arXiv Machine Learning
Multiclass Linear Perceptrons with Multiplicative Margins
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
3d ago
From Dataset Spectral Geometry to Network Weights: A Geometry-Aware Initialization for Sigmoidal MLPs in Image Classification
arXiv:2606.28444v2 Announce Type: replace-cross Abstract: Classical universal approximation theorems (UAT) establish the expressive power of sigmoidal multilayer perceptrons, but they do not specify...
arXiv AI
Jul 7
A Unified Algebraic Framework for Classification Performance Evaluation
arXiv:2607. 04028v1 Announce Type: cross Abstract: We propose a unified algebraic framework for classification performance evaluation that encompasses binary, multiclass, multilabel, ordinal, hierarchical, cost-sensitive, and soft-label settings within a single formalism.
arXiv Machine Learning
Jun 2
Sensitivity as a Double-Edged Sword: A Trade-off Between Discriminability and Adversarial Robustness
arXiv:2606. 01746v1 Announce Type: cross Abstract: Modern neural networks are highly susceptible to adversarial perturbations.
arXiv Machine Learning
Jun 5
Robust and sparse support vector machine via hybrid truncated loss for supervised classification
arXiv:2606. 05814v1 Announce Type: new Abstract: The support vector machine (SVM) is a widely used classifier, but choosing an appropriate loss function remains difficult.
arXiv Machine Learning
Jun 9
Similarity-Distance-Magnitude Activations
arXiv:2509. 12760v5 Announce Type: replace Abstract: We introduce the Similarity-Distance-Magnitude (SDM) activation function, a more robust and interpretable formulation of the standard softmax activation function, adding Similarity (i.
arXiv Machine Learning
Jun 8
Twin: Tuning Learning Rate and Weight Decay of Deep Homogeneous Classifiers without Validation
arXiv:2403. 05532v2 Announce Type: replace Abstract: We introduce Tune without Validation (Twin), a simple and effective pipeline for tuning learning rate and weight decay of homogeneous classifiers without validation sets, eliminating the need to hold out data and avoiding the two-step process.