Study on top-k classification with new loss functions and algorithms.
problem Improving multi-class classification accuracy and cardinality trade-off.
method Introducing cardinality-aware loss functions and deriving their consistency bounds.
result New cardinality-aware algorithms for top-k classification. LC-GNN improves GNNs for node classification by incorporating label consistency.
problem Limited performance of GNNs due to label consistency assumption not always holding.
method LC-GNN uses node pairs with the same label but unconnected to expand GNN's receptive field.
result LC-GNN outperforms traditional GNNs in semi-supervised node classification.
Study of loss functions for learning to defer, proving consistency.
problem Learning to defer in machine learning.
method Introduced a family of surrogate losses parameterized by Ψ and proved their consistency. result Proved realizable H-consistency and Bayes-consistency of specific surrogate losses. We improve random forest consistency and performance with DMRF, a new variant.
problem Improving the consistency and performance of random forest models.
method Developed DMRF, a data-driven multinomial random forest, by modifying proof methods and improving data utilization.
result DMRF achieves strong consistency with probability 1, surpassing previous models in classification tasks.
Improved incremental sequence classification with temporal consistency.
problem Updating predictions as new sequence elements are revealed.
method Temporal-difference learning and a temporal-consistency condition for successive predictions.
result Optimizing a novel loss function improves data efficiency and predictive accuracy.
Enhanced consistency bounds derived for classification under a new noise condition.
problem Enhanced consistency bounds for classification under a new noise condition.
method Model Margin Noise (MM noise) assumption, derived enhanced H-consistency bounds.
result Enhanced H-consistency bounds under MM noise condition, interpolates between linear and square-root regimes.
Enhanced H-consistency bounds derived under relaxed conditions.
problem Quantifying the relationship between zero-one estimation error and surrogate loss estimation error.
method Relaxing the condition on the surrogate loss conditional regret and presenting a general framework for establishing enhanced H-consistency bounds. result Derivation of more favorable H-consistency bounds in various scenarios. Study finds AUC is most consistent across different prevalence in binary classification.
problem Consistency of model evaluation metrics across varying prevalence in binary classification.
method Analysis of 156 data scenarios with 18 metrics, 5 models, and a random guess model.
result AUC has the smallest variance in evaluating individual models and ranking of models.
The paper studies consistency of surrogate loss procedures under constrained classifiers.
problem Consistency of surrogate loss approaches under constrained classifiers without correct specification.
method The paper develops theoretical results and hinge loss based procedures for a constrained classification problem.
result Hinge losses are the only surrogate losses that preserve consistency in second-best scenarios.
Improves GAN-based semi-supervised learning with consistency regularization.
problem Lack of consistency in class probability predictions under local perturbations.
method Introduces consistency regularization to GANs, leveraging both local and interpolation consistency.
result Significantly improves performance and achieves new state-of-the-art results.
Reduces bounded loss learning to binary classification.
problem Universal consistency of non-i.i.d. processes with bounded loss.
method Constructive reduction to binary classification.
result Any bounded loss output setting can be reduced to binary classification.
Study on H-consistency bounds for machine learning surrogates.
problem Estimating target loss error relative to surrogate loss error in machine learning.
method Developed H-consistency bounds for various surrogates and loss functions. result Stronger guarantees than existing methods, offering distribution-dependent and -independent bounds.
Adversarial consistency depends on the uniqueness of adversarial Bayes classifiers.
problem Consistency of adversarial surrogate losses is not guaranteed.
method Connected consistency of adversarial surrogate losses to the uniqueness of adversarial Bayes classifiers.
result A convex surrogate loss is statistically consistent for adversarial learning if and only if the adversarial Bayes classifier is unique.
We consider the problem of n-class classification (n≥2), where the classifier can choose to abstain from making predictions at a given cost, say, a factor α of the cost of misclassification. Designing consistent algorithms for such n-class classification problems with a `reject option' is the main goal of t…
A new framework integrates classification and regression tasks in multi-task learning.
problem Jointly solving classification and regression tasks in multi-task scenarios.
method Two-Stage Learning-to-Defer (L2D) framework with a unified deferral mechanism.
result Unified deferral mechanism ensures convergence to the Bayes-optimal rejector.
The paper explores trading off consistency and dimensionality in convex surrogates for multiclass classification.
problem Designing consistent surrogate losses for multiclass classification with high-dimensional outcomes.
method Investigates embedding outcomes into convex polytopes and examining consistency under low-noise assumptions.
result Consistency can be achieved with less than n−1 dimensions, but hallucination occurs for some distributions. Study evaluates consistency of LLMs in binary text classification, providing systematic guidance.
problem Lack of reliable methods for evaluating large language model (LLM) binary text classification.
method Adapting psychometric principles, the study determines sample size requirements, develops metrics for invalid responses, and evaluates intra- and inter-rater reliability.
result LLMs demonstrated high intra-rater consistency, achieving perfect agreement on 90-98% of examples, with smaller models outperforming larger counterparts.
Paper bounds convergence rate of adversarial surrogate risk.
problem Vulnerability of binary classification models to adversarial attacks.
method Characterizes conditions for adversarial consistency and provides surrogate risk bounds.
result Surrogate risk bounds quantify the rate of convergence of adversarial classification risk.
Paper explores connections between loss functions and consistency in binary classification and regression.
problem Consistency in binary classification and regression applications.
method Characterization of conformable loss functions and derivation of a new Huber-type loss function.
result Margin-based loss functions are equivalent to loss functions of squared standardized logistic regression residuals.
A new method for PU learning improves classification error on CIFAR-10.
problem Learning from positive and unlabeled data in practical applications.
method A simple yet effective data augmentation method based on consistency regularization.
result Achieves an averaged improvement of 3.40 points in classification error on CIFAR-10.
New framework improves generative models with prediction and consistency constraints.
problem Improving generative models with sparse labeled data.
method Optimizes variational autoencoders with prediction and consistency constraints.
result Promising image classification performance, especially in semi-supervised scenarios.
ε-Consistent Mixup improves semi-supervised classification accuracy.
problem Improving semi-supervised classification accuracy with limited labeled data.
method Combines Mixup's linear interpolation with consistency regularization, using an adaptive tradeoff between the two.
result ε-Consistent Mixup yields the largest gains in low label-availability scenarios.
Proposes a method to classify binary data from multiple unlabeled datasets.
problem High annotation costs in training classifiers from weakly supervised data.
method Introduces surrogate set classification (SSC) to predict data origin from multiple unlabeled datasets, then uses this to train a binary classifier.
result Demonstrates superior performance compared to existing methods.
Differentially-private Bayes consistency rule for binary classification and density estimation.
problem Privacy constraints limit private learning in the distribution-free PAC model.
method Constructs a universally Bayes consistent learning rule that satisfies differential privacy.
result Private learning is possible for arbitrary distributions, even with a single algorithm.
New metric reduces arbitrariness in fair binary classification predictions.
problem Variance in predictions leads to arbitrary decisions in fair classification.
method Developed a self-consistency metric and an abstention algorithm.
result Fair binary classification is often close to fair due to variance, not interventions.
Prototype rules simplify multiclass classification in metric spaces, achieving consistency and reduced complexity.
problem Multiclass classification in metric spaces, focusing on universal consistency and convergence rates.
method Novel Proto-NN and hybrid rules for multiclass classification in metric spaces, analyzing convergence rates.
result Proto-NN is universally consistent and simpler to implement, with similar computational advantages.
In this work we show that, using the eigen-decomposition of the adjacency matrix, we can consistently estimate feature maps for latent position graphs with positive definite link function κ, provided that the latent positions are i.i.d. from some distribution F. We then consider the exploitation task of vertex classi…
Decision trees are consistent for regression and classification tasks even with many predictors.
problem Consistency of decision trees with many predictors.
method CART and C4.5 methodology, oracle inequality, sparsity constraints.
result Decision trees and random forests are consistent for various types of data.
Proposes an angle-based framework for multicategory cost-sensitive classification.
problem Cost-sensitive multicategory classification challenges.
method Angle-based cost-sensitive classification framework without sum-to-zero constraint.
result Proposed boosting algorithms yield competitive classification performances.
This paper introduces new loss functions for balanced multi-class classification.
problem Balancing class imbalance in multi-class classification.
method Introduces two new surrogate loss families: GLA and GCA.
result GCA losses offer stronger theoretical guarantees in imbalanced settings.
Study on learning to defer to multiple experts with consistent surrogates and confidence calibration.
problem Addressing the open problems of consistent surrogates, confidence calibration, and ensembling of experts.
method Derive two consistent surrogates (softmax and OvA) and propose a conformal inference technique for choosing experts.
result The OvA-based loss does not cause mis-calibration propagation, while the softmax-based loss does.
The classification of Riemannian manifolds by the holonomy group of their Levi-Civita connection picks out many interesting classes of structures, several of which are solutions to the Einstein equations. The classification has two parts. The first consists of isolated examples: the Riemannian symmetric spaces. The sec…
Paper corrects Max-Margin loss for multi-label tasks.
problem Max-Margin loss inconsistency in multi-label classification.
method Introduced Restricted-Max-Margin loss.
result Consistent loss for multi-label tasks under milder conditions.
Paper develops a privacy-preserving nonparametric regression method.
problem Nonparametric regression with local differential privacy constraints.
method Privatised discretisation and Laplace noise applied to feature vectors and responses.
result Strongly universally consistent estimator for regression and classification.
New tests for binary classification regression functions without distribution assumptions.
problem Testing regression functions in binary classification without distributional assumptions.
method Conditional kernel mean embeddings and resampling-based framework.
result Distribution-free hypothesis tests with exact type I error control.
We use the consistency approach to classify discrete integrable 3D equations of the octahedron type. They are naturally treated on the root lattice Q(A3) and are consistent on the multidimensional lattice Q(AN). Our list includes the most prominent representatives of this class, the discrete KP equation and its S…
Paper establishes a universal growth rate for smooth surrogate losses in classification.
problem Analyzing growth rates of consistency bounds for various surrogate losses.
method Proves square-root growth rate for smooth margin-based losses; extends to multi-class classification.
result Demonstrates a universal square-root growth rate for smooth comp-sum and constrained losses.
Cross-lingual Text Classification (CLC) consists of automatically classifying, according to a common set C of classes, documents each written in one of a set of languages L, and doing so more accurately than when naively classifying each document via its corresponding language-specific classifier. In order to obtain an…
This work explains how large neural networks generalize well despite overparameterization.
problem Understanding the generalization behavior of large neural networks.
method Theoretical analysis of approximation and generalization errors in regression and classification tasks.
result Deep overparameterized neural networks are statistically consistent across different tasks when regularization is applied.
Implementing k-NN classification using Gromov--Wasserstein distances
problem Comparing metric measure spaces
method Gromov--Wasserstein and fused Gromov--Wasserstein distances
result Universal consistency of k-NN classifiers New algorithm achieves strong consistency in binary non-uniform hypergraph classification.
problem Node classification on binary non-uniform hypergraphs with varying edge probabilities.
method Proposes a refinement algorithm using power iteration on weighted adjacency matrices.
result Proves optimality of the refinement algorithm, achieving strong consistency and IT lower bound.
Study reveals how high-dimensional models are vulnerable to consistent adversarial attacks.
problem Understanding the vulnerability of high-dimensional linear classifiers to adversarial attacks.
method Introducing a new error metric to quantify model vulnerability, and rigorously characterizing these metrics in asymptotic settings.
result As models become more overparameterized, their vulnerability to label-preserving perturbations increases.
We describe the genus two knots which admit a genus one, one bridge position. These are divided into several families, one consists of vertical bandings of two genus one (1,1)-knots, other consists of vertical bandings of two cross cap number two 2-bridge knots, and the last one consists of genus two tunnel number on…
A new method for weakly supervised learning that improves model accuracy.
problem Training machine learning models with precise labels is expensive; weak supervision provides a low-cost alternative.
method Data consistent weak supervision algorithm that searches over classifiers to find plausible labelings, considering features of the training data and estimating labels for low/no coverage data.
result Empirically, the method significantly outperforms state-of-the-art weak supervision methods on text and image classification tasks.
Unified framework for hierarchical image classification with epistemic uncertainty.
problem Overconfident predictions and lack of logical consistency in deep learning models.
method Neurosymbolic approach with epistemic deep learning, using focal set reasoning and differentiable fuzzy logic.
result Maintains accuracy on par with transformer baselines while providing more calibrated and interpretable predictions.
In this work we show that, using the eigen-decomposition of the adjacency matrix, we can consistently estimate latent positions for random dot product graphs provided the latent positions are i.i.d. from some distribution. If class labels are observed for a number of vertices tending to infinity, then we show that the …
We study the problem of fair binary classification using the notion of Equal Opportunity. It requires the true positive rate to distribute equally across the sensitive groups. Within this setting we show that the fair optimal classifier is obtained by recalibrating the Bayes classifier by a group-dependent threshold. W…
Develops an online federated learning framework for classification.
problem Handling streaming data from multiple clients while ensuring data privacy and efficiency.
method Leverages generalized distance-weighted discriminant technique and Majorization-Minimization principle.
result Achieves high classification accuracy, significant computational efficiency, and data security enhancements.