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 “model-centric”

Model-Centric and Data-Centric Aspects of Active Learning for Deep Neural Networkscs.LG

Unified study of active learning for deep neural networks.

problem Improving performance of deep neural networks through active learning.

method Investigation of incremental and cumulative training modes, model configurations, query strategies, and pseudo-labels.

result Proposed more efficient querying procedures and insights into active learning behavior.

active learning deep neural networks model-centric data-centric incremental training

2020-09-22abs ↗pdf ↗

Evaluation of importance estimators in deep learning classifiers for Computed Tomographycs.CV

Study evaluates different saliency maps for CT image classification.

problem Understanding how deep learning models make decisions in medical imaging.

method Compared several saliency maps using three evaluation metrics.

result Two versions of SmoothGrad performed best across all metrics.

deep learning computed tomography saliency maps interpretability medical imaging

2022-09-30abs ↗pdf ↗

Model-centric Data Manifold: the Data Through the Eyes of the Modelcs.LG

Deep neural networks reveal a low-dimensional manifold structure in data.

problem Understanding the structure of data for better model performance.

method Model-centric analysis of the data manifold using the local data matrix and Fisher information matrix.

result The dataset lies on a data leaf with a dimension bounded by the number of labels.

deep learning neural networks data manifold Fisher information classification

2021-04-26abs ↗pdf ↗

Active Learning with Combinatorial Coveragecs.LG

New active learning method uses combinatorial coverage to improve data transfer and reduce bias.

problem Inability to transfer sampled data to new models and sampling bias issues.

method Data-centric active learning methods utilizing combinatorial coverage.

result Sampling data with coverage leads to better data transfer and competitive sampling bias.

active learning machine learning data transfer sampling bias combinatorial coverage

2023-02-28abs ↗pdf ↗

FinRL-X: An AI-Native Modular Infrastructure for Quantitative Tradingq-fin.TR

FinRL-X unifies trading components for AI and rule-based strategies.

problem Inconsistent between research and live deployment in trading platforms.

method Modular architecture integrating data processing, strategy construction, backtesting, and execution.

result Unified protocol supports AI and rule-based trading components without altering execution.

quantitative trading AI-native reinforcement learning broker execution modular architecture

2026-03-22abs ↗pdf ↗

Data Selection for ERMscs.LG

The paper explores how to select data points for optimal learning performance.

problem Optimizing data selection for empirical risk minimizers.

method Fixing a learning rule and focusing on optimizing the training data selection.

result Achieving performance comparable to training on the entire population with a small subset of data points.

data selection empirical risk minimizers learning theory optimal algorithms binary classification

2025-04-20abs ↗pdf ↗

In Automation We Trust: Investigating the Role of Uncertainty in Active Learning Systemscs.LG

Study examines how uncertainty visualization affects analyst trust in automated classification systems.

problem The impact of uncertainty on analyst trust in automated classification systems.

method Empirical study evaluating different active learning query policies and visualizations.

result Query policy significantly influences analyst trust in automated classification systems.

active learning classification uncertainty analyst trust image data oracle query policies

2020-04-02abs ↗pdf ↗

Technologies for Trustworthy Machine Learning: A Survey in a Socio-Technical Contextcs.LG

Survey of technologies for trustworthy machine learning systems.

problem Building machine learning systems that are fair, explainable, auditable, and secure.

method Survey of technologies across data and model stages of machine learning.

result Four categories of system properties (fairness, explainability, auditability, safety & security) are essential for trustworthy systems.

trustworthy machine learning fairness explainability auditability safety & security

2020-07-17abs ↗pdf ↗

HyPV-LEAD: Proactive Early-Warning of Cryptocurrency Anomalies through Data-Driven Structural-Temporal Modelingcs.LG

HyPV-LEAD detects cryptocurrency anomalies proactively, improving financial security.

problem Cryptocurrency anomalies like mixing, fraud, and pump-and-dump operations are hard to detect due to class imbalance and temporal volatility.

method HyPV-LEAD integrates lead time into anomaly detection through window-horizon modeling, Peak-Valley sampling, and hyperbolic embedding.

result HyPV-LEAD achieves a PR-AUC of 0.9624 on Bitcoin transaction data, significantly outperforming state-of-the-art methods.

cryptocurrency anomaly detection lead time Peak-Valley hyperbolic embedding

2025-09-03abs ↗pdf ↗

Enabling Synthetic Data adoption in regulated domainscs.LG

DAISYnt evaluates synthetic data quality and privacy in regulated domains.

problem Balancing data quality and privacy in regulated domains.

method Developed a suite of advanced tests (DAISYnt) to evaluate synthetic data quality and privacy.

result DAISYnt sets a de facto standard for synthetic data evaluation in regulated domains.

Synthetic Data Privacy Enhancing Technologies Data-Centric Regulated Domains Credit Bureau Data

2022-04-13abs ↗pdf ↗

Towards Human-Guided, Data-Centric LLM Co-Pilotscs.LG

CliMB-DC combines human guidance and data-centric tools to improve ML for non-technical experts.

problem Lack of data-centric handling in LLM co-pilots for non-technical users.

method Human-guided, data-centric framework combining advanced tools and LLM reasoning.

result Significantly outperforms existing co-pilot baselines for data-centric challenges.

LLM co-pilots data-centric challenges human-guided systems domain expertise data processing

2025-01-17abs ↗pdf ↗