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.
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.
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.
Researchers use LRP to explain CNN predictions in NLP tasks.
problem Explaining predictions of complex non-linear classifiers in NLP.
method Layer-wise relevance propagation (LRP) applied to a CNN for topic categorization.
result LRP highlights relevant words for CNN predictions, validating its suitability for NLP.
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.
LCC algorithm maps instances to a central space for better classification.
problem Improving classification accuracy for various datasets.
method Formulated as a quadratic program, simplified to a linear program, uses kernel functions for non-linear cases.
result LCC outperforms other methods in accuracy on standard datasets.
A new game-theoretic approach optimizes complex rate metrics.
problem Optimizing non-decomposable performance metrics and rate constraints.
method Extending two-player game approaches to a three-player game, seeking equilibrium.
result Generalizes and improves upon existing algorithms for constrained optimization.
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.
The performance of the Self-Organizing Map (SOM) algorithm is dependent on the initial weights of the map. The different initialization methods can broadly be classified into random and data analysis based initialization approach. In this paper, the performance of random initialization (RI) approach is compared to that…
Machine learning improves joint default assessment by capturing non-linear dependencies.
problem Capturing non-linear dependencies among covariates for accurate joint default assessment.
method Application of machine learning techniques to credit card dataset, comparing with logistic regression.
result Machine learning outperforms logistic regression in assessing portfolio riskiness.
Study modular surfaces in Lorentz-Minkowski 3-space, classifying and analyzing their curvature and applications.
problem Understanding the curvature properties of modular surfaces in Lorentz-Minkowski space.
method Analyzing the sign of Gaussian and mean curvature, classifying surfaces, and applying to conformal field theories.
result Complete classification of zero Gaussian curvature modular surfaces and non-existence of non-planar maximal modular surfaces.
Extends neural network verification to non-linear specifications.
problem Certifying richer properties of neural networks.
method Introduces convex-relaxable specifications for verification.
result Effective verification of important properties like energy conservation and semantic consistency.
This work optimizes reservoir computing models by linking recurrence and non-linear dynamics.
problem Understanding how recurrence and non-linear dynamics in cortical networks contribute to their function.
method Transformed time-continuous, recurrent dynamics into an effective feed-forward structure of linear and non-linear temporal kernels.
result Optimal time-series classifiers can be built from random reservoir networks, demonstrating significant performance gains.
Proposes method for global explanations of credit risk models.
problem Lack of interpretability in credit risk scoring models.
method Sampling decision function to learn interpretable models.
result Unified solution to approximate complex decision boundaries.
New research shows CFG improves high-dimensional data generation.
problem Characterizing CFG's effect on high-dimensional distributions.
method High-dimensional analysis of CFG's impact on target distributions.
result CFG accurately reproduces the target distribution in high dimensions.
A new PU classifier PUAL tackles trifurcate data issues.
problem Training classifiers on trifurcate data containing only labeled-positive instances and unlabeled instances.
method PUAL classifier with asymmetric loss and kernel-based algorithm.
result PUAL achieves satisfactory classification on trifurcate data.
The paper classifies solitons for a specific type of flow.
problem Classifying solitons for a fully non-linear Yamabe flow.
method Careful analysis of an associated dynamical system.
result Existence and description of solitons for certain dimensions.
This paper explains a mechanism called phase collapse that improves image classification accuracy.
problem Understanding the role of non-linearities and convolutional filters in image classification.
method Demonstrates phase collapse as a mechanism that eliminates spatial variability and linearly separates classes.
result Phase collapse improves classification accuracy, while thresholding operators degrade performance.
Novel SVDD framework classifies water saturation from seismic attributes.
problem Difficult classification of water saturation from diverse and non-linear seismic attributes.
method Support Vector Data Description (SVDD) framework with G-metric performance quantification.
result Proposed framework outperforms existing classifiers.
This paper shows neural networks can learn non-linear sparse parities.
problem The challenge of learning non-linear models with neural networks.
method Gradient descent on depth-two neural networks.
result Sparse parities are learnable by neural networks but not by linear methods.
Learning codes for non-linear computations improves resilience in machine learning.
problem Resilience of machine learning models in the face of unavailability.
method Learning neural network architectures to design codes for non-linear computations.
result Learned codes can reconstruct up to 98% of unavailable predictions from neural networks.
LQF linearizes deep models for better interpretability.
problem Lack of interpretability in deep neural networks.
method Simple modifications to architecture, loss function, and optimization.
result Comparable performance to non-linear fine-tuning, with interpretability.
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.
This study evaluates handwriting features to diagnose Parkinson's disease.
problem Diagnosing Parkinson's disease through handwriting analysis.
method Kinematic, geometrical, and non-linear features were evaluated using K-nearest neighbors, support vector machines, and random forest classifiers.
result Up to 93.1% accuracy in classifying Parkinson's disease and healthy subjects.
META-DES framework selects best classifiers dynamically.
problem Dynamic selection of ensemble classifiers.
method Meta-learning approach to estimate classifier competence.
result META-DES framework improves classification performance.
Deep networks classify and predict with high accuracy.
problem High-dimensional data classification and regression.
method Cascade of linear filters and non-linearities, mathematical analysis of properties.
result Mathematical framework for analyzing deep network properties.
Study uses EEG features HFD and SampEn to detect depression with high accuracy.
problem Diagnosing depression reliably and accurately.
method Applied Higuchi Fractal Dimension and Sample Entropy on EEG signals using seven machine learning algorithms.
result Good classification possible even with small EEG data, achieving high accuracy.
Bistable structures associated with non-linear deformation behavior, exemplified by the Venus flytrap and slap bracelet, can switch between different functional shapes upon actuation. Despite numerous efforts in modeling such large deformation behavior of shells, the roles of mechanical and nonlinear geometric effects …
Here, a non-linear analysis method is applied rather than classical one to study projective Finsler geometry. More intuitively, by means of an inequality on Ricci-Finsler curvature, a projectively invariant pseudo-distance is introduced and an analogous of Schwarz' lemma in Finsler geometry is proved. Next, the Schwarz…
This paper considers a portfolio trading strategy formulated by algorithms in the field of machine learning. The profitability of the strategy is measured by the algorithm's capability to consistently and accurately identify stock indices with positive or negative returns, and to generate a preferred portfolio allocati…
This work generates training-time adversarial data using auto-encoders to manipulate classifiers.
problem Manipulating the behavior of trained classifiers during test time with bounded perturbation.
method An auto-encoder-like network generates perturbations, learning to update weights to produce harmful noise.
result The method can manipulate classifiers effectively, showing good transferability.
Paper introduces r-DEP classifier for binary classification tasks.
problem No natural ordering for feature patterns in practical situations.
method Introduces reduced dilation-erosion (r-DEP) classifier using multi-valued mathematical morphology.
result r-DEP classifiers outperform traditional SVCs in balanced accuracy.
Paper proposes methods to improve SVM classifiers in noisy data scenarios.
problem Improving SVM classifiers when training data contains label noise.
method Mixed Integer Linear and Non Linear models with relabeling and clustering.
result Effective methods improve SVM performance in noisy data scenarios.
A new embedding method for high-dimensional data.
problem Handling large sample sizes in high-dimensional spaces.
method Partitioning space into simplices and embedding into barycentric coordinates.
result Linear classifier in rich feature space yields highly non-linear decision boundaries.
Develops a risk-averse classification method based on coherent risk measures.
problem Designing a classifier that considers risk in classification problems.
method Uses coherent measures of risk and risk sharing ideas to design a risk-averse classifier.
result The risk-sharing classification problem is equivalent to an optimization problem with unequal weights.
New neural network units resist adversarial attacks effectively.
problem Adversarial attacks on neural networks that misclassify inputs.
method Introduced RBFI units with non-linear structure.
result RBFI units maintain high accuracy in adversarial attacks.
Approximating non-linear kernels using feature maps has gained a lot of interest in recent years due to applications in reducing training and testing times of SVM classifiers and other kernel based learning algorithms. We extend this line of work and present low distortion embeddings for dot product kernels into linear…
New algebraic-geometric method classifies superintegrable systems in any dimension.
problem Classifying superintegrable systems in arbitrary dimensions is challenging.
method Algebraic-geometric approach based on quasi-projective varieties.
result Established foundations for classification in arbitrary dimensions.
Extends tangent functor to microformal morphisms, creating non-linear pullbacks for forms and cohomology.
problem Generalizing smooth maps to microformal morphisms for new types of mappings.
method Introduces microformal morphisms and shows how they act on functions and forms via non-linear pullbacks.
result Non-linear pullbacks of forms respect de Rham differentials and induce transformations of cohomology.
CW-ICA improves on ANICA for non-linear source separation.
problem Non-linear source separation challenges with many applications.
method CW-ICA extends ANICA by using a simpler, closed-form optimization target.
result CW-ICA achieves comparable results to ANICA without adversarial training.
New methods improve accuracy and scalability for large datasets in multi-class classification.
problem Improving accuracy and scalability for multi-class classification with large datasets.
method Randomized block kernel matrices for approximation of least-squares support vector machines.
result The proposed methods provide good accuracy and reliable scaling for multi-class classification problems with large data sets.
Paper presents a new method for multiclass classification using hyperplane arrangements.
problem Developing efficient multiclass classifiers.
method Mixed integer programming formulations with hyperplane arrangements, kernel trick adaptation, and dimensionality reductions.
result Our proposal outperforms other methods in multiclass classification tasks.
Paper introduces non-linear process convolutions for multi-output Gaussian processes.
problem Building accurate covariance functions for multi-output Gaussian processes.
method Volterra series for non-linearity, closed-form expressions for mean and covariance.
result Non-linear model outperforms classical process convolution in synthetic and real datasets.
The paper analyzes boosting and minimum-ℓ1-norm classifiers in high dimensions.
problem Understanding the generalization error and optimal Bayes error in boosting.
method High-dimensional asymptotic theory, Gaussian comparison techniques, uniform deviation argument.
result Precise characterizations of boosting test error and optimal Bayes error.
Develops non-linear affine processes for modeling interest rates under parameter uncertainty.
problem Modeling interest rates under Knightian uncertainty.
method Constructs non-linear expectation and links it to a variational form of the Kolmogorov equation.
result Introduces non-linear Vasicek-CIR model suitable for negative interest rates.
Proposes a method to infer causal relationships using non-linear ICA.
problem Inferring causal relationships between variables with non-linear dependencies.
method Non-linear ICA to recover latent disturbances and infer causal direction.
result Demonstrates the effectiveness of the method through simulation and neuroimaging data.
Paper uses non-linear dimension reduction for better economic forecasting.
problem Analyzing economic effects of shocks in large datasets.
method Non-linear dimension reduction in factor-augmented vector autoregressions.
result Non-linear dimension reduction techniques improve forecasting, especially in volatile data.
Optimal algorithms for non-linear ridge bandits reduce burn-in cost.
problem Non-linear models introduce a burn-in period with fixed cost.
method Two-stage algorithm: find initial action, then treat locally linear.
result Two-stage algorithm is statistically optimal.