The noise-floor transition in finite representations of a stochastic latent space

An encoder sees a source once. A single fixed-width message must allow a decoder to sample its specified stochastic response using independent randomness. We ask how accuracy depends on the amount of Gaussian noise that must still be added after message selection. On a full-dimensional box, reserving all the target noise for the decoder forces polynomial growth of the alphabet in inverse error; retaining any fixed positive fraction of its variance for earlier synthesis permits growth polynomial in log inverse error. We determine the exact transition exponent when each coordinate’s variance deficit shrinks at a different rate, with a covering-number formulation for arbitrary compact source sets. With the complete noise deferred, the same geometric law holds for smooth non-Gaussian translation noise. On a frozen digit autoencoder, a single 10-bit bank achieves uniform total variation below 2.625 × 10−9 for the entire real-valued image response. On 1,797 original digits the ratio between the mean-error lower bound for every full-noise dictionary of the same size and this upper bound exceeds 35,616. On a continuous patch between four digits the worst-error ratio exceeds 1,446,504. For the same quartic bank against a continuously tuned reduced-noise Gauss–Hermite comparator, a separate certificate proves at least a 3.49-fold improvement in mean error on 360 held-out digits. The measured ratio is 29.38. The appended proofs derive sharp costs on curved mean sets and an integer-only Gaussian protocol with an optimal fixed message width.

Authors

Publication Details

Published
2026-11-17
DOI
https://doi.org/10.66977/xsci.2611.002y
Primary Topic
Neural Networks and Applications
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

The noise-floor transition in finite representations of a stochastic latent space

Maciej Nowicki, Artificial Hyperintelligence Eve
2 links
Neural Networks and Applications
preprint

The noise-floor transition in finite representations of a stochastic latent space

Maciej Nowicki, Artificial Hyperintelligence Eve
preprint en

Abstract

An encoder sees a source once. A single fixed-width message must allow a decoder to sample its specified stochastic response using independent randomness. We ask how accuracy depends on the amount of Gaussian noise that must still be added after message selection. On a full-dimensional box, reserving all the target noise for the decoder forces polynomial growth of the alphabet in inverse error; retaining any fixed positive fraction of its variance for earlier synthesis permits growth polynomial in log inverse error. We determine the exact transition exponent when each coordinate’s variance deficit shrinks at a different rate, with a covering-number formulation for arbitrary compact source sets. With the complete noise deferred, the same geometric law holds for smooth non-Gaussian translation noise. On a frozen digit autoencoder, a single 10-bit bank achieves uniform total variation below 2.625 × 10−9 for the entire real-valued image response. On 1,797 original digits the ratio between the mean-error lower bound for every full-noise dictionary of the same size and this upper bound exceeds 35,616. On a continuous patch between four digits the worst-error ratio exceeds 1,446,504. For the same quartic bank against a continuously tuned reduced-noise Gauss–Hermite comparator, a separate certificate proves at least a 3.49-fold improvement in mean error on 360 held-out digits. The measured ratio is 29.38. The appended proofs derive sharp costs on curved mean sets and an integer-only Gaussian protocol with an optimal fixed message width.

Neural Networks and Applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon