arXiv Machine Learning By Florian H\"ubler, Thomas Pethick, Suvrit Sra

Free Heavy-Tailed Lunch for Muon: A Theoretical Justification of Empirical Success

Read the original on arXiv Machine Learning →

arXiv:2606. 14560v1 Announce Type: cross Abstract: Non-Euclidean optimisation methods with matrix-valued updates, such as Muon and Scion, have recently shown strong empirical performance for training Transformer models, yet their theoretical advantages over Euclidean methods remain poorly understood.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

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
arXiv Machine Learning
Jul 27

On the Convergence of Stochastic Low-Rank Adaptation

arXiv:2607. 21975v1 Announce Type: new Abstract: Low-rank adaptation (LoRA) optimizes $J(B,A)=\mathcal L(W_\mathrm{base}+sBA)$ over two adapters $B \in \mathbb{R}^{m \times r}$ and $A \in \mathbb{R}^{r \times n}$ that form a low-rank update to a frozen pretrained weight matrix $W_\mathrm{base} \in \mathbb{R}^{m \times n}$.

By Ru Wang, Chengchang Liu, John C. S. Lui