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.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “NATS-Bench”

NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Sizecs.LG

NATS-Bench benchmarks NAS algorithms for architecture topology and size.

problem Incomparable performance of NAS algorithms due to different search spaces and training setups.

method Unified benchmarking platform for architecture topology and size searching.

result Validated benchmark for 15,625 topology and 32,768 size candidates.

NATS-Bench NAS algorithms architecture search topology size

2020-08-28abs ↗pdf ↗

Neural Architecture Search without Trainingcs.LG

Automates neural network design without training, speeding up search by seconds.

problem Time and effort in hand-designing deep neural networks.

method Predict trained accuracy from untrained network state using activation overlap.

result Search for powerful networks in seconds, verified on various benchmarks.

Neural Architecture Search NAS Deep Learning Automated Design Activation Overlap

2020-06-08abs ↗pdf ↗

A Benchmark Study on Calibrationcs.LG

Study explores calibration properties in neural architectures.

problem Calibration issues in deep neural networks despite improved accuracy.

method Leverages Neural Architecture Search (NAS) to evaluate 117,702 neural networks.

result Identifies key architectural designs beneficial for calibration.

neural architecture search calibration properties deep learning model evaluation NAS-Bench

2023-08-23abs ↗pdf ↗

RARTS: An Efficient First-Order Relaxed Architecture Search Methodcs.LG

RARTS improves neural architecture search efficiency and accuracy.

problem Efficiency and accuracy issues in first-order DARTS.

method Formulates a relaxed architecture search (RARTS) method that uses whole dataset splitting.

result RARTS outperforms DARTS and its variants in accuracy and efficiency.

neural architecture search first-order optimization data-driven design bilevel optimization network pruning

2020-08-10abs ↗pdf ↗