Skip to Content
ゼロから作るDeep Learning ❻ ―LLM編
book

ゼロから作るDeep Learning ❻ ―LLM編

by 斎藤 康毅
June 2026
Intermediate
384 pages
4h 17m
Japanese
O'Reilly Japan, Inc.
Content preview from ゼロから作るDeep Learning ❻ ―LLM編

付録DAdamのバイアス補正

「6.1 AdamWの仕組み」でAdamのバイアス補正について簡単に触れました。ここでは「なぜ(1-\beta^t)で割るとバイアス補正できるのか」、その理由を数式と具体例で詳しく見ていきます。

まず、Adamの更新式を再掲します。

\begin{aligned} m_t &= \beta_1 m_{t-1} + (1-\beta_1) g_t &\qquad(1)\\ v_t &= \beta_2 v_{t-1} + (1-\beta_2) g_t^2 &\qquad(2)\\ \hat{m}_t &= \frac{m_t}{1-\beta_1^t}&\qquad(3)\\ \hat{v}_t &= \frac{v_t}{1-\beta_2^t} &\qquad(4)\\ \theta_{t+1} &= \theta_{t} - \alpha \frac{\hat{m}_t}{\sqrt{\hat{v}_t} + \varepsilon}&\qquad(5) \end{aligned}

ここでは、第3式と第4式のバイアス補正に注目します。以降、説明を簡単にするため\beta_1を単に\betaと表記し、1次モーメントm_tに焦点を当てます(2次モーメントも同様の理屈です)。

問題:初期値ゼロによる偏り

Adamでは、1次モーメントと2次モーメントを、で初期化します。この初期値ゼロが原因で、学習の初期段階では移動平均が真の期待値よりも小さく見積もられてしまいます。 ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

AirBnbBlueOriginElectronic ArtsHomeDepotNasdaqRakutenTata Consultancy Services

QuotationMarkO’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.
Julian F.
Head of Cybersecurity
QuotationMarkI wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.
Addison B.
Field Engineer
QuotationMarkI’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.
Amir M.
Data Platform Tech Lead
QuotationMarkI'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
Mark W.
Embedded Software Engineer

You might also like

ゼロから作るDeep Learning ―Pythonで学ぶディープラーニングの理論と実装

ゼロから作るDeep Learning ―Pythonで学ぶディープラーニングの理論と実装

斎藤 康毅

Publisher Resources

ISBN: 9784814401611Publisher Website