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.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

1 result for “doubly-normalized”

Attention that does not Explain Awaycs.LG

Improved Transformer performance by addressing 'explaining away' effect.

problem Transformer's self-attention mechanism can explain away important input features.

method Proposed a doubly-normalized attention scheme to avoid 'explaining away' effect.

result Improved performance on benchmarks with the new attention scheme.

Transformer self-attention explaining away doubly-normalized performance improvement

2020-09-29abs ↗pdf ↗