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.

168,786 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “data-loaders”

Torchmeta: A Meta-Learning library for PyTorchcs.LG

Torchmeta simplifies meta-learning evaluation across multiple datasets.

problem Inconsistent evaluation of meta-learning algorithms across different datasets.

method Introduces a library that provides data-loaders for standard benchmarks and simplifies model compatibility.

result Seamless and consistent evaluation of meta-learning algorithms on multiple datasets.

meta-learning PyTorch data-loaders few-shot classification regression

2019-09-14abs ↗pdf ↗

TUDataset: A collection of benchmark datasets for learning with graphscs.LG

TUDataset provides benchmark datasets for graph learning.

problem Lack of meaningful benchmark datasets and standardized evaluation procedures for graph learning.

method Collection and standardization of 120 graph datasets from various applications.

result Standardized evaluation procedures and baseline experiments provided.

benchmark datasets graph learning graph neural networks graph classification graph regression

2020-07-16abs ↗pdf ↗

Accelerating Data Loading in Deep Neural Network Trainingcs.LG

Accelerates data loading in deep neural network training by 30x.

problem Data loading is a bottleneck in deep neural network training.

method Locality-aware data loading method using software caches.

result More than 30x speedup in data loading.

data loading deep learning distributed training performance optimization software caching

2019-10-02abs ↗pdf ↗

Open Graph Benchmark: Datasets for Machine Learning on Graphscs.LG

OGB provides diverse graph datasets for robust ML research.

problem Challenges in scalable and robust graph machine learning.

method Unified evaluation protocol, diverse datasets, and automated pipeline.

result Significant scalability and generalization challenges identified.

graph machine learning benchmark datasets scalability robustness generalization

2020-05-02abs ↗pdf ↗

Quantum analog-encoding for correlated Gaussian vectors and their exponentiation with application to rough volatilityquant-ph

Quantum algorithms simulate and exponentiate correlated Gaussian vectors for financial modeling.

problem Efficiently simulate and exponentiate correlated Gaussian vectors for financial applications.

method Proposes quantum algorithms for preparing and exponentiating normalised correlated Gaussian random vectors.

result Achieves subcubic complexity in

N

for quantum state preparation, providing a quantum advantage over classical methods.

quantum computing Gaussian vectors exponentiation financial modeling rough volatility

2026-04-24abs ↗pdf ↗