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. Theory for soft-margin classifiers on object manifolds.
problem Classifying object manifolds with variability.
method Mean-field theory of soft-margin classifiers applied to object manifolds.
result Prediction of classification errors and their dependence on regularization.
Gradient descent finds halfspaces with low error for agnostic learning.
problem Agnostic learning of linear halfspaces with convex surrogates.
method Gradient descent on convex surrogates for zero-one loss.
result Gradient descent finds halfspaces with error O(OPT1/2+ε) in poly time and sample complexity. Margin maximization in the hard-margin sense, proposed as feature elimination criterion by the MFE-LO method, is combined here with data radius utilization to further aim to lower generalization error, as several published bounds and bound-related formulations pertaining to lowering misclassification risk (or error) pe…
Enhances SVM interpretability by integrating data priors.
problem Lack of interpretability in black-box models.
method Integrates data-based priors into soft-margin SVM to enhance interpretability.
result Proposes an interpretable SVM optimization model and solves it as a nonlinear quadratic programming problem.
A model classifies music genres from MP3 files using metric learning and feature extraction.
problem Classifying music genres from MP3 files efficiently and accurately.
method Metric learning and feature extraction using MFCC and PCA.
result Promising results in classification accuracy compared to baseline algorithms.
Paper analyzes SVM behavior in high dimensions with exact formulas.
problem Characterizing SVM behavior in high-dimensional data with fixed ratio of features to samples.
method Exact asymptotic formulas derived through heuristic leave-one-out calculations.
result Exact formulas for variability of optimal coefficients, support vectors, objective function value, and misclassification error.
Tropical SVM tackles phylogenomics by classifying multi-locus data.
problem Classifying multi-locus data sets for phylogenetic analysis.
method Proposes tropical support vector machines (SVMs) for phylogenomics, formulated as linear programming problems.
result Developed methods for hard and soft margin tropical SVMs, proving necessary and sufficient conditions for separation.
This work establishes the equivalence between neural networks and support vector machines.
problem Establishing the equivalence between neural networks and support vector machines.
method Proposed a method to establish the equivalence between infinitely wide neural networks trained by soft margin loss and standard soft margin SVMs with NTK trained by subgradient descent.
result The equivalence between NN and SVM is established, enabling practical applications such as non-vacuous generalization bounds and robustness certificates.
Let X be a data matrix of rank ρ, whose rows represent n points in d-dimensional space. The linear support vector machine constructs a hyperplane separator that maximizes the 1-norm soft margin. We develop a new oblivious dimension reduction technique which is precomputed and can be applied to any input matrix X. We pr…
Recently, there has been much interest in finding globally optimal Bayesian network structures. These techniques were developed for generative scores and can not be directly extended to discriminative scores, as desired for classification. In this paper, we propose an exact method for finding network structures maximiz…
The distance metric plays an important role in nearest neighbor (NN) classification. Usually the Euclidean distance metric is assumed or a Mahalanobis distance metric is optimized to improve the NN performance. In this paper, we study the problem of embedding arbitrary metric spaces into a Euclidean space with the goal…
Proposes training objectives for neural networks to produce robust attributions.
problem Training models that produce robust interpretations for their predictions.
method Classic robust optimization models and Integrated Gradients (IG) for axiomatic attribution.
result The proposed objectives give principled generalizations of previous objectives for robust predictions.
New algorithms estimate Q-functions under partial coverage and realizability, improving offline RL guarantees.
problem Offline RL with limited exploration and assumptions about data coverage and Q-function realizability.
method Proposes minimax learning algorithms to estimate soft or vanilla Q-functions with L2-convergence guarantees. result PAC guarantees for offline RL under partial coverage and realizability conditions.
We investigate the relation of two fundamental tools in machine learning and signal processing, that is the support vector machine (SVM) for classification, and the Lasso technique used in regression. We show that the resulting optimization problems are equivalent, in the following sense. Given any instance of an $\ell…
Uniform sampling of modest size is a coreset for regularized loss minimization.
problem Designing efficient algorithms for large data with restricted access.
method Sampling-based algorithms for regularized loss minimization problems.
result Uniform sample of modest size is a coreset for certain regularized loss minimization problems.
New kernel class improves SVM performance.
problem No universal, tractable, scalable kernel set.
method Proposed Tessellated Kernel (TK) class with positive matrices.
result TK kernels outperform other methods in SVM problems.
New sampling technique improves KGC model performance.
problem Ignoring entity neighbors in minibatches affects KGC model training.
method Random-walk based minibatch sampling.
result Proposed method achieves state-of-the-art performance on DB100K.
Framework learns stochastic dynamics from endpoint and intermediate distributions using soft energy constraints.
problem Learning stochastic dynamics from endpoint and intermediate distributional observations.
method Formulates generation as a McKean-Vlasov control problem with soft energy constraints, solving it through FBSDE.
result Model learns coherent stochastic trajectories matching prescribed marginal laws.
Combines neural networks and decision trees for supervised learning.
problem Challenges in optimizing hierarchical parameters and constructing tree structures.
method Probabilistic approach with modified gradient ascent and adaptive tree construction.
result Novel classification and regression technique that combines strengths of neural networks and decision trees.
Unified SVM framework tackles multiclass and multilabel classification.
problem Extending SVM to handle multiclass and multilabel problems.
method Unified framework with class-specific weight vectors and penalizing patterns close to an origin.
result Unified framework achieves competitive performance for multiclass and multilabel classification.