Checked fact 320330 Oct 2026Research

Each guess is checked against a random threshold using the ratio of the target's and the approximation model's probabilities, and guesses that pass are kept in order.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

r1 ~ U(0, 1), ..., rγ ~ U(0, 1); n <- min({i - 1 : 1 <= i <= γ, ri > pi(x)/qi(x)} U {γ})

What the source said when we opened it, on 30 Oct 2026.

The source

Fast Inference from Transformers via Speculative Decoding
arXiv (Leviathan, Kalman, Matias) · 2022-11-30

Open the source archived copy

Checked

Checked by the notis newsroom on 30 Oct 2026, against the source above.

In the story

How speculative decoding lets a small model draft and a large one check 30 Oct 2026

Cite this fact

Short permanent address

In a sentence

“Each guess is checked against a random threshold using the ratio of the target's and the approximation model's probabilities, and guesses that pass are kept in order.” ai notis, checked 30 Oct 2026. Source: Fast Inference from Transformers via Speculative Decoding (arXiv (Leviathan, Kalman, Matias)). https://ainotis.com/c/3203

As a reference (APA style)

ai notis. (2026, October 30). Each guess is checked against a random threshold using the ratio of the target's and the approximation model's probabilities, and guesses that pass are kept in order [Checked claim 3203]. ai notis. https://ainotis.com/c/3203

Anyone may quote this address. It does not change; if we correct the story, this page says so.