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.

168,932 papers · 148 categories

Trend · papers per month

count% of corpus
0.3%0.5%0.8%0.1% · Apr 201919922001200920172026
2 results for “collage-CNN”
Collage Inference: Achieving low tail latency during distributed image classification using coded redundancy modelscs.DC

Collage-CNN reduces cloud inference latency by 1.47X with 9X reduced latency variation.

problem Reducing latency variance in cloud machine learning inference.
method Proposes a novel Collage-CNN model that combines multiple images for classification, providing redundancy and cost efficiency.
result Significant reduction in 99th percentile tail latency and variation in inference latency.
machine learninginference latencycloud computingredundancycollage-CNN
2019-06-05abs ↗pdf ↗