Optimal Autoregressive Chain-of-Thought Learning via Bagging

We study how to learn an autoregressive next-token generator $f\colonΣ^\star\toΣ$ from a class $\mathcal{F}$, given chain-of-thought (CoT) demonstrations of length $T$ generated by $f$. We present a simple algorithm based on bagging, which outputs a majority vote of generators that are trained to be CoT-consistent on bootstrap samples of the training data. For binary token sets, it achieves the optimal sample complexity of $O((d_{\mathrm{VC}}+\log(1/δ))/ε)$, independent of the CoT length $T$, where $d_{\mathrm{VC}}$ is the VC dimension of $\mathcal{F}$. For finite token sets $Σ$, the VC dimension is replaced by a multiclass analogue, the Graph dimension $d_{\mathrm{G}}$, and the sample complexity is optimal up to a $\log|Σ|$ factor. The number of generators in the majority-vote ensemble is $O(\log(T/δ))$, and we show that the ensemble can be distilled into a single generator in $\mathcal{F}$ at the expense of $n\log(nT)$ unlabeled prompts.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-16
DOI
https://doi.org/10.48550/arxiv.2611.21597
Primary Topic
Machine Learning and Algorithms
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Optimal Autoregressive Chain-of-Thought Learning via Bagging

Awni Altabaa, John Lafferty, Omar Montasser
arXiv (Cornell University)
Machine Learning and Algorithms
preprint

Optimal Autoregressive Chain-of-Thought Learning via Bagging

Awni Altabaa, John Lafferty, Omar Montasser
preprint en

Abstract

We study how to learn an autoregressive next-token generator $f\colonΣ^\star\toΣ$ from a class $\mathcal{F}$, given chain-of-thought (CoT) demonstrations of length $T$ generated by $f$. We present a simple algorithm based on bagging, which outputs a majority vote of generators that are trained to be CoT-consistent on bootstrap samples of the training data. For binary token sets, it achieves the optimal sample complexity of $O((d_{\mathrm{VC}}+\log(1/δ))/ε)$, independent of the CoT length $T$, where $d_{\mathrm{VC}}$ is the VC dimension of $\mathcal{F}$. For finite token sets $Σ$, the VC dimension is replaced by a multiclass analogue, the Graph dimension $d_{\mathrm{G}}$, and the sample complexity is optimal up to a $\log|Σ|$ factor. The number of generators in the majority-vote ensemble is $O(\log(T/δ))$, and we show that the ensemble can be distilled into a single generator in $\mathcal{F}$ at the expense of $n\log(nT)$ unlabeled prompts.

arXiv (Cornell University)
Machine Learning and Algorithms
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