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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “cutoff-scale”

Blind Adversarial Training: Balance Accuracy and Robustnesscs.LG

This paper proposes BAT to balance accuracy and robustness in adversarial training.

problem Balancing accuracy and robustness in adversarial training models.

method Blind adversarial training (BAT) uses a cutoff-scale strategy to adaptively estimate a nonuniform budget for AEs.

result BAT improves the overall robustness of adversarial training models.

adversarial training robustness accuracy cutoff-scale nonuniform budget

2020-04-10abs ↗pdf ↗

Blind Adversarial Pruning: Balance Accuracy, Efficiency and Robustnesscs.LG

This paper introduces blind adversarial pruning to balance accuracy, efficiency, and robustness in neural networks.

problem Balancing accuracy, efficiency, and robustness in neural networks with limited resources.

method Adversarial pruning with a cutoff-scale strategy to dynamically adjust the strength of adversarial examples.

result Blind adversarial pruning improves the overall AER of pruned models compared to adversarial pruning.

neural networks robustness compression adversarial training gradual pruning

2020-04-10abs ↗pdf ↗