Support Vector Data Description (SVDD) is a popular outlier detection technique which constructs a flexible description of the input data. SVDD computation time is high for large training datasets which limits its use in big-data process-monitoring applications. We propose a new iterative sampling-based method for SVDD…
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.
169,181 papers · 148 categories
Trend · papers per month
48 results for “Support Vector Data Description”
A new method for projecting multimodal data to a common subspace for one-class classification.
problem Classifying data from multiple sources with varying features.
method Iterative transformation to a common subspace, separate transformations for each modality, regularization strategies.
result Outperforms competing methods across multiple datasets.
A new method for one-class classification using ellipsoidal encapsulation.
problem One-class classification for data optimization.
method Iterative transformation into an optimized subspace with regularization terms.
result Better results in one-class classification compared to existing methods.
Enhances SVM for uncertain data with probabilistic Gaussian distributions.
problem Binary classification with uncertain data and error bounds.
method Probabilistic kernel Support Vector Machines using Gaussian distributions.
result Suitable kernel function for uncertain data.
Paper proposes a new method to automatically select Gaussian kernel bandwidth for SVDD.
problem Selecting optimal Gaussian kernel bandwidth for SVDD is crucial but challenging.
method Automatic unsupervised method for selecting Gaussian kernel bandwidth.
result The selected bandwidth is competitive with existing methods and can be computed quickly.
Support Vector Data Description (SVDD) is a machine-learning technique used for single class classification and outlier detection. SVDD formulation with kernel function provides a flexible boundary around data. The value of kernel function parameters affects the nature of the data boundary. For example, it is observed …
New method selects kernel bandwidth for SVDD and OCSVM.
problem Selecting optimal Gaussian kernel bandwidth for SVDD and OCSVM.
method Exploits low-rank representation of kernel matrix to suggest bandwidth.
result Method performs well for both low-dimensional and high-dimensional data.
An incremental SVDD algorithm for online data using Gaussian kernel.
problem Efficiently handling online or large data for SVDD.
method Incremental learning algorithm using Gaussian kernel, focusing on existing support vectors and new data points.
result Significant gains in efficiency with almost no loss in outlier detection accuracy or objective function value.
New results on max-entropy distributions with succinct descriptions and stability.
problem Understanding the complexity and stability of max-entropy distributions.
method Polynomial-time algorithms and bounds on bit complexity.
result Polynomial bit complexity of ε-optimal dual solutions to max-entropy convex programs.
SVDD and Deep SVDD improve radar target detection in clutter.
problem Clutter and thermal noise degrade classical radar detection methods.
method Support Vector Data Description (SVDD) and Deep SVDD for one-class learning.
result SVDD and Deep SVDD outperform traditional methods on simulated radar data.
Support Vector Data Description (SVDD) provides a useful approach to construct a description of multivariate data for single-class classification and outlier detection with various practical applications. Gaussian kernel used in SVDD formulation allows flexible data description defined by observations designated as sup…
A Theory of the Risk for Optimization with Relaxation and its Application to Support Vector Machinescs.LG
New results on risk estimation for SVM and related methods.
problem Estimating risk in support vector machine applications.
method Expanding relaxation theory to support vector methods and analyzing their generalization ability.
result Risk approaches ratio of complexity to data sample size as sample size increases.
A new method detects outliers in dirty data using a leave-out strategy.
problem Outliers in training data skew support vector machine performance.
method Leave-out strategy: temporarily omit one candidate at a time for outlier detection.
result The leave-out strategy improves outlier detection compared to existing methods.
Proposes LAMA for principled SVDD hyperparameter estimation.
problem Estimating SVDD hyperparameters is difficult and heuristic methods are unreliable.
method LAMA (Local Active Min-Max Alignment) using active learning and kernel alignment.
result LAMA provides evidence-based estimates for SVDD hyperparameters with quality scores.
Improves anomaly detection with contaminated unlabeled data.
problem Weakness in existing semi-supervised anomaly detection methods when unlabeled data contain anomalies.
method Integrates positive-unlabeled learning with deep anomaly detection models.
result Achieves better detection performance on various datasets.
Detects and explains anomalies in non-i.i.d data with latent-class dependencies.
problem Detecting and explaining anomalies in data with latent-class dependencies.
method Derives SVDD method to handle latent-class dependency structure, provides probabilistic interpretation.
result Demonstrates effectiveness on real-world offshore data.
Morse neural networks improve uncertainty quantification and detection.
problem Uncertainty quantification and out-of-distribution detection.
method Generalizes unnormalized Gaussian densities to high-dimensional submanifolds using KL-divergence loss.
result Unified approach for OOD detection, anomaly detection, and continuous learning.
Variational Optimizationstat.ML
We discuss a general technique that can be used to form a differentiable bound on the optima of non-differentiable or discrete objective functions. We form a unified description of these methods and consider under which circumstances the bound is concave. In particular we consider two concrete applications of the metho…
New method prevents mode collapse in deep SVDD for anomaly detection.
problem Mode collapse in deep SVDD due to architectural constraints.
method Two regularizers: noise injection and minibatch variance penalization.
result Regularized deep SVDD outperforms state-of-the-art methods.
Proposed SMO algorithm for OC-SVM+ significantly outperforms non-sequential algorithms.
problem One-class SVM with privileged information
method Sequential Minimal Optimization (SMO) algorithm
result Finite-time convergence established
Quantum SVM clustering speeds up big data analysis.
problem Performance degradation of classical SVM clustering on big data.
method Developed a quantum version of SVM clustering using quantum support vector machine and kernels.
result Significant speed-up gain on run-time complexity.
Support spinor machine extends SVM to handle spinor fields in time series data.
problem Handling nonstationary and nonlinear time series data for classification.
method Using wedge product to extend vector fields to spinor fields, extending SVM to support spinor machine.
result Support spinor machine outperforms SVM in one class classification of physiological time series data.
Paper adapts SVDD for 3D-shapes filtering and outlier detection.
problem Filtering and detecting outliers in 3D-shapes.
method Adapted SVDD to SimpleMKL, developing Slim-MK-SVDD for tighter boundaries.
result Slim-MK-SVDD produces a tighter boundary around data.
A new method for support vector regression using a data-driven insensitive parameter.
problem Determining an optimal insensitive parameter in support vector regression.
method A data-driven approach to approximate the insensitive parameter by minimizing a generalized loss function based on the likelihood principle.
result The proposed method outperforms traditional support vector regression methods and has lower computational costs.
Minimal SVM reduces support vectors for better classification.
problem Finding optimal hyperplane for classification with fewer support vectors.
method Proposes a Minimal SVM using L0.5 norm on slack variables.
result Increases classification performance by reducing support vectors.
Tensor approach simplifies Euclidean space descriptions.
problem Simplifying tensor descriptions of Euclidean spaces.
method Emphasizes geometric vectors in tensor description.
result Proved integral identities with vector integrands.
Enhances network intrusion detection in noisy data.
problem Robustness against contaminated and noisy data inputs in network intrusion detection.
method Probabilistic Temporal Graph Network Support Vector Data Description (TGN-SVDD) model.
result Significant improvements in detection performance with synthetic noise.
Quantum algorithm solves SOCP and SVM problems faster than classical methods.
problem Quantum algorithms for solving SOCP and SVM problems.
method Quantum interior-point method (IPM) for SOCP, scaling as O(n^k).
result Quantum algorithm exhibits polynomial speedup over classical methods.
New process capability index for non-normal data.
problem Measuring process capability when data does not follow normal distributions.
method Developed a new multivariate non-parametric PCI using Support Vector Data Description (SVDD).
result Demonstrated improved accuracy in process capability measurement for non-normal data.
Distributed estimation of principal support vector machines for sufficient dimension reductionstat.ML
New algorithms reduce computational burden for principal support vector machines.
problem High computational cost of principal support vector machines for large datasets.
method Two distributed estimation algorithms for principal support vector machines.
result Statistical efficiency is maintained with distributed algorithms.
Bayesian SVM method speeds up big data predictions.
problem Efficiently predicting with big data and uncertainty.
method Stochastic variational inference and inducing points.
result Faster than competing Bayesian methods, scalable to millions of data points.
Solving different types of optimization models (including parameters fitting) for support vector machines on large-scale training data is often an expensive computational task. This paper proposes a multilevel algorithmic framework that scales efficiently to very large data sets. Instead of solving the whole training s…
Many datasets can be viewed as a noisy sampling of an underlying space, and tools from topological data analysis can characterize this structure for the purpose of knowledge discovery. One such tool is persistent homology, which provides a multiscale description of the homological features within a dataset. A useful re…
A new SVM method for predicting time series labels.
problem Learning to predict labels from high-dimensional time series data.
method Extended SVM concept to continuous time series data, formulated as a convex optimization problem.
result Empirical results show the algorithm's effectiveness for analyzing long-term multivariate data.
Anomaly detection with LSTM neural networks for variable-length data.
problem Anomaly detection in variable-length data sequences.
method LSTM neural networks, OC-SVM, SVDD, gradient and quadratic programming.
result Significant performance gains over conventional methods.
Paper proposes DMGD for integrating outlier and community detection in graph embedding.
problem Outlier nodes affect graph embedding of regular nodes, especially in networks with multiple communities.
method DMGD integrates outlier and community detection with node embedding using multiclass graph description.
result DMGD detects outliers relative to their communities and achieves better node embedding compared to state-of-the-arts.
This paper speeds up SVC clustering by compressing data while preserving key properties.
problem Efficiently clustering large-scale real-world data sets.
method Spectrum-preserving data compression for fast support vector clustering.
result Achieved 100X and 115X speedups on real-world data sets while maintaining clustering quality.
Introduces STTM to improve STM's performance.
problem Overfitting and curse of dimensionality in SVM.
method Replaces rank-one tensor in STM with tensor train.
result STTM outperforms SVM and STM.
RAPID efficiently samples SVDD subsets for better anomaly detection.
problem Efficiently sampling SVDD subsets for large datasets.
method Formulated as an optimization problem, RAPID selects samples that approximate the full SVDD decision boundary.
result RAPID outperforms competitors in classification accuracy, sample size, and runtime.
Predict road friction levels using connected vehicle data and weather parameters.
problem Predict road friction levels for connected vehicles.
method Proposes a framework using supervised machine learning (logistic regression, SVM, neural networks) to classify road friction levels.
result Neural networks model performs best across different prediction horizons and conditions.
A new OCC model for unbalanced datasets with better interpretability.
problem Handling unbalanced datasets in OCC.
method Kernel density estimation within a tree-based learning algorithm (OC-Tree).
result The OC-Tree outperforms state-of-the-art methods on benchmark datasets.
Deep-learning model detects ASD from MRI data with high accuracy.
problem Challenges in diagnosing ASD due to subjective behavioral assessments and informant biases.
method Integrates deep-learning and SVM techniques to classify ASD brain scans.
result Highly accurate classification of ASD brain scans from neurotypical scans.
We propose an algorithm for exploring the entire regularization path of asymmetric-cost linear support vector machines. Empirical evidence suggests the predictive power of support vector machines depends on the regularization parameters of the training algorithms. The algorithms exploring the entire regularization path…
Statistical learning theory explains SVMs for data-driven decision making.
problem Decision making and model construction from data.
method Statistical learning theory, focusing on empirical and structural risk minimization.
result Support Vector Machines (SVMs) are a prominent implementation of structural risk minimization.
Distributed SVM algorithm improves performance in real-world applications.
problem Improving SVM performance in distributed computing environments.
method Proposes HPSVM, a distributed SVM algorithm that minimizes inter-machine communications.
result HPSVM achieves similar or better results than state-of-the-art SVM techniques.
The support vector machine (SVM) is a widely used method for classification. Although many efforts have been devoted to develop efficient solvers, it remains challenging to apply SVM to large-scale problems. A nice property of SVM is that the non-support vectors have no effect on the resulting classifier. Motivated by …
SVM generalizes well even with many support vectors in high dimensions.
problem Generalization of SVM in high-dimensional spaces with many support vectors.
method Identified new deterministic equivalences and proved conditions for support vector proliferation.
result Broadened conditions for SVM generalization in high-dimensional settings and proved converse result.
SMM preserves matrix data structure for SVM classification.
problem Preserving spatial correlations in matrix data for SVM.
method SMM uses spectral elastic net combining nuclear and Frobenius norms.
result SMM improves SVM performance on matrix data.