AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Near-Optimal Smoothing of Structured Conditional Probability Matrices

Moein Falahatgar, Mesrob I Ohannessian, Alon Orlitsky

NeurIPS 2016 · Learning theory and algorithms › Matrix and tensor methods · approach: Structured low-rank learning · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add low-rank structure with absolute-discounting smoothing instead of Kneser-Neybigram model · tartuffecross-entropy: 5.7555 -> 5.6923Improved
add low-rank structure with absolute-discounting smoothing instead of Kneser-Neybigram model · genesiscross-entropy: 5.7341 -> 5.6673Improved
add low-rank structure with absolute-discounting smoothing instead of Kneser-Neybigram model · browncross-entropy: 7.7001 -> 7.609Improved
low-rank smoothing instead of Stupid Backoffbigram model · tartuffecross-entropy: 6.0426 -> 5.6923Improved
low-rank smoothing instead of plain absolute discountingbigram model · browncross-entropy: 7.9819 -> 7.609Improved
naive Add-1/2 smoothing then low-rank factorization vs Add-1/2 without structure (ablation)low-rank bigram · synthetic uniform B rowsKL lossHurt
smooth counts inside the low-rank procedure instead of naive smoothing then factorizing (ablation)low-rank bigram · syntheticKL lossImproved
Kneser-Ney on uniform-row synthetic dataKneser-Ney · synthetic uniform B rowsKL lossHurt
low-rank smoothing vs Stupid Backoff at 15k training wordsSmoothed Low Rank · tartuffecross-entropy diff: 0.1 nats/wordImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy