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

11 results for “correlation-aware”

CAKD: A Correlation-Aware Knowledge Distillation Framework Based on Decoupling Kullback-Leibler Divergencecs.LG

CAKD framework optimizes knowledge transfer by focusing on influential components of distillation.

problem Balancing and optimizing knowledge transfer in distillation models.

method Decouple KL divergence into BCD, SCD, and WCD; prioritize influential components.

result CAKD framework consistently outperforms baseline across diverse models and datasets.

knowledge distillation correlation-aware Kullback-Leibler divergence binary classification strong correlation

2024-10-17abs ↗pdf ↗

Correlation-aware Unsupervised Change-point Detection via Graph Neural Networkscs.LG

Proposes a model to detect changes in multivariate time series data.

problem Detect abrupt changes in multivariate time series data considering dependencies and correlations.

method Integrates graph neural networks into an encoder-decoder framework to model correlation structures and dynamics.

result Advantageous performance on CPD tasks over strong baselines, classifying changes as correlation or independent.

Multivariate Time Series Change-point Detection Graph Neural Networks Correlation Structures Dynamic Modeling

2020-04-24abs ↗pdf ↗

Collaborative Compressors in Distributed Mean Estimation with Limited Communication Budgetstat.ML

New compression schemes save communication in distributed mean estimation.

problem Efficiently compressing vectors for mean estimation in a limited communication setting.

method Collaborative compression schemes that exploit vector similarities without requiring known correlations.

result Analysis shows varying error types with vector similarity.

distributed mean estimation compression schemes vector similarity communication efficiency graceful degradation

2026-01-26abs ↗pdf ↗

Correlation-aware Deep Generative Model for Unsupervised Anomaly Detectioncs.LG

CADGMM detects anomalies by capturing complex correlations in data.

problem Detecting anomalies in complex, unstructured data.

method CADGMM uses a graph structure to encode correlations, then a dual-encoder to learn low-dimensional latent space, followed by a Gaussian Mixture Model for anomaly detection.

result CADGMM effectively detects anomalies in real-world datasets.

anomaly detection unsupervised learning deep generative models graph structure Gaussian Mixture Model

2020-02-18abs ↗pdf ↗

Correlation-Aware Feature Attribution Based Explainable AIcs.LG

ExCIR provides efficient, consistent, and scalable explainability for complex models.

problem Complex models lack transparency and require efficient, stable, and scalable explainability methods.

method ExCIR uses correlation-aware feature attribution with robust centering and groupwise aggregation.

result ExCIR delivers trustworthy agreement with global baselines and full model rankings, reduces runtime, and scales to large datasets.

explainable AI feature attribution correlation robust centering groupwise aggregation

2025-11-20abs ↗pdf ↗

Integrating Feature Correlation in Differential Privacy with Applications in DP-ERMcs.LG

Paper relaxes differential privacy for correlated features, improving privacy-utility trade-off.

problem Standard differential privacy ignores feature correlation, leading to suboptimal privacy-utility balance.

method Introduces CorrDP framework that accounts for feature correlation, using total variation distance for quantification.

result CorrDP algorithms outperform standard DP in synthetic and real-world datasets with insensitive features.

differential privacy feature correlation empirical risk minimization total variation distance privacy-utility trade-off

2026-05-05abs ↗pdf ↗

Enhancing Multivariate Time Series Forecasting with Mutual Information-driven Cross-Variable and Temporal Modelingcs.LG

New framework improves multivariate time series forecasting by minimizing redundant information.

problem Improving multivariate time series forecasting with deep learning techniques.

method Cross-variable Decorrelation Aware feature Modeling (CDAM) and Temporal correlation Aware Modeling (TAM) to refine Channel-mixing and exploit temporal correlations.

result Significantly surpasses existing models in comprehensive tests.

multivariate time series forecasting deep learning channel-mixing cross-variable decorrelation temporal correlation

2024-03-01abs ↗pdf ↗

Stochastic Path Planning in Correlated Obstacle Fieldsstat.ML

A framework for navigating environments with spatially correlated obstacles and uncertain blockage status.

problem Navigation in environments with spatially correlated obstacles of uncertain blockage status.

method Modeling spatial correlation with Gaussian Random Field, developing Bayesian belief updates, proposing a two-stage learning framework with offline and online phases.

result Consistent performance gains over baselines in environments with adversarial interruptions or clustered natural hazards.

navigation correlated obstacles Bayesian belief updates Monte Carlo distributional reinforcement learning

2025-09-23abs ↗pdf ↗

MoCA: Multi-modal Cross-masked Autoencoder for Digital Health Measurementsstat.ML

MoCA uses a novel autoencoder to analyze multi-modal health data.

problem Challenges in analyzing continuous multi-modal health data from wearable devices.

method Proposes MoCA, a self-supervised learning framework combining transformer and masked autoencoder methods.

result Demonstrates strong performance boosts across reconstruction and classification tasks.

self-supervised learning multi-modal data wearable devices health monitoring transformer architecture

2025-06-02abs ↗pdf ↗

Distributional Correlation--Aware Knowledge Distillation for Stock Trading Volume Predictionq-fin.TR

A new distillation framework predicts stock trading volumes more accurately with less model size.

problem Predicting stock trading volumes using regression models without class correlations.

method Transformed regression model into a probabilistic forecasting model, matching distributions and correlational relationships.

result Framework achieves superior prediction accuracy with significantly smaller model size.

stock trading volume prediction knowledge distillation distributional correlation regression

2022-08-04abs ↗pdf ↗

PortBench: A Correlation-Aware, Full-Pipeline Benchmark for LLM-Driven Portfolio Managementcs.AI

PortBench benchmarks LLMs for PM, revealing their weaknesses in diversification and robustness.

problem Lack of benchmarks for LLM-driven portfolio management, especially in diversification and robustness.

method Developed a comprehensive benchmark with a static QA dataset and a dynamic allocation pipeline, introducing metrics to evaluate correlation and robustness.

result 90% of LLMs fail to outperform a basic equal-weight allocation, highlighting their limitations in diversification and robustness.

portfolio management large language models correlation robustness stress testing

2026-05-27abs ↗pdf ↗