Maximum Dimension of Subspaces with No Product Basis
- URL: http://arxiv.org/abs/2010.16293v1
- Date: Fri, 30 Oct 2020 14:39:58 GMT
- Title: Maximum Dimension of Subspaces with No Product Basis
- Authors: Yuuya Yoshida
- Abstract summary: We show that the maximum dimension of subspaces of $mathcalFd_otimescdotsotimesmathcalFd_n$ with no product basis is equal to $d_n-2$ if either (i) $n=2$ or (ii) $nge3$ and $#mathcalF>maxd_i.
When $mathcalF=bbC$, this result is related to the maximum number of simultaneously distinguishable states in general probabilistic theories
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Let $n\ge2$ and $d_1,\ldots,d_n\ge2$ be integers, and $\mathcal{F}$ be a
field. A vector $u\in\mathcal{F}^{d_1}\otimes\cdots\otimes\mathcal{F}^{d_n}$ is
called a product vector if $u=u^{[1]}\otimes\cdots\otimes u^{[n]}$ for some
$u^{[1]}\in\mathcal{F}^{d_1},\ldots,u^{[n]}\in\mathcal{F}^{d_n}$. A basis
composed of product vectors is called a product basis. In this paper, we show
that the maximum dimension of subspaces of
$\mathcal{F}^{d_1}\otimes\cdots\otimes\mathcal{F}^{d_n}$ with no product basis
is equal to $d_1d_2\cdots d_n-2$ if either (i) $n=2$ or (ii) $n\ge3$ and
$\#\mathcal{F}>\max\{d_i : i\not=n_1,n_2\}$ for some $n_1$ and $n_2$. When
$\mathcal{F}=\mathbb{C}$, this result is related to the maximum number of
simultaneously distinguishable states in general probabilistic theories (GPTs).
Related papers
- Efficient Continual Finite-Sum Minimization [52.5238287567572]
We propose a key twist into the finite-sum minimization, dubbed as continual finite-sum minimization.
Our approach significantly improves upon the $mathcalO(n/epsilon)$ FOs that $mathrmStochasticGradientDescent$ requires.
We also prove that there is no natural first-order method with $mathcalOleft(n/epsilonalpharight)$ complexity gradient for $alpha 1/4$, establishing that the first-order complexity of our method is nearly tight.
arXiv Detail & Related papers (2024-06-07T08:26:31Z) - Provably learning a multi-head attention layer [55.2904547651831]
Multi-head attention layer is one of the key components of the transformer architecture that sets it apart from traditional feed-forward models.
In this work, we initiate the study of provably learning a multi-head attention layer from random examples.
We prove computational lower bounds showing that in the worst case, exponential dependence on $m$ is unavoidable.
arXiv Detail & Related papers (2024-02-06T15:39:09Z) - Dimension-free Remez Inequalities and norm designs [48.5897526636987]
A class of domains $X$ and test sets $Y$ -- termed emphnorm -- enjoy dimension-free Remez-type estimates.
We show that the supremum of $f$ does not increase by more than $mathcalO(log K)2d$ when $f$ is extended to the polytorus.
arXiv Detail & Related papers (2023-10-11T22:46:09Z) - On character table of Clifford groups [0.0]
We construct the character table of the Clifford group $mathcalC_n$ for $n=1,2,3$.
As an application, we can efficiently decompose the (higher power of) tensor product of the matrix representation.
As a byproduct, we give a presentation of the finite symplectic group $Sp(2n,2)$ in terms of generators and relations.
arXiv Detail & Related papers (2023-09-26T11:29:35Z) - A Fast Optimization View: Reformulating Single Layer Attention in LLM
Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time [7.613259578185218]
We focus on giving a provable guarantee for the one-layer attention network objective function $L(X,Y).
In a multi-layer LLM network, the matrix $B in mathbbRn times d2$ can be viewed as the output of a layer.
We provide an iterative algorithm to train loss function $L(X,Y)$ up $epsilon$ that runs in $widetildeO( (cal T_mathrmmat(n,d) + d
arXiv Detail & Related papers (2023-09-14T04:23:40Z) - Low-degree learning and the metric entropy of polynomials [49.1574468325115]
We prove that any (deterministic or randomized) algorithm which learns $mathscrF_nd$ with $L$-accuracy $varepsilon$ requires at least $Omega(sqrtvarepsilon)2dlog n leq log mathsfM(mathscrF_n,d,|cdot|_L,varepsilon) satisfies the two-sided estimate $$c (1-varepsilon)2dlog
arXiv Detail & Related papers (2022-03-17T23:52:08Z) - Matrix concentration inequalities and efficiency of random universal
sets of quantum gates [0.0]
For a random set $mathcalS subset U(d)$ of quantum gates we provide bounds on the probability that $mathcalS$ forms a $delta$-approximate $t$-design.
We show that for $mathcalS$ drawn from an exact $t$-design the probability that it forms a $delta$-approximate $t$-design satisfies the inequality $mathbbPleft(delta geq x right)leq 2D_t
arXiv Detail & Related papers (2022-02-10T23:44:09Z) - Learning low-degree functions from a logarithmic number of random
queries [77.34726150561087]
We prove that for any integer $ninmathbbN$, $din1,ldots,n$ and any $varepsilon,deltain(0,1)$, a bounded function $f:-1,1nto[-1,1]$ of degree at most $d$ can be learned.
arXiv Detail & Related papers (2021-09-21T13:19:04Z) - Spectral properties of sample covariance matrices arising from random
matrices with independent non identically distributed columns [50.053491972003656]
It was previously shown that the functionals $texttr(AR(z))$, for $R(z) = (frac1nXXT- zI_p)-1$ and $Ain mathcal M_p$ deterministic, have a standard deviation of order $O(|A|_* / sqrt n)$.
Here, we show that $|mathbb E[R(z)] - tilde R(z)|_F
arXiv Detail & Related papers (2021-09-06T14:21:43Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.