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.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “time-to-result”

Benchmarking Neural Network Training Algorithmscs.LG

This work introduces a new benchmark to compare neural network training algorithms.

problem Lack of reliable benchmarks to compare training algorithms effectively.

method Developed a new benchmark called AlgoPerf: Training Algorithms benchmark.

result Demonstrated the feasibility of the benchmark and set a provisional state-of-the-art.

neural networks training algorithms benchmarks optimizers time-to-result

2023-06-12abs ↗pdf ↗

Accelerating Neural Network Training: An Analysis of the AlgoPerf Competitioncs.LG

AlgoPerf competition evaluates neural network training speed-ups.

problem Improving neural network training speed using better algorithms.

method Compared 18 diverse submissions from 10 teams on multiple workloads.

result Schedule Free AdamW algorithm achieved best results in self-tuning ruleset.

neural networks training algorithms AlgoPerf competition hyperparameter-free non-diagonal preconditioning

2025-02-20abs ↗pdf ↗