New classifier combines locally linear kernels for fast and accurate non-linear classification.
problem Developing a fast and accurate non-linear classifier.
method Combines locally linear classifiers using a ℓ1 Multiple Kernel Learning (MKL) problem with scalable MKL training for streaming kernels. result The resulting classifier achieves high accuracy with fast inference time.
Generative classifiers' properties are linked to linear constraints.
problem Understanding the Markov property in generative classifiers.
method Characterization of discrimination functions using linear constraints and a second order finite difference operator.
result Discrimination functions of undirected Markov network classifiers are characterized by sets of linear constraints.
TaCo prevents non-linear classifiers from detecting sensitive attributes.
problem Ensuring fairness in NLP models by preventing sensitive attribute detection.
method Targeted Concept Erasure (TaCo) removes sensitive information from final latent representations, even against non-linear classifiers.
result TaCo outperforms state-of-the-art methods in reducing sensitive attribute prediction accuracy while preserving overall task performance.
Linear classifiers in product space forms improve scRNA-seq data classification.
problem Linear classification in products of Euclidean, spherical, and hyperbolic spaces.
method Novel formulations of linear classifiers on Riemannian manifolds, proving expressive power, and formalizing perceptron and SVM classifiers.
result Linear classifiers in product space forms have the same expressive power as in Euclidean space of the same dimension.
diproperm tests differences in HDLSS data with binary classifiers.
problem Testing differences in HDLSS data with binary classifiers.
method DiProPerm test for binary linear classifiers.
result Validates the DiProPerm test on real-world data.
Binary linear classifiers are the most explainable up to negligible sets.
problem Measuring the explainability of machine learning classifiers.
method Introducing pointwise coverage to measure explainability and proving the binary linear classifier is the most explainable up to negligible sets.
result The binary linear classifier is uniquely the most explainable classifier up to negligible sets.
Classifies linear embeddings of grassmannians and ind-grassmannians.
problem Understanding linear embeddings of grassmannians and ind-grassmannians.
method Classification through isomorphism of Picard groups and direct limits.
result Most linear embeddings of grassmannians are equivariant.
Linear classifiers can be made robust to strong adversarial examples attacks.
problem Understanding and quantifying adversarial examples in linear classification.
method Proposed a more practical definition of strong adversarial examples, showing robustness to attacks.
result Linear classifiers can be made robust to strong adversarial examples attacks.
Test assesses if a linear classifier is random or significant.
problem Determining if a linear classifier captures meaningful differences between classes.
method Proposes a homogeneity test related to linear separability, establishes upper bounds for p-values.
result Upper bounds for p-values are highly accurate for normally distributed samples.
Support vector machines (SVM) and other kernel techniques represent a family of powerful statistical classification methods with high accuracy and broad applicability. Because they use all or a significant portion of the training data, however, they can be slow, especially for large problems. Piecewise linear classifie…
Geometric insights reveal transferable adversarial directions across classifiers and models.
problem Adversarial perturbations transfer between different inputs, models, and architectures.
method Geometric analysis of linear classifiers and two-layer ReLU networks.
result Transferable adversarial directions exist for linear separators and ReLU networks with high probability.
New insights into how linear classifiers and leaky ReLU networks can overfit without harming generalization.
problem Understanding conditions for benign overfitting in linear classifiers and leaky ReLU networks.
method Utilizing Karush--Kuhn--Tucker (KKT) conditions for margin maximization.
result Satisfaction of KKT conditions leads to benign overfitting in linear classifiers and leaky ReLU networks.
Classifies surfaces with special curvature properties.
problem Rotational surfaces with specific curvature conditions.
method Classifies surfaces with rotationally symmetric norms and linear curvature relations.
result Rotational surfaces with linearly related curvatures are classified.
New algorithms explain Naive Bayes classifiers in polynomial time and delay.
problem Computing explanations for Naive Bayes classifiers efficiently.
method Developed log-linear time and polynomial delay algorithms for PI-explanations.
result Efficiently computed PI-explanations for linear classifiers.
NCC is inefficient in higher dimensions, NCDA improves performance.
problem Inefficiency of NCC in higher dimensions.
method Combining NCC with LDA to create NCDA.
result NCDA outperforms NCC and competes with LDA and QDA.
Multithreshold Entropy Linear Classifier (MELC) is a recent classifier idea which employs information theoretic concept in order to create a multithreshold maximum margin model. In this paper we analyze its consistency over multithreshold linear models and show that its objective function upper bounds the amount of mis…
A new metric estimates classifier accuracy using only training data.
problem Assessing classifier accuracy without cross-validation.
method Bayesian Area Under the ROC Curve (CBAUC) metric for linear classifiers.
result The CBAUC is faster and more accurate than conventional AUC estimators.
This paper optimizes binary linear classifiers by tuning their weight vectors.
problem Optimizing the weight vector of binary linear classifiers for better performance.
method Parameterization of the discriminant through a scalar to control trade-offs between informative and noisy terms.
result Weight vector tuning compensates for non-optimal native hyperparameters, improving classification performance.
Linear classifiers can resist adversarial attacks on Gaussian data.
problem Adversarial attacks on high-dimensional data.
method Adversarial training of linear classifiers on Gaussian data.
result Linear classifiers can resist adversarial attacks on Gaussian data.
Study assesses linear classifiers for virus genotyping and subtyping.
problem Challenges in classifying viral sequences, especially in alignment-free methods.
method Comprehensive evaluation of linear classifiers on HCV genomes, varying parameters and sequence lengths.
result Several classifiers perform well under specific conditions, providing robust assessment.
A classification algorithm, called the Linear Centralization Classifier (LCC), is introduced. The algorithm seeks to find a transformation that best maps instances from the feature space to a space where they concentrate towards the center of their own classes, while maximimizing the distance between class centers. We …
Proposes a new scoring function for linear classifiers to improve object positioning in feature space.
problem Lack of information about relative positions of recognized objects in feature space.
method Calculates a scoring function based on object distance from decision boundary and class centroid.
result Demonstrates effectiveness of the proposed method compared to other ensemble algorithms on multiple datasets.
Distillation speeds up classifier training and provides insights into its success.
problem Empirical success of knowledge distillation without theoretical explanation.
method Study of linear and deep linear classifiers, proving a generalization bound.
result Three key factors for distillation success: data geometry, optimization bias, strong monotonicity.
Researchers combined linear classifiers using score functions and found simple and trimmed averages to be the best combination strategies.
problem Combining linear classifiers using their score functions.
method Two score functions tested; four combination strategies investigated; comparison with majority voting and model averaging.
result Simple and trimmed average combination strategies were the best.
Paper generalizes strategic classification framework and introduces SVC for PAC-learning.
problem Strategic manipulation of testing data to fool classifiers.
method Unified framework for strategic classification, strategic VC-dimension (SVC).
result Characterizes the learnability and computational tractability of linear classifiers.
We classify all of the 4-dimensional linear Poisson structures of which the corresponding Lie algebras can be considered as the extension by a derivation of 3-dimensional unimodular Lie algebras. The affine Poisson structures on R^3 are totally classified.
Study shows how over-parameterized classifiers can still perform well on noisy data.
problem Understanding how maximum margin classifiers perform in over-parameterized settings with noisy data.
method Analyzes maximum margin classifiers on sub-Gaussian mixtures, providing risk bounds.
result Characterizes conditions for 'benign overfitting' in linear classification problems.
The paper classifies certain types of Ricci solitons with specific curvature properties.
problem Classifying gradient steady Ricci solitons with linear curvature decay.
method Analyzing the curvature properties and using classification techniques.
result Classification of 3D and 4D steady Ricci solitons with nonnegative curvature under linear decay.
A new classifier uses linear programming to classify sets based on their covariance.
problem Classifying sets of observations as a whole, not individually.
method Proposes a new classifier, CLIPS, using linear programming for set classification.
result The CLIPS classifier performs better with multiple observations in a set.
A Gaussian mixture model improves generalization for long-tailed data.
problem Optimizing generalization for rare data in long-tailed distributions.
method Suggested Gaussian mixture model and comparison of linear vs. nonlinear classifiers.
result Nonlinear classifiers outperform linear ones for long-tailed data.
Dynamic ensemble selection (DES) techniques work by estimating the level of competence of each classifier from a pool of classifiers. Only the most competent ones are selected to classify a given test sample. Hence, the key issue in DES is the criterion used to estimate the level of competence of the classifiers in pre…
SEFR is a fast, energy-efficient classifier for ultra-low power devices.
problem Running machine learning on battery-powered devices is challenging due to time and energy constraints.
method SEFR is an ultra-low power classifier with linear time complexity for training and testing.
result SEFR is 63 times faster and 70 times more energy efficient than state-of-the-art classifiers.
A set of introductory notes on the subject of data classification using a linear classifier and least-squares cost function, and the negative effect of the presence of outliers on the decision boundary of the linear discriminant. We also show how a simple scaling could make the outlier less significant, thereby obtaini…
MALT improves adversarial attacks by targeting classes more efficiently.
problem Naive targeting of adversarial attacks based on classifier confidence.
method MALT - Mesoscopic Almost Linearity Targeting, based on medium-scale almost linearity assumptions.
result MALT wins over AutoAttack on CIFAR-100 and ImageNet datasets, five times faster.
Adversarial training can lead to overfitting without compromising robustness.
problem Explaining benign overfitting in adversarially robust linear classification.
method Theoretical analysis and numerical experiments on adversarial training.
result Adversarially trained linear classifiers can achieve near-optimal risks despite overfitting noisy data.
We consider a discriminative learning (regression) problem, whereby the regression function is a convex combination of k linear classifiers. Existing approaches are based on the EM algorithm, or similar techniques, without provable guarantees. We develop a simple method based on spectral techniques and a `mirroring' tr…
A new method for efficient BNC parameter estimation outperforms HDP smoothing.
problem Efficiently estimating parameters for Bayesian network classifiers to match or exceed random forest performance.
method Uses log-linear regression to approximate hierarchical Dirichlet process (HDP) smoothing, making the approach simpler and faster.
result Our method outperforms HDP smoothing while being orders of magnitude faster and competitive with random forests.
Batch normalization biases linear models towards uniform margins, improving performance in binary classification.
problem Understanding the implicit bias of batch normalization in linear models and neural networks.
method Analyzing gradient descent convergence on linear models and two-layer CNNs with batch normalization.
result Gradient descent with batch normalization in linear models converges to a uniform margin classifier with an exponential convergence rate.
Linear classifiers separate the data with a hyperplane. In this paper we focus on the novel method of construction of multithreshold linear classifier, which separates the data with multiple parallel hyperplanes. Proposed model is based on the information theory concepts -- namely Renyi's quadratic entropy and Cauchy-S…
Improves robustness of ReLU networks by maximizing linear regions.
problem Neural networks are not robust, raising concerns for safety-critical systems.
method Maximizes linear regions and distance to decision boundary.
result Improves robustness and minimizes adversarial perturbations.
Linear trends in classifier accuracy observed under distribution shift.
problem Understanding why classifier accuracies show linear trends under distribution shift.
method Assumed model similarity and verified empirically.
result Linear trend in classifier accuracy occurs unless distribution shift is large.
Classifies non-linear Fredholm maps linking to stable homotopy groups of spheres.
problem Classifying non-linear proper Fredholm maps between Hilbert spaces.
method Using stable homotopy groups of spheres to classify maps up to proper homotopy.
result Determines the non-trivial kernel of the map from stable homotopy groups to non-linear proper Fredholm maps.
Develops an online nonparametric classifier for massive data.
problem Challenges of batch kernel-based nonparametric classifiers in massive data.
method Online principle components analysis to reduce dimensionality, followed by stochastic approximation algorithm for real-time calculation.
result Online classifier provides the best trade-off between accuracy and computation cost.
Paper proposes a statistical model for detecting mu-suppression in EEG signals.
problem Detecting mu-suppression in motor imagery EEG signals.
method Proposes a statistical model based on the generalized extreme value distribution (GEV) and a linear classifier.
result Preliminary results show good classification accuracy in detecting mu-suppression and distinguishing EEG events.
Study of linear classifiers in infinite imbalance scenarios.
problem Behavior of linear discriminant functions in extreme imbalance conditions.
method Analysis of linear classifiers under infinite imbalance, focusing on weight function properties and limit behavior.
result Limiting coefficient vectors reflect robustness or conservatism, optimizing against worst-case alternatives.
This work provides efficient approximations for linear classifiers' performance.
problem Improving the efficiency and accuracy of linear classifiers.
method Developed smooth functions approximating the expected error and ranking loss of linear classifiers, derived from data moments.
result The proposed approximations and optimization algorithms achieve similar or better performance than state-of-the-art methods, significantly faster.
Novel approach for creating interpretable classifiers using bilevel optimization of split-rules in NLDTs.
problem Creating highly accurate and easily interpretable classifiers for practical applications.
method Representing classifiers as assemblies of simple mathematical rules using NLDTs with evolutionary bilevel optimization.
result The approach ensures interpretability while achieving high accuracy on various classification problems.
Develops methods for fair classification under linear disparity constraints.
problem Disparate impacts of machine learning algorithms on protected groups.
method Bayes-optimal fair classification methods via pre-, in-, and post-processing.
result Explicit forms of Bayes-optimal fair classifiers under linear disparity measures.