The dense result substantially generalizes a theorem of Bansal and Spencer (2020) for Rademacher inputs and gives an efficient $O(\sqrt{n})$ bound for Gaussian inputs, as conjectured by Gamarnik et al. (2022).
Abstract
We study online discrepancy minimization: vectors $v_1,\ldots,v_T\in\mathbb{R}^n$ arrive sequentially, and each must immediately be assigned a sign $x_t\in\{\pm1\}$, with the aim of minimizing $\|\sum_{t=1}^T x_t v_t\|_\infty$. We give a polynomial-time potential-based algorithm combining a regularization of the $\ell_\infty$-norm with restriction to an adaptively chosen coordinate set. For i.i.d. inputs with independent, symmetric, centered, unit-variance sub-Gaussian coordinates of sub-Gaussian norm at most $\sigma$, the algorithm achieves terminal discrepancy $O(\sigma^8\sqrt{n})$ with probability at least $1-\exp(-\Omega(\sigma^3\sqrt{n}))$. If the coordinates are independently masked by Bernoulli variables with mean $k/n$, where $k\gtrsim(\log n)^2$, the bound improves to $O(\sigma^8\sqrt{k})$, with failure probability $\exp(-\Omega(\sigma^3\sqrt{k}))$. Both guarantees hold for every prescribed finite horizon $T$, with no dependence on $T$. The dense result substantially generalizes a theorem of Bansal and Spencer (2020) for Rademacher inputs and gives an efficient $O(\sqrt{n})$ bound for Gaussian inputs, as conjectured by Gamarnik et al. (2022). When $T$ is polynomially larger than $n$, this is conditionally close to optimal: under worst-case hardness assumptions for standard approximate lattice problems, Vafa and Vaikuntanathan (2025) showed that no polynomial-time algorithm, even offline, can improve the $\sqrt{n}$ scale by a fixed polynomial factor in $T/n$.
We prove that the $L_1$-discrepancy with arbitrary nonnegative weights suffers from the curse of dimensionality. More precisely, for every $\varepsilon \in (0,1)$ and $d \in \mathbb{N}$, the inverse of the $L_1$-discrepancy satisfies \[ N_{1,+}(\varepsilon, d) \ge \frac{(1-\varepsilon)^2}{1 + \varepsilon} \left( \frac{3+2 \sqrt{3}}{6}\right)^d, \] where $(3+2\sqrt{3})/6 = 1.07735\ldots$. The proof combines a change to a volume-biased probability measure with a fractional-moment estimate for the normalized discrepancy function. The lower bound applies, in particular, to equally weighted point sets. The argument uses the nonnegativity of the weights in an essential way and does not cover arbitrary signed weights.
Let $X_1,\ldots,X_n$ be independent Gaussian tensors in $\mathbb{R}^{d_1}\otimes\cdots\otimes\mathbb{R}^{d_k}$ with a common covariance matrix given by the Kronecker product of $k$ unknown positive-definite factors, and let $D=\prod_{a=1}^k d_a$ and $d_{\max}=\max_a d_a$. Franks et al. (2026) established condition-number-free guarantees for the tensor-normal maximum likelihood estimator under the sample-size condition $nD\gtrsim k^2 d_{\max}^3$ and asked whether the cubic dependence on $d_{\max}$ could be reduced to a quadratic one. We answer this question affirmatively. For $t\geq 1$, if $nD\geq C k^2 d_{\max}^2 t^2$, then with high probability the maximum likelihood estimator exists, is unique, and satisfies $d_{\rm FR}(\widehat\Theta,\Theta)\leq C t \sqrt{k} d_{\max}/\sqrt{n}$ and $d_{\rm FR}(\widehat\Theta_a,\Theta_a)\leq C t\sqrt{k d_a} d_{\max}/\sqrt{nD}$ for every mode $a$. For every mode $a$ with $d_a=d_{\max}$, we further establish the sharp Thompson-metric bound $d_{\rm op}(\widehat\Theta_a,\Theta_a)\leq C t d_{\max}/\sqrt{nD}$. These guarantees are uniform over the unknown covariance factors and require neither condition-number bounds nor sparsity assumptions. Gaussian submodel lower bounds match the full and largest-factor Fisher--Rao rates up to a factor of $\sqrt{k}$ and the largest-factor Thompson rate up to universal constants. Consequently, for fixed $k$, the quadratic dependence of the sample-size threshold on $d_{\max}$ is optimal. GPT-5.6 Sol and Claude Fable 5 were used to assist with proof development, verification, and manuscript preparation.
This work develops an approach to the spectral norm of the matrix product $\Pi U_V$, based on entropy estimates for level sets of vectors $x\in V$, and shows that matching results hold for other random models with negatively associated entries.
Let $R$ be an $m\times m$ correlation matrix satisfying $R-\mathbf{1}\mathbf{1}^{\mathsf T}/m\succeq0$, let $X\sim\mathcal{N}(0,R)$, and let $Z_1,\ldots,Z_m$ be independent standard Gaussian random variables. We prove $\max_i X_i\leq_{\mathrm{st}}\max_i Z_i$, with equality in distribution if and only if $R=I_m$. We use this comparison to resolve the Weak Simplex Conjecture: among $d+1$ equiprobable equal-energy signals in $\mathbb{R}^d$ transmitted over an additive white Gaussian noise channel, the regular simplex is the unique maximizer of the average probability of correct maximum-likelihood decoding at every signal-to-noise ratio. The same comparison proves the Simplex Mean Width Conjecture and gives the exact finite-energy performance of deterministic no-feedback AWGN codes with equiprobable messages, no restriction on the number of channel uses, and a maximal per-codeword energy constraint. The proof uses a Gaussian product inequality for log-concave functions whose first moments with respect to standard Gaussian measure vanish. A variational argument chooses one exponential tilt and one truncation endpoint in each coordinate so that this product inequality applies and a Gaussian change of measure returns all coordinates to the prescribed common threshold. A strict form of the product inequality also shows that, unless $R=I_m$, $\mathbb{P}\{X\leq c\mathbf{1}\}>\Phi(c)^m$ for every finite $c$, and hence gives the distributional equality statement. A Lean formalization is available at https://github.com/abhmul/weak-simplex-conjecture-lean.
For $n$ unit vectors $x_1,\ldots,x_n \in \mathbb{R}^d$, we study the continuous ReLU derivative Gram matrix $H$, whose entries are obtained by averaging pairwise gated inner products over a standard Gaussian direction. Writing $ \Delta_\pm := \min_{i \neq j} \min\{ \|x_i-x_j\|_2, \|x_i+x_j\|_2 \} $ for their projective separation, we prove the universal dimension-free lower bound $ \lambda_{\min}(H) = \Omega( \Delta_\pm/\sqrt{\log n} ) $. Conversely, we construct worst-case families satisfying the matching upper bound $ \lambda_{\min}(H) = O( \Delta_\pm/\sqrt{\log n} ) $, showing that this rate is tight up to universal constants.
A nonuniform version in which the failure probability depends on the individual parameters, and a lower bound showing that a universal constant prefix discrepancy is impossible when $d=o(\ln T)$, are proved.
Antonios Hmadi· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
