paper-with-me

홈 › Papers

Tight Sample Complexity of Transformers

2026-06-08 · Chenxiao Yang, Nathan Srebro, Zhiyuan Li arxiv

We tightly characterize the VC dimension of depth-$L$ Transformers with a total of $W$ parameters, mapping an input sequence of length $T$ to a single output, establishing an upper bound of $O(L W \log (T W))$ and a nearly matching lower bound of $Ω(L W \log (T W / L))$. We further tightly characterize the sample complexity of chain-of-thought learning using such a Transformer, showing teacher forcing (i.e. selecting a predictor consistent with the entire chain-of-thought on training data) learns with sample complexity $O\left(L W \log \left(\left(T+T^{\prime}\right) W\right)\right)$ and that any learning rule that uses chain-of-thought data requires at least $Ω\left(L W \log \left(\left(T+T^{\prime}\right) W / L\right)\right)$ examples, where $T$ is the input length and $T^{\prime}$ is the number of autoregressive steps.

📄 PDF Abstract BibTeX arXiv:2606.09731

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers

2021-07-28 · Colin Wei, Yining Chen, Tengyu Ma

A common lens to theoretically study neural net architectures is to analyze the functions they can approximate. However, constructions from approximation theory may be unrealistic and therefore less meaningful. For examp…

Generalization Bounds

Tight Sample Complexity of Large-Margin Learning

2010-12-01 · NeurIPS 2010 12 · Sivan Sabato, Nathan Srebro, Naftali Tishby

We obtain a tight distribution-specific characterization of the sample complexity of large-margin classification with L2 regularization: We introduce the gamma-adapted-dimension, which is a simple function of the spectru…

ClassificationGeneral ClassificationL2 Regularization

Statistically Meaningful Approximation: a Theoretical Analysis for Approximating Turing Machines with Transformers

2021-09-29 · Colin Wei, Yining Chen, Tengyu Ma

A common lens to theoretically study neural net architectures is to analyze the functions they can approximate. However, constructions from approximation theory may be unrealistic and therefore less meaningful. For examp…

Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty Quantification

2025-10-02 · Zeqi Ye, Minshuo Chen arxiv

Imputation methods play a critical role in enhancing the quality of practical time-series data, which often suffer from pervasive missing values. Recently, diffusion-based generative imputation methods have demonstrated …

Expressivity of Transformers: A Tropical Geometry Perspective

2026-04-16 · Ye Su, Yong Liu arxiv

To quantify the geometric expressivity of transformers, we introduce a tropical geometry framework to characterize their exact spatial partitioning capabilities. By modeling self-attention as a vector-valued tropical rat…