A construction based on a hidden determinant sign is introduced and a lower bound of the $\Omega_\delta(\sqrt{\kappa}\log d)$ lower bound at constant accuracy is proved even when the spectrum of the precision matrix is known to the algorithm.
Abstract
We study the number of exact matrix-vector queries needed to sample a centered $d$-dimensional Gaussian with condition number at most $\kappa$ to total variation error $\varepsilon$. The best known algorithm uses $O(\min\{d,\sqrt{\kappa}\log(\frac{d}{\varepsilon})\})$ queries, while the known lower bounds do not grow as $\varepsilon\to0$ and match this bound only for $\kappa\le d^{1/5-\delta}$ at constant accuracy. We introduce a construction based on a hidden determinant sign and prove a lower bound of $\Omega\!\left(\min\left\{d,\sqrt{\kappa}\log\left(1+\frac{d}{\sqrt{\kappa}\,\varepsilon}\right)\right\}\right)$ uniformly for all $d\ge1$, $\kappa\ge4$, and $0<\varepsilon\le\tfrac{1}{16}$. This bound matches the known upper bound up to constant factors whenever $\kappa\le d^{2-\delta}$ for fixed $\delta\in(0,2)$, or $\varepsilon\le d^{-c}$ for fixed $c>0$. We also extend a recent fixed-spectrum construction with a hidden eigenbasis from $\kappa=2$ to $2\le\kappa\le d^{1-\delta}$, for any fixed $\delta\in(0,1)$. This gives an $\Omega_\delta(\sqrt{\kappa}\log d)$ lower bound at constant accuracy that holds even when the spectrum of the precision matrix is known to the algorithm.
We study the average-case matrix discrepancy problem: given independent normalized $d\times d$ Gaussian orthogonal ensemble matrices $A_1,\dots,A_N$ and a fixed margin $\kappa>0$, find signs $\sigma_1,\dots,\sigma_N\in\{-1,1\}$ such that the operator norm of $\sum_{i=1}^N \sigma_i A_i$ is at most $\kappa\sqrt{N}$. Focu...
We provide sharp estimates on the number of vertices needed to approximate the Euclidean unit ball $B_d\subset\mathbb R^d$ with relative symmetric-difference volume error at most $\varepsilon\in(0,1)$. We show that the minimum vertex budget $N_\varepsilon(d)$ satisfies $$\log N_\varepsilon(d)\asymp d\log\left(1+\frac1{...
Yegor Gorodzha, Steven Hoehner, Gil Kur· 0 citations
We determine the Fourier dimension of exactly approximation set for all dimensions. More precisely, let $m,n\ge1$, $\boldsymbol\theta\in\mathbb R^m$, and $\psi:\mathbb N\to \mathbb R^+$ be a non-increasing approximate function. Denote by $\textrm{Exact}_{m,n}(\psi,\boldsymbol\theta)$ the set of $m\times n$ matrices whi...
We establish upper bounds on the Shannon entropy $\mathbb H(\widehat f^{\,2})$ of the Fourier distribution of Boolean functions. We prove that $$ \mathbb H(\widehat f^{\,2}) =O\!\left(\log\bigl(1+\|\widehat f\|_{1,1/3}\bigr)\right), $$ where $\|\widehat f\|_{1,1/3}$ denotes the minimum spectral norm of a pointwise $1/3...
We characterize, up to logarithmic factors, the minimax expected query complexity of finite-sum nonconvex-strongly-concave optimization under mean-squared averaged smoothness. For randomized zero-respecting incremental first-order algorithms, the complexity is $\tilde{\Theta}(n+\min\{\sqrt{n}\,\kappa,n^{3/4}\sqrt{\kapp...
We study deterministic adaptive optimization of globally $\beta$-smooth, $\mu$-strongly convex functions using exact scalar function values. Queries and outputs lie in $B_2^d(R)$, and the minimizer lies in $B_2^d(R/2)$. Set $\kappa=\beta/\mu$, $Q=\beta R^2/\epsilon$, and $D_d=(d/\log(ed))^{1/3}$. For sufficiently large...
Wen-Dao Wu, Hai-Han Zhang, Chen-Heng Zhang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.