New reformulations for multiclass classification problems using optimal transport.
problem Adversarial multiclass classification problems.
method Multimarginal optimal transport formulation.
result Reveals geometric structure and extends binary classification results.
The number of possible methods of generalizing binary classification to multi-class classification increases exponentially with the number of class labels. Often, the best method of doing so will be highly problem dependent. Here we present classification software in which the partitioning of multi-class classification…
Investigates the limits of cost-sensitive classification problems.
problem Cost-sensitive classification problem in mission-critical applications.
method Extending the minimax lower bound of balanced binary classification problem.
result Cost terms significantly impact the hardness of the problem.
New framework tackles adversarial classification problems.
problem Security classification problems with adversaries.
method Adversarial risk analysis approach.
result Illustrated with examples and discussed computational issues.
C-HMCNN(h) improves HMC classification by leveraging class hierarchy.
problem Hierarchical multi-label classification with class hierarchy constraints.
method Exploits class hierarchy to produce coherent predictions for multi-label classification.
result C-HMCNN(h) outperforms state-of-the-art models in HMC classification.
Estimates neural network errors for classification problems.
problem Binary and multi-class classification problems.
method Rademacher complexity estimates and direct approximation theorems.
result A priori error estimates for regularized loss functionals.
Probabilistic learning for binary classification with categorical variables.
problem Binary classification with categorical covariates.
method Probabilistic analysis and two algorithms for learning boolean functions.
result Effective learning of boolean functions from binary data.
Introduces topological deep learning for neural network classification problems.
problem Classifying neural networks using minimal topological structures.
method Formalizes classification problems in a topological setting.
result Demonstrates conditions for the feasibility of classification problems in neural networks.
New NHCAs improve multi-category classification efficiency.
problem Efficient multi-category classification for real-world problems.
method Twin SVM (TWSVM), Generalized eigenvalue proximal SVM (GEPSVM), Regularized GEPSVM (RegGEPSVM), and Improved GEPSVM (IGEPSVM) with OAA, BT, and TDS approaches.
result TDS-TWSVM outperforms other methods in classification accuracy.
Improved KELM for multiclass classification with wavelet kernel.
problem Low test accuracy in multiclass classification problems.
method Mexican Hat wavelet kernel ELM.
result Significantly improved performance compared to other classifiers.
RFSVM uses learned RF similarity for HDLSS classification.
problem High dimension, low sample size classification problems.
method Transposes RFD approach to HDLSS classification using RF similarity as SVM kernel.
result RFSVM outperforms existing methods for HDLSS problems.
We show how binary classification methods developed to work on i.i.d. data can be used for solving statistical problems that are seemingly unrelated to classification and concern highly-dependent time series. Specifically, the problems of time-series clustering, homogeneity testing and the three-sample problem are addr…
This paper classifies solutions for a specific geometric problem.
problem Classifying solutions for the planar isotropic Lp dual Minkowski problem. method Converted the ODE for the solution into an integral and studied its asymptotic behavior, duality, and monotonicity.
result Complete classification of solutions for the equation.
Unified fair classification with provable guarantees.
problem Fairness in classification algorithms for sensitive attributes.
method Meta-algorithm for convex and non-convex constraints.
result Provable guarantees for multiple fairness metrics.
Few-shot image classification is improved by correcting CNNs' texture bias.
problem Few-shot image classification performance is hindered by CNNs' texture bias.
method Corrected CNNs' texture bias using a simpler method than state-of-the-art approaches.
result State-of-the-art performance on miniImageNet task achieved.
Advances few-shot classification by treating it as supervised learning and proposing new training techniques.
problem Formulating the ability of humans to learn from limited data in machine learning.
method Formulated few-shot classification as a supervised learning problem and introduced multi-episode and cross-way training techniques.
result Proposed training strategies accelerate the training process without accuracy loss.
Graph-based multi-label classifier extends CULP for multi-label data.
problem Solving multi-label classification problems.
method Extends CULP algorithm to handle multi-label data.
result Competitive results compared to cutting-edge multi-label classifiers.
Proposes an angle-based framework for multicategory cost-sensitive classification.
problem Cost-sensitive multicategory classification challenges.
method Angle-based cost-sensitive classification framework without sum-to-zero constraint.
result Proposed boosting algorithms yield competitive classification performances.
Improved classification with costly features using deep reinforcement learning.
problem Optimizing classification error with limited and costly feature acquisition.
method Revisited Q-learning approach with neural network approximation for sequential feature requests and classification decisions.
result Deep reinforcement learning approach comparable to state-of-the-art algorithms, robust across datasets.
Improved Naive Bayes for text classification with small datasets.
problem Poor performance of Naive Bayes in small training datasets.
method Introducing a correlation factor to Naive Bayes estimator.
result Our method achieves better accuracy than traditional Naive Bayes.
LSTM network aids intent classification in QA.
problem Classifying intent in question-answering.
method Used LSTM architecture for intent classification.
result Effective and efficient intent classification achieved.
Solves regression problems with CP by converting to classification.
problem Challenges in CP for heteroscedastic, multimodal, or skewed regression outputs.
method Converts regression to classification, uses CP for classification to obtain CP sets for regression.
result Simple approach yields good results on practical problems.
Paper proposes a new efficient transport-based dissimilarity measure for time series classification.
problem Classifying time series with warping distortions.
method Defining a problem statement, proposing an Optimal Transport-based dissimilarity measure.
result The proposed method can solve the time series classification problem with reduced computational cost.
Paper presents Label Mapping method to solve large-scale multi-class classification problems.
problem Large-scale multi-class classification problems in deep neural networks.
method Label Mapping (LM) method to decompose the problem into smaller sub-problems.
result LM significantly outperforms standard methods in terms of accuracy and model complexity.
Extends binary data classification for hierarchical data.
problem Efficiently classify data with hierarchical class labels.
method Extends a simple binary data classification approach to handle hierarchical relationships.
result Shows computational and accuracy advantages in certain settings.
Non-negative constraints improve neural network defenses.
problem Effective defenses against adversarial attacks in neural networks.
method Non-negative weight constraints applied to binary and non-binary classification problems.
result Non-negative constraints can improve resistance to adversarial attacks, especially in binary classification with asymmetric costs.
New method visualizes decision boundaries of classification models.
problem Difficulty in understanding how classification models interpret data.
method Hybrid supervised-unsupervised technique for visualizing decision boundaries.
result Provides interpretable maps for qualitative and quantitative analysis.
A new classification method using hypothesis testing.
problem Statistical significance in classification problems.
method Formulate classification as a two-sample testing problem; calculate distances and perform tests.
result Outperforms state-of-the-art classifiers and controls false discovery rate.
Paper defines predictive multiplicity and measures its severity in classification problems.
problem Challenges in machine learning due to competing models with conflicting predictions.
method Formal measures and integer programming tools for linear classification problems.
result Real-world datasets may admit competing models with wildly conflicting predictions.
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.
ICE algorithm solves exact 0-1 loss linear classification problem efficiently.
problem Exact solution to the 0-1 loss linear classification problem for non-linearly separable data.
method Incremental cell enumeration (ICE) algorithm, leveraging combinatorial and incidence relations.
result First provably optimal algorithm for exact 0-1 loss linear classification problem.
CCCDs tackle class imbalance in classification.
problem Class imbalance in statistical classification.
method Class cover catch digraphs (CCCDs) for graph theoretic solutions.
result CCCD classifiers perform well in class imbalance scenarios.
A new kNN imputation method improves classification performance on datasets with missing data.
problem Missing data in classification problems.
method Class weighted grey distance with MI weighting for kNN imputation.
result Improved classification performance compared to existing methods.
A new R package for ordinal classification and preprocessing.
problem Lack of proper methods for ordinal data in machine learning.
method Developed an R package named ocapis in Scala.
result Improves classification and preprocessing of ordinal data.
A novel feature selection method for SVM improves model accuracy and interpretability.
problem Feature selection in nonlinear SVM classification problems.
method Embedded min-max optimization problem, leveraging duality theory.
result Improves model accuracy and interpretability on benchmark data sets.
A new method for compressive classification using bridge regression.
problem Efficient pattern classification with compact representation.
method Proposed a deterministic bridge regression solution for compressive classification.
result Validation of the proposed solution through numerical studies on simulated and real-world data.
Simple heuristics can outperform sophisticated methods in high-dimensional pattern recognition.
problem Quantifying the difficulty of high-dimensional pattern recognition problems.
method Classification benchmarks based on simple random projection heuristics.
result Optimal classification curves asymptotes indicate no structural advantage over simple heuristics.
HexaGAN tackles real-world classification issues with missing data, class imbalance, and missing labels.
problem Missing data, class imbalance, and missing labels in real-world data.
method Generative adversarial network framework with six components and novel loss functions.
result Up to 5% improvement in classification performance compared to state-of-the-art methods.
New approach improves classification guarantees by focusing on direction rather than regression risk.
problem Improving classification guarantees in binary classification problems.
method Establishing a geometric distinction between classification and regression, leveraging scale invariance.
result Improved guarantees for classification risk compared to regression risk.
ADMM-Softmax improves classification accuracy for multiclass problems.
problem Multinomial logistic regression for classification tasks with many examples and features.
method Alternating direction method of multipliers (ADMM) for decoupling and solving the problem into efficient steps.
result ADMM-Softmax leads to improved generalization compared to other methods on two image classification problems.
Enhances classification performance with small, additive perturbations.
problem Improving classification performance using small, additive perturbations.
method Proposes a perturbation generation network (PGN) based on adversarial learning to enhance classifier performance.
result Demonstrates that PGN can enhance overall classification performance without altering the target classifier network.
We study realizations of Lie algebras by vector fields. A correspondence between classification of transitive local realizations and classification of subalgebras is generalized to the case of regular local realizations. A reasonable classification problem for general realizations is rigorously formulated and an algori…
Extends linear classification framework to nonlinear SVM-based ranking problems.
problem Maximizing performance on relevant samples in ranking problems.
method Dualization, kernel addition, componentwise dual ascent method.
result General framework for nonlinear classifiers in ranking problems.
New method corrects skewed confidence for PbN classification.
problem Weakly supervised binary classification with biased negative data.
method Corrects skewed confidence in negative data to improve classifier.
result Reduces distortion in posterior probability for PbN classification.
Regression or classification? This is perhaps the most basic question faced when tackling a new supervised learning problem. We present an Evolutionary Deep Learning (EDL) algorithm that automatically solves this by identifying the question type with high accuracy, along with a proposed deep architecture. Typically, a …
Machine learning reveals hidden features in knot classification.
problem Classifying the topology of closed curves.
method Investigating shortcut methods used by ML for knot classification.
result Developed a dataset and code to remove non-topological features.
This paper surveys measures of classification complexity.
problem Estimating the difficulty of separating data points into classes.
method Analysis of descriptors from training datasets.
result Characterization of classification problem complexity.
Paper proposes a new method for brain disease classification using connectome data.
problem Challenges in classifying brain diseases due to small sample size and high dimensionality.
method Simultaneous approximate diagonalization of adjacency matrices to compute stable eigenstructures.
result The method outperforms simple baselines and state-of-the-art approaches for Alzheimer's disease detection.