On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

8 results for “anchor-based”

LargeMvC-Net: Anchor-based Deep Unfolding Network for Large-scale Multi-view Clusteringcs.CV

LargeMvC-Net improves scalability of multi-view clustering.

problem Scalability issues in multi-view clustering.

method Deep unfolding of multi-view clustering into a network architecture with three modules.

result LargeMvC-Net consistently outperforms state-of-the-art methods in scalability and effectiveness.

multi-view clustering anchor-based deep learning unsupervised reconstruction loss

2025-07-28abs ↗pdf ↗

Consistency of Anchor-based Spectral Clusteringstat.ML

New method shows spectral clustering is consistent with theoretical guarantees.

problem Lack of theoretical support for anchor-based spectral clustering.

method Defined and analyzed a specific anchor-based algorithm.

result Theoretical consistency of the method in asymptotic settings.

spectral clustering anchor-based consistency asymptotic analysis clustering algorithms

2020-06-24abs ↗pdf ↗

The Devil Is in Gradient Entanglement: Energy-Aware Gradient Coordinator for Robust Generalized Category Discoverycs.LG

EAGC boosts GCD by regulating gradient entanglement, improving known and novel category separability.

problem Gradient entanglement distorts supervised gradients and overlaps known and novel class representations.

method EAGC uses AGA and EEP to align and project gradients, reducing entanglement and overlap.

result EAGC consistently boosts GCD performance, setting new state-of-the-art results.

Generalized Category Discovery Gradient Entanglement Energy-Aware Gradient Coordinator Anchor-based Gradient Alignment Energy-aware Elastic Projection

2026-03-25abs ↗pdf ↗

Anchor-Based Heteroscedastic Noise for Preferential Bayesian Optimizationcs.LG

A new noise model for preferential Bayesian optimization using user anchors.

problem Inadequate assumption of homoscedastic noise in human-in-the-loop settings.

method Proposes a heteroscedastic noise model with anchors and a KDE uncertainty map.

result Risk-adjusted performance improvement and clarified anchor placement effects.

Bayesian optimization heteroscedastic noise anchors user preferences kernel density estimation

2024-05-23abs ↗pdf ↗

Sparse mixed linear modeling with anchor-based guidance for high-entropy alloy discoverycond-mat.mtrl-sci

Study improves materials discovery for high-entropy alloys using sparse linear models.

problem Inefficient materials discovery due to combinatorial explosion in alloy compositions.

method Sparse mixed linear modeling with anchor-based guidance for feature selection and prediction.

result Developed a method that balances predictive performance and interpretability for materials discovery.

materials science high-entropy alloys machine learning sparse modeling feature selection

2025-04-29abs ↗pdf ↗

Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddingscs.LG

IDGL learns better graph structure and embeddings iteratively.

problem Improving graph neural network node embeddings and graph structure.

method Iterative Deep Graph Learning framework that dynamically stops when graph structure optimizes for downstream tasks.

result IDGL consistently outperforms state-of-the-art baselines on nine benchmarks.

Graph Neural Networks Graph Learning Node Embeddings Iterative Learning Graph Structure Optimization

2020-06-21abs ↗pdf ↗

AutoAnchor: Stable Diffusion Unlearning Using Cross-Attention as a Manifold Surrogatecs.LG

AutoAnchor uses cross-attention to improve text-to-image model unlearning.

problem Mitigating harmful or copyrighted content in text-to-image models.

method Two-stage framework that automatically synthesizes manifold-proximal anchors using cross-attention consistency loss.

result Effective robust and unbiased unlearning across various baselines.

Diffusion unlearning Stable Diffusion Cross-attention Manifold optimization Text-to-image models

2026-07-09abs ↗pdf ↗

Forecasting Medium-Horizon Alzheimer's Disease Progression: Residual Gap-Aware Transformers for 24-Month CDR-SB Change from ADNI Clinical and Biomarker Historiescs.LG

Transformers improve Alzheimer's disease progression prediction by accounting for irregular biomarker histories.

problem Difficult prediction of medium-horizon Alzheimer's disease progression due to tied clinical scores and irregular biomarker observations.

method Developed a residual gap-aware transformer that combines statistical reference with transformer-based residual learning.

result The proposed model reduces mean error and improves prediction-observation correlation compared to baseline models.

Alzheimer's disease progression prediction residual gap-aware transformers Clinical Dementia Rating biomarker histories

2026-05-04abs ↗pdf ↗