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.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “DeepLearning”

Bridging OOD Detection and Generalization: A Graph-Theoretic Viewcs.LG

Unified framework for OOD detection and generalization using graph theory.

problem Challenges in out-of-distribution (OOD) generalization and detection in real-world machine learning models.

method Graph-theoretic framework to jointly tackle OOD generalization and detection.

result Empirical validation of theoretical underpinnings with competitive performance.

graph theory OOD detection generalization machine learning covariate shift

2024-09-26abs ↗pdf ↗

Ascertaining price formation in cryptocurrency markets with DeepLearningq-fin.GN

Deep learning predicts cryptocurrency price movements with 78% accuracy.

problem Predicting price formation in cryptocurrency markets with high volatility and illiquidity.

method Applied deep learning to predict mid-price changes on live tick-level cryptocurrency data.

result Achieved 78% accuracy in predicting mid-price movement of Bitcoin vs USD.

cryptocurrency deep learning price prediction volatility high-frequency trading

2020-02-09abs ↗pdf ↗

Your Classifier Can Be Secretly a Likelihood-Based OOD Detectorcs.LG

INK scores improve OOD detection for classifiers.

problem Detecting out-of-distribution inputs for classification models.

method INK scores operate on constrained latent embeddings modeled as a mixture of hyperspherical embeddings, optimizing in modern neural networks.

result INK establishes a new state-of-the-art in OOD detection.

OOD detection classification models likelihood-based discriminative classifiers neural networks

2024-08-09abs ↗pdf ↗

How Does Unlabeled Data Provably Help Out-of-Distribution Detection?cs.LG

SAL framework uses unlabeled data to improve OOD detection.

problem Lack of clean OOD samples makes OOD detection challenging.

method SAL framework separates candidate outliers and trains an OOD classifier.

result SAL achieves state-of-the-art performance on benchmarks.

out-of-distribution detection unlabeled data machine learning theoretical guarantees empirical effectiveness

2024-02-05abs ↗pdf ↗

Analyzing Neuroimaging Data Through Recurrent Deep Learning Modelscs.LG

DeepLight uses LSTM to decode fMRI data, improving cognitive state analysis.

problem Challenges in analyzing neuroimaging data due to high dimensionality, low sample size, and complex dependency structure.

method Introduces DeepLight framework using LSTM-based DL models to process fMRI data sequences, adapts LRP for interpretability.

result DeepLight outperforms conventional fMRI analysis methods in decoding cognitive states and identifying brain regions.

DeepLearning fMRI Neuroimaging Recurrent Neural Networks LongShortTermMemory

2018-10-23abs ↗pdf ↗