefit-of-splitting which can be efficiently computed.
In this paper we establish rigorous benchmarks for image classifier robustness. Our first benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while showing which classifiers are preferable in safety-critical applications. Unlike recent robustness research, this benchmark evaluates performan…
Improves multi-label classification with a new network model.
problem Improving multi-label classification accuracy.
method Introduces Classifier Chain Network (CCN) for multi-label classification.
result CCN outperforms benchmark methods in simulations and real data.
Study shows image classifiers struggle with temporal changes in videos.
problem Temporal robustness of image classifiers in videos.
method Constructed datasets and evaluated various classifiers and detection models.
result Median classification accuracy drops of 16-10 points in robust datasets.
A new approach to make classifiers safer by allowing them to abstain from making decisions on adversarial inputs.
problem Making machine learning systems robust against adversarial attacks, especially in safety-critical applications.
method Introducing a novel objective function and a simple baseline for adversarial robustness with abstention, followed by CARL (Combined Abstention Robustness Learning) for joint classifier and abstention region learning.
result Training with CARL results in a more accurate, robust, and efficient classifier than a simple baseline.
Generative model creates poisoning attacks against machine learning classifiers.
problem Poisoning attacks degrade machine learning classifier performance.
method Generative Adversarial Net with generator, discriminator, and classifier components.
result Effectively compromises machine learning classifiers, including deep networks.
META-DES.H selects competent classifiers using meta-learning and dynamic weighting.
problem Selecting competent classifiers in dynamic ensemble selection.
method META-DES framework using meta-learning and dynamic weighting.
result Improvements in recognition accuracy on 30 datasets.