← Back to all news
arXiv Statistics ML By Dario Bocchi, Matteo Negri, Flavio Nicoletti, Francesco D'Amico

Generalization properties of the token perceptron: the role of embedding and vocabulary

Read the original on arXiv Statistics ML →

The paper investigates how the geometry of token embeddings influences learning in a minimal token‑perceptron model, where a linear predictor maps sequences of embedded tokens to outputs. Using the replica method, it derives generalization errors for continuous spherical embeddings and for discrete vocabulary embeddings, revealing that learning thresholds depend on embedding dimension and that optimal learners prioritize directions of greatest variance in the embedding space. The study also quantifies storage capacity and recovery thresholds for noiseless regression and random associations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Statistics ML.

Related stories

arXiv Statistics ML
Oct 1

Optimal VC Dimension of Contrastive Learning with Margin

arXiv:2609.38834v1 Announce Type: cross Abstract: Contrastive learning is a successful paradigm for learning $d$-dimensional geometric representations from a collection of ``anchor--positive--negativ...

By Dionysis Arvanitakis, Vaggos Chatziafratis, Yiyuan Luo, Konstantin Makarychev
rag
More like this →
arXiv Machine Learning
Sep 3

Exact Limits of Random Projections for Preserving Geometry: Distance Recovery, Nearest-Neighbor Rankings, and Covariance Shape in Gaussian Models

arXiv:2609. 02155v1 Announce Type: new Abstract: The Johnson-Lindenstrauss (JL) lemma guarantees that a random projection of $n$ points to $m=O(\varepsilon^{-2}\log n)$ dimensions preserves pairwise squared distances within relative error $\varepsilon$ with high probability, and this dimension order is asymptotically optimal.

By Piyush Sao
More like this →
arXiv Machine Learning
Jul 13

A Fourier analytique approach to Gaussian mixture learning

arXiv:2004. 05813v3 Announce Type: replace-cross Abstract: Suppose that we are given independent, identically distributed random samples $x_1,\cdots,x_n$ from a mixture at most $k$ many $d$-dimensional spherical Gaussian distributions $\mu_1,\cdots,\mu_{k_0}$ of identical and known variance $\sigma^2$ in each coordinate, such that the minimum $\ell^2$ distance between two distinct centers $y_l$ and $y_j$ is greater than $2\Delta\sigma \min\{\sqrt{d},\sqrt k\}$, where $\Delta>C_0$, and $C_0$ is a sufficiently large universal constant.

By Somnath Chakraborty, Hariharan Narayanan
More like this →