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.

168,742 papers · 148 categories

Trend · papers per month

count% of corpus
0111 · Feb 202019922001200920172026
2 results for “bitlength”
BitPruning: Learning Bitlengths for Aggressive and Accurate Quantizationcs.LG

BitPruning learns optimal bitlengths for neural networks to balance accuracy and efficiency.

problem Finding the minimum bitlength for neural network accuracy.
method A training method that penalizes large bitlengths and minimizes other quantifiable criteria.
result The method learns efficient representations while maintaining accuracy, reducing bitlengths by 3.76 bits on average per layer.
quantizationneural networksbitlengthaccuracyefficiency
2020-02-08abs ↗pdf ↗
WL meet VCcs.LG

The paper connects GNNs to VC dimension theory to study their generalization performance.

problem Understanding GNNs' ability to make meaningful predictions beyond the training set.
method Using Vapnik-Chervonenkis (VC) dimension theory in two settings: no upper bound on graph order and known upper bound.
result Tight connections between GNNs' bitlength, number of colors, and VC dimension in different settings.
graph neural networksVC dimensiongeneralizationgraph isomorphism1-WL algorithm
2023-01-26abs ↗pdf ↗