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.
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.
Improved fuzzy support vector machine for stock price trend forecasting.
problem Weak performance of traditional support vector machines in handling fuzzy and noisy data.
method Proposed a novel advanced fuzzy support vector machine (NA-FSVM) to improve precision.
result Improved model precision in predicting stock price trends.
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 vector machines have attracted much attention in theoretical and in applied statistics. Main topics of recent interest are consistency, learning rates and robustness. In this article, it is shown that support vector machines are qualitatively robust. Since support vector machines can be represented by a functio…
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.
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.
Rgtsvm speeds up SVMs on GPUs for big data.
problem Scaling SVMs to large datasets.
method GPU acceleration for SVM classification and regression.
result Up to 100x performance improvement for millions of examples.
Study on recovering supports of multiple sparse vectors from mixed linear measurements.
problem Recovering supports of multiple sparse vectors from a mixture of linear measurements.
method Developed algorithms to identify the support of all component vectors using polynomial and quasi-polynomial number of measurements.
result Polynomial and quasi-polynomial number of measurements sufficient for recovering the supports of all component vectors.
Proposes algorithm to explore entire regularization path for asymmetric-cost SVMs.
problem Predictive power of SVMs depends on regularization parameters.
method Develops algorithm to explore entire regularization path for asymmetric-cost linear SVMs.
result Demonstrates two-dimensional regularization paths for linear SVMs.
The paper proposes an algorithm to enumerate K best models with distinct support vectors for SVM.
problem Finding multiple models with distinct support vectors for non-standard machine learning applications.
method A K-best model enumeration algorithm for SVM that efficiently finds models with distinct support vectors in the dual SVM problem.
result The algorithm efficiently finds the next best model with small latency, useful for interactive examination of requirements.
Efficiently handles large support vectors in kernelized online learning.
problem Efficiency in communication for large support vectors in kernelized models.
method Extends a previously proposed protocol to kernelized online learners, introducing a novel communication criterion.
result Communication is bounded by the loss suffered, improving efficiency.
This paper proposes MMD-SVR to improve SVR's margin distribution for better generalization.
problem Improving SVR's generalization performance by maximizing the margin distribution of the whole dataset.
method Introducing MMD-SVR with coupled constraints to convert a non-convex optimization problem into a convex one.
result MMD-SVR significantly improves prediction accuracy and generalization compared to classic SVR.
SVM and linear regression models coincide in high dimensions.
problem Understanding the connection between SVM and linear regression in high-dimensional data.
method Analyzing feature models and proving lower bounds on dimensionality.
result A sharp phase transition in Gaussian feature models, with support vector proliferation occurring only in very high dimensions.
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.
LIBTwinSVM offers a free library for efficient Twin Support Vector Machines.
problem Large-scale classification problems.
method Efficient implementation of Twin Support Vector Machines.
result Effectiveness demonstrated through benchmarks.
GVM replaces SVM with general project vectors and a Monte Carlo algorithm for improved feature extraction.
problem Improving feature extraction and reducing overlearning in SVM.
method Replaces support vectors with general project vectors and uses a Monte Carlo algorithm to find them.
result The GVM can achieve better performance, especially for small-set training problems.
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.
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.
Investigates point spectra of vector fields and their properties.
problem Understanding the point spectra of vector fields.
method Define and study point spectra, prove properties under isometries, and analyze compactly supported fields.
result Point spectra are well-behaved under isometries and trivial for compactly supported fields.
In this paper we solve support vector machines in reproducing kernel Banach spaces with reproducing kernels defined on nonsymmetric domains instead of the traditional methods in reproducing kernel Hilbert spaces. Using the orthogonality of semi-inner-products, we can obtain the explicit representations of the dual (nor…
Algebraic multigrid speeds up SVM training for large datasets.
problem Computational inefficiency of support vector machines on large-scale data.
method Inspired by algebraic multigrid, a fast multilevel framework for solving SVM models.
result Significant improvement in running time achieved without loss in quality.
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.
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.
EnsembleSVM is a free software package containing efficient routines to perform ensemble learning with support vector machine (SVM) base models. It currently offers ensemble methods based on binary SVM models. Our implementation avoids duplicate storage and evaluation of support vectors which are shared between constit…
Support vector classifier constructs confidence sets for binary classification.
problem Learning confidence sets with specific probability guarantees for binary classification.
method Support vector classifier to construct confidence sets.
result The proposed learner controls non-coverage rates and minimizes ambiguity with high probability.
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.
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…
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 …
The paper studies skew ruled surfaces with specific normalization properties.
problem Characterizing skew ruled surfaces with relative normalizations.
method Analyzes skew ruled surfaces in E3 with a specific form of support function. result Investigates properties of Tchebychev and support vector fields for these surfaces.
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.
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.
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.
A new SVM classifier using L0/1 soft-margin loss for improved performance.
problem Improving SVM performance in binary classification tasks.
method Introducing L0/1 soft-margin loss and using the alternating direction method of multipliers. result The new L0/1-SVM model generates better performance with shorter computational time and fewer support vectors. Paper solves support vector regression in Banach spaces using tensor-kernels.
problem Support vector regression in Banach function spaces.
method Fenchel-Rockafellar duality theory and tensor-kernel representation.
result Explicit formulation of dual problem and optimality conditions.
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 algorithm improves SVM models by making them sparser and more stable.
problem Training SVM models with sparsity and stability.
method Modified Frank-Wolfe algorithm with re-weighted L2 SVM.
result The algorithm produces sparser SVM models with improved stability.
Paper proposes a new pipeline for few-shot classification using forget-update module and channel vector sequence.
problem Few-shot classification with limited support samples.
method Channel vector sequence construction module and forget-update module.
result Pipeline achieves state-of-the-art results on various datasets.
We provide a formulation for Local Support Vector Machines (LSVMs) that generalizes previous formulations, and brings out the explicit connections to local polynomial learning used in nonparametric estimation literature. We investigate the simplest type of LSVMs called Local Linear Support Vector Machines (LLSVMs). For…
A k-means clustering-based SVM method classifies aggressive and moderate drivers.
problem Classifying drivers based on their curve-negotiating behaviors.
method k-means clustering for feature extraction, SVM for classification.
result kMC-SVM method reduces recognition time and improves classification accuracy.
The paper improves SVR with linear constraints for better model properties.
problem Improving Support Vector Regression with linear constraints.
method Generalized SMO algorithm for solving optimization with linear constraints.
result The proposed method shows better practical performance on various datasets.
A new method for fast incremental/decremental analysis without recursion.
problem Efficiently updating support-vector models with new data.
method Ridge Support Vector Models with Weight-Error Curves (WECs) for recursion-free computation.
result All new Lagrangian multipliers can be computed simultaneously, relaxing previous constraints.
New IRLS algorithms for SVM fitting via MM approach.
problem Fitting support vector machines (SVMs) via quadratic programming.
method Majorization--Minimization (MM) paradigm for iteratively-reweighted least-squares (IRLS) algorithms.
result IRLS algorithms for SVM risk minimization problems with various losses and penalties.
Paper proposes SVM-based methods for inferring interaction networks.
problem Modeling interaction between variables in time series and high dimensions.
method Two approaches: neighborhood SVM and restricted Bayesian network for time series.
result Efficiency demonstrated through simulations with linear and nonlinear data.
In this paper, we investigate a multivariate multi-response (MVMR) linear regression problem, which contains multiple linear regression models with differently distributed design matrices, and different regression and output vectors. The goal is to recover the support union of all regression vectors using l1/l2-reg…
Proposes MLPSVM for multi-label learning, improving on binary relevance.
problem Handles multi-label learning tasks more efficiently than binary relevance.
method Uses standard support vector machines with parallel decision hyper-planes.
result Outperforms other multi-label learning algorithms on various data sets.
We present an approximation scheme for support vector machine models that use an RBF kernel. A second-order Maclaurin series approximation is used for exponentials of inner products between support vectors and test instances. The approximation is applicable to all kernel methods featuring sums of kernel evaluations and…
Fuzzy Bounded Twin Support Vector Machine for large datasets and streaming data.
problem Handling large datasets and learning from data streams.
method Combining TWSVM with fuzzy membership function and using dual coordinate descent with Fourier Gaussian approximation.
result Fuzzy Bounded Twin Support Vector Machine (FBTWSVM) provides fast training and robust classification.