arXiv Machine Learning

A Counterexample to the Tang Zhang Schatten Norm Conjecture and Sharp Positive Results

arXiv:2608. 15558v1 Announce Type: cross Abstract: For $m\geq 2$, let $c_p(m)$ be the all-dimensional best constant in $$ \left\|\sum_{k=1}^m A_k\right\|_p \leq c_p(m)\left\|\sum_{k=1}^m |A_k|\right\|_p.

arXiv Machine Learning
Aug 31

An algebraic proof of Colombo's difference-power determinant conjecture

arXiv:2608. 28274v1 Announce Type: new Abstract: Let $n\ge2$ be even, let $\lambda=(\lambda_1,\ldots,\lambda_n)\in\mathbb{R}^n$ have pairwise distinct coordinates, and define the difference-power matrix \[ A_d(\lambda) := \bigl[(\lambda_r-\lambda_s)^d\bigr]_{r,s=1}^n, \qquad d\in\mathbb{N}.

By Kun Li, Li Tie, Peng Wang, Zihan Liu
arXiv Machine Learning
Jul 28

A Resolution of the SS--RS--GD Inequalities

arXiv:2607. 22620v1 Announce Type: cross Abstract: Yun, Sra, and Jadbabaie (COLT 2021, open question) conjectured the SS--RS--GD inequalities: for well-conditioned symmetric matrices $A_1,\dots,A_n$, the operators $W_{ss}$, $W_{rs}$, and $W_{gd}$ that encode the expected iterate of single-shuffle SGD, random-reshuffle SGD, and gradient descent on a quadratic finite sum should satisfy \[ \|W_{ss}\|\le \| W_{rs}\|\le \|W_{gd}\|.

By Binghui Peng