New framework for fair and stable classification.
problem Stability of fair classification algorithms under dataset variations.
method Extended fair classification framework with stability regularization.
result Improved stability with only slight accuracy loss.
Enhanced KNN-TSVM reduces noise and overfitting with stable learning rules.
problem High computational cost and overfitting in KNN-based TSVM classifiers.
method Weighted KNN with stabilizer term and LDMDBA for efficient computation.
result Effective in both classification accuracy and computational time, with up to 14x speedup.
Proposes a stable classifier using inflated argmax for multiclass classification.
problem Inherent instability of taking the maximizer in multiclass classification.
method Bagging for stable continuous scores, inflated argmax for stable labels.
result Inflated argmax provides necessary protection against unstable classifiers without loss of accuracy.
New optimization methods for neural networks improve classification accuracy.
problem Optimizing shallow networks for binary classification.
method Introducing a new family of optimization problems not covered by existing methods.
result New training algorithms with stable convergence and improved performance.
NodeSig efficiently computes binary node embeddings for scalable graph analysis.
problem Scalability issues in graph representation learning models.
method NodeSig uses random walk diffusion probabilities and stable random projections to compute binary node embeddings efficiently.
result NodeSig achieves a good balance between accuracy and efficiency on node classification and link prediction tasks.
We improve MoE models for classification with rigorous guarantees and practical methods.
problem Limited guarantees for stable maximum-likelihood training and model selection in softmax-gated MoE models.
method Derived a batch MM algorithm with closed-form updates, proved finite-sample rates, and developed a dendrogram selector.
result Achieved near-parametric optimal rates for parameter recovery and improved accuracy over baselines.
The study examines how class imbalance impacts logistic regression models in low-default credit portfolios.
problem The impact of class imbalance on logistic regression models in low-default credit portfolios.
method Simulation study with controlled data-generating mechanisms to vary class imbalance and predictor-response association strength.
result Classification accuracy decreases significantly as event rate decreases, and optimal cut-off shifts with imbalance.
SIRUS creates interpretable rules from random forests for manufacturing.
problem Lack of interpretability in complex models for critical decisions.
method SIRUS is a classification algorithm based on random forests that produces a simple list of rules.
result SIRUS achieves stability and accuracy comparable to random forests.
Randomly shuffled kernels can be compressed efficiently.
problem Reducing storage cost of CNN parameters on resource-limited platforms.
method Randomly-shuffled tensor decomposition (RsTD) to embed kernels into random low-rank subspaces.
result CNNs can be significantly compressed even with randomly shuffled kernels, achieving more stable accuracy.
SoftAD improves classification accuracy with less fine-tuning and fewer computational costs.
problem Improving classification accuracy with less fine-tuning and fewer computational costs.
method SoftAD is a softened, pointwise mechanism that downweights borderline points and limits the effects of outliers.
result SoftAD achieves classification accuracy competitive with flooding and SAM, with a smaller loss generalization gap and model norm.
Convolutional and Recurrent, deep neural networks have been successful in machine learning systems for computer vision, reinforcement learning, and other allied fields. However, the robustness of such neural networks is seldom apprised, especially after high classification accuracy has been attained. In this paper, we …
Study on hyperparameter optimization for smartphone-based HAR.
problem Maintaining stable classification accuracy in HAR systems with mobile devices.
method Semi-supervised classifier and study on hyperparameter configuration.
result Adjusting hyperparameters can maintain classification accuracy.
Proof that stable minimal surfaces in 3D are flat.
problem Classification of stable minimal surfaces in R3. method Index theory for Dirac operators on twisted spinor bundles.
result Every complete two-sided stable minimal surface in R3 is flat. New study shows Gaussian samplers struggle with heavy-tailed targets, while stable samplers excel.
problem The difficulty of sampling from heavy-tailed distributions using Gaussian versus stable oracles.
method Comparison of Gaussian and stable oracles for proximal samplers.
result Gaussian samplers have a fundamental barrier for high-accuracy guarantees in heavy-tailed sampling, while stable samplers excel.
Classifies when homeomorphism groups of stable surfaces have automatic continuity.
problem Determining when homeomorphism groups of stable surfaces are continuous.
method Developed a general framework to prove automatic continuity for homeomorphism groups, applied to stable surfaces and Stone spaces.
result Classification of stable surfaces with respect to automatic continuity of their homeomorphism groups.
Classifies very stable Higgs bundles for complex groups.
problem Classifying Higgs bundles for arbitrary complex groups.
method Classification based on stability and Higgs field properties.
result Extends previous classification for GLn to arbitrary groups.
Measures neural network decision boundary volume to predict model performance.
problem Understanding the geometry of deep learning models for better performance.
method Local surface volumes to measure decision boundary, applying Weyl's tube formula.
result Smaller surface volume correlates with higher classification accuracy.
New classification for some unorientable 4-manifolds using modified surgery theory.
problem Classifying stable diffeomorphism classes of unorientable 4-manifolds.
method Modified surgery theory applied to unorientable 4-manifolds with specific fundamental groups.
result Found nine stable diffeomorphism classes for pin+ manifolds, one for pin−, and four for neither, under certain conditions. Paper uses topological data analysis for time series classification.
problem Classifying univariate time series data, especially physiological signals.
method Persistent homology for feature engineering, followed by machine learning.
result Higher accuracy achieved with fewer features compared to traditional methods.
Classification of 4-manifolds with finite fundamental groups using stable homeomorphism criteria.
problem Classifying 4-manifolds with finite fundamental groups.
method Using stable homeomorphism criteria based on quadratic 2-types and Kirby-Siebenmann invariant.
result Two 4-manifolds are CP2-stably homeomorphic if and only if their quadratic 2-types are stably isomorphic and their Kirby-Siebenmann invariant agrees. Proposes a new method to improve CNNs' shift invariance and accuracy.
problem Improving CNNs' shift invariance and prediction accuracy.
method Replaces RMax with CMod, a Gabor-like structure, to increase shift invariance and accuracy.
result Achieves superior accuracy on ImageNet and CIFAR-10 classification tasks.
The Rectified Linear Unit (ReLU) is a foundational activation function in artficial neural networks. Recent literature frequently misattributes its origin to the 2018 (initial) version of this paper, which exclusively investigated ReLU at the classification layer. This paper formally corrects the citation record by tra…
A novel approach stores encoded images as centroids and covariance matrices to improve classification accuracy with less memory.
problem Catastrophic forgetting and memory limitations in continual learning.
method Trains autoencoders with Neural Style Transfer to encode images, replay encoded episodes to avoid forgetting, and use centroids and covariance matrices for pseudo-images when memory is full.
result Increases classification accuracy by 13-17% over state-of-the-art methods on benchmark datasets, while requiring 78% less storage space.
Method predicts multistable system states from sparse measurements.
problem Predicting multistable system states from limited data.
method Semi-supervised classification with SPML optimization.
result 95% accuracy in predicting reaction-diffusion equation states.
Homotopy theory for (2n+1)-dimensional manifold triads with fixed boundary.
problem Classifying stable moduli spaces of (2n+1)-dimensional manifold triads. method Homotopy-theoretic description of stable moduli spaces, stabilization by boundary connected sum with SnimesDn+1. result Established homology of stable moduli spaces for (2n+1)-dimensional manifold triads. PFDL improves deep learning models' OOD generalization by decorrelating feature embeddings.
problem Out-of-distribution generalization in deep learning models.
method PFDL algorithm that optimizes feature decomposition network and image classification model.
result PFDL improves the accuracy of image classification models on OOD datasets.
GCWSNet improves neural network training speed and accuracy with power transformation.
problem Training deep neural networks efficiently and accurately.
method Developed GCWS for hashing powered-GMM kernel, enabling power transformation on data.
result GCWSNet often improves classification accuracy and converges faster with one epoch.
We study compact stable embedded minimal surfaces whose boundary is given by two collections of closed smooth Jordan curves in close planes of Euclidean 3-space. Our main result is a classification of these minimal surfaces, under certain natural geometric asymptotic constraints, in terms of certain associated varifold…
Supervised contrastive learning improves image classification accuracy.
problem Improving image classification accuracy using supervised contrastive learning.
method Extending self-supervised batch contrastive approach to fully-supervised setting, leveraging label information.
result Top-1 accuracy of 81.4% on ImageNet dataset, outperforming cross-entropy.
Stable compact minimal submanifolds of the product of a sphere and any Riemannian manifold are classified whenever the dimension of the sphere is at least three. The complete classification of the stable compact minimal submanifolds of the product of two spheres is obtained. Also, it is proved that the only stable comp…
New methods for estimating ARMA and GARCH models with stable noise.
problem Estimating parameters of ARMA and GARCH models with stable noise.
method Modified Hannan-Rissanen Method and Modified Empirical Characteristic Function for estimation.
result Efficiency, accuracy, and simplicity of proposed methods demonstrated through simulation.
The paper proposes a method to create domain-invariant representations using Wasserstein distance.
problem Domain shifts in training data affect machine learning model performance across different domains.
method The method combines classification/regression losses with a GAN-type discriminator to minimize the Wasserstein distance between domains.
result The approach produces the highest minimum classification accuracy and most invariant representation across domains.
The study classifies stable submanifolds in product spaces of projective spaces.
problem Classifying stable submanifolds in product spaces of projective spaces.
method Provided a classification theorem for compact stable minimal immersions in product spaces of projective spaces.
result Characterized complex minimal immersions in the product of two complex projective spaces.
The paper examines how adversarial robustness affects accuracy disparity across different classes.
problem Understanding the impact of adversarial robustness on accuracy disparity across different classes.
method Linear classifiers under a Gaussian mixture model, decomposing the impact into inherent and imbalance effects.
result Adversarial robustness consistently degrades standard accuracy in balanced classes, but the class imbalance ratio plays a different role in accuracy disparity.
We study closed, oriented 4-manifolds whose fundamental group is that of a closed, oriented, aspherical 3-manifold. We show that two such 4-manifolds are stably diffeomorphic if and only if they have the same w_2-type and their equivariant intersection forms are stably isometric. We also find explicit algebraic invaria…
A new method for fair classification using characteristic function distance.
problem Fairness in high-stakes decision-making with sensitive groups.
method Proposes a novel approach based on characteristic function distance to ensure minimal sensitive information in learned representations.
result Consistently matches or achieves better fairness and predictive accuracy than existing methods.
New ODE solvers improve training efficiency and accuracy.
problem Training Neural ODEs requires efficient and accurate gradient calculation.
method Presented algebraically reversible ODE solvers that are time and memory efficient, calculate exact gradients, and are numerically stable.
result Reversible solvers strictly improve upon previous architectures in efficiency and accuracy.
New method classifies spin 4-manifolds using Kervaire-Milnor invariant.
problem Classifying spin 4-manifolds up to stabilisation.
method Using Kervaire-Milnor invariant to compute Arf invariants and classify.
result New stable classification of spin 4-manifolds with 2-dimensional fundamental groups.
Randomized classifiers improve strategic classification efficiency.
problem Designing optimal classifiers in strategic classification games.
method Investigation of randomized classifiers and their efficiency in strategic classification.
result Randomized classifiers are necessary for maximizing classification efficiency.
Classifies stable diffeomorphism of spin 4-manifolds with specific fundamental groups.
problem Classifying stable diffeomorphism of spin 4-manifolds with given fundamental groups.
method Formulated conjectural relationships between algebraic invariants and obstructions, proved for specific groups.
result Proved conjectures for specific fundamental groups, providing complete algebraic stable classification.
Mapper-GIN simplifies 3D point cloud classification with lightweight structure.
problem Robust 3D point cloud classification under corruption.
method Mapper algorithm for structural decomposition, GIN for graph classification.
result Mapper-GIN achieves competitive accuracy with minimal parameters.
MOSS optimizes decision rules for accuracy and stability.
problem Constructing stable sets of decision rules.
method Multi-objective optimization framework incorporating sparsity, accuracy, and stability.
result MOSS outperforms state-of-the-art rule ensembles in predictive performance and stability.
The paper explores density of stable mappings and their properties.
problem Density of stable mappings in different dimensions.
method Infinitesimal and algebraic methods to prove density of proper stable and topologically stable mappings.
result Density of topologically stable mappings holds for any pair (n,p), and for proper stable mappings if (n,p) is in nice dimensions.
This paper is concerned with the problem of stable diffeomorphism classification of 4-manifolds obtained using the surgery on loops. The main theorem states that under the assumption that the normal 1-type of two 4-manifolds in question is the same, the only classifying invariant is the signature. In particular, in som…
We prove that any C2 complete, orientable, connected, stable area-stationary surface in the sub-Riemannian Heisenberg group H1 is either a Euclidean plane or congruent to the hyperbolic paraboloid t=xy.
A TTA framework improves forecasting accuracy in non-stationary time series.
problem Improving forecasting accuracy in non-stationary time series.
method Normalization-based test-time adaptation for causal timeseries forecasting and direction classification.
result Normalization-based TTA improves forecasting error in synthetic gradual drift and can even hurt in aggressive norm-only adaptation in financial markets.
In this paper, we prove a classification theorem for the stable compact minimal submanifolds of the Riemannian product of an m1-dimensional (m1≥3) hypersurface M1 in the Euclidean space and any Riemannian manifold M2, when the sectional curvature KM1 of M1 satisfies $\frac{1}{\sqrt{m_1-1}}\leq K…
We introduce the anti-profile Support Vector Machine (apSVM) as a novel algorithm to address the anomaly classification problem, an extension of anomaly detection where the goal is to distinguish data samples from a number of anomalous and heterogeneous classes based on their pattern of deviation from a normal stable c…