Research
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
0.3%0.5%0.8%0.1% · May 201919922001200920182026
1 result for “YOPO”
You Only Propagate Once: Accelerating Adversarial Training via Maximal Principlestat.ML

YOPO reduces adversarial training time by one forward/backward pass per group of updates.

problem Adversarial training's high computational cost limits deep learning's robustness.
method YOPO uses the Pontryagin's Maximal Principle to limit propagation to the first layer.
result YOPO achieves comparable defense accuracy with significantly less computational time.
adversarial trainingYOPOmaximal principlerobustnesscomputational cost
2019-05-02abs ↗pdf ↗