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.

168,982 papers · 148 categories

Trend · papers per month

count% of corpus
0111 · Mar 201919922001200920172026
1 result for “alpha-blending”
Learning low-precision neural networks without Straight-Through Estimator(STE)cs.LG

A new method quantizes neural networks to low-precision without STE, improving accuracy.

problem Quantization of neural networks to low-precision without a complete theoretical understanding.
method Alpha-blending (AB) using stochastic gradient descent (SGD) to quantize weights and gradually increase the coefficient αα.
result Improves top-1 accuracy by 0.9% on 1-bit BinaryNet, 0.82% on 8-bit MobileNet v1, and 2.93% on 4-bit ResNet_50 v1/2 compared to STE.
neural networksquantizationlow-precisionstochastic gradient descentalpha-blending
2019-03-04abs ↗pdf ↗