Presents first online L2D algorithm for multiclass classification with bandit feedback and varying experts, achieving O((n+n_e)T^{2/3}) regret generally and O((n+n_e)√T) under low noise.
hub
Machine learning: Trends, perspectives, and prospects
7 Pith papers cite this work, alongside 8,110 external citations. Polarity classification is still indexing.
7
Pith papers citing it
8,110
external citations · Crossref
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Empirical audit of LAION-2B-en and LAION-2B-multi finds overrepresentation of young adults, White people, and males plus stereotypical emotion associations across two attribute classifiers.
High magnetic fields directly enhance the amplitude and correlation length of stripe order in a cuprate superconductor far above the vortex melting transition, indicating a coupling mechanism independent of superconductivity suppression.
Neural networks represent densities in a variational extended Thomas-Fermi model, yielding binding energies within 0.5% of prior ETF results and reproducing nuclear pasta phases.
A survey and benchmark of ~60 PSD algorithms on two radiation datasets finds deep learning models (MLPs and hybrids) often outperform traditional statistical methods, with an open-source Python/MATLAB toolbox and datasets released.
Proposes the EL-MIATTs framework for ML predictive modeling by assuming the true target does not exist and defining democratic supervision via multiple inaccurate true targets.
SONARR now uses generic .NET-type logic instead of Boolean-only facts and supports multi-compute to improve performance on network attack analysis and digital-twin modeling.
citing papers explorer
-
Online Learning-to-Defer with Varying Experts
Presents first online L2D algorithm for multiclass classification with bandit feedback and varying experts, achieving O((n+n_e)T^{2/3}) regret generally and O((n+n_e)√T) under low noise.
-
Unmasking LAION-5B: Age, Gender, Race, and Emotion Biases in Large-Scale Image Datasets
Empirical audit of LAION-2B-en and LAION-2B-multi finds overrepresentation of young adults, White people, and males plus stereotypical emotion associations across two attribute classifiers.
-
Direct High-Magnetic-Field Coupling to Stripe Order in a Cuprate Superconductor
High magnetic fields directly enhance the amplitude and correlation length of stripe order in a cuprate superconductor far above the vortex melting transition, indicating a coupling mechanism independent of superconductivity suppression.
-
Neural-Network-Based Variational Method in Nuclear Density Functional Theory: Application to the Extended Thomas-Fermi Model
Neural networks represent densities in a variational extended Thomas-Fermi model, yielding binding energies within 0.5% of prior ETF results and reproducing nuclear pasta phases.
-
Pulse Shape Discrimination Algorithms: Survey and Benchmark
A survey and benchmark of ~60 PSD algorithms on two radiation datasets finds deep learning models (MLPs and hybrids) often outperform traditional statistical methods, with an open-source Python/MATLAB toolbox and datasets released.
-
Negative Ontology of True Target for Machine Learning: Towards Evaluation and Learning under Democratic Supervision
Proposes the EL-MIATTs framework for ML predictive modeling by assuming the true target does not exist and defining democratic supervision via multiple inaccurate true targets.
-
Core Logic and Algorithmic Performance Enhancements for a System Vulnerability Analysis Technique for Complex Mission Critical Systems Implementation
SONARR now uses generic .NET-type logic instead of Boolean-only facts and supports multi-compute to improve performance on network attack analysis and digital-twin modeling.