Linear sketches estimate properties of high-dimensional inputs from a fixed low-dimensional projection. At constant accuracy, randomized Euclidean-norm sketches, notably the Johnson-Lindenstrauss transform, support exponentially many nonadaptive queries in sketch dimension $k$. For adaptive black-box queries, known privacy-based defenses guarantee $\widetilde{\Omega}(k^2)$ and it remained open whether stronger guarantees were possible. Prior attacks used more queries, restricted the responder, or provided weaker failure guarantees. We show that the quadratic guarantee is optimal up to logarithmic factors, even with a computationally unbounded responder that knows the matrix, attack algorithm, history, and query distributions and may change its randomized rule after every query. For every fixed hidden $A\in\mathbb{R}^{k\times n}$ with $n>40k$ and target accuracy $\alpha \in (0,1]$, our black-box attack uses $O(k+\alpha^2k^2\log(2+\alpha^2k))$ queries in $\widetilde{O}(1+\alpha^2k)$ adaptive rounds to force, with constant probability, a round in which a constant fraction of answers have $\Omega(\alpha)$ relative error. Our results clarify the limits of defending a fixed compressive linear representation by adapting the prediction rule.
Can a constant number of linear minimizations per round improve on the $T^{3/4}$ regret rate of online Frank-Wolfe on general convex sets? Weibel et al. conjectured that fixed-coefficient methods cannot. We prove their conjecture and extend the lower bound to every deterministic learner in an oracle-only model. The lea...
We study the offline release of a public family of $k$ statistical queries on a database of $N$ records from a public universe of size $d$, under pure $\varepsilon$-differential privacy. We give an efficient algorithm that, with probability at least $1-\beta$, answers all queries simultaneously to error $$O\left(\min\l...
We study the query complexity of optimization with exact scalar-value information. For globally $L$-smooth convex functions on $\mathbb R^d$ with a minimizer in a Euclidean ball of radius $R$, we prove the lower bound $\Omega(d\min\{d,\sqrt{LR^2/\varepsilon}\})$ for adaptive randomized algorithms in the stated accuracy...
Y. Dorn, D. Dvinskikh, Т. В. Логінов et al.· 0 citations
We design adversarially robust algorithms for dynamic geometric streams that $(1 + \epsilon)$-approximate $k$-Median and $k$-Means in Euclidean space $\mathbb{R}^d$, using $\tilde{O}(kd \mathrm{poly}(\epsilon^{-1}))$ space. This result significantly improves a recent $O(d\log n)$-approximation for $k$-Median [Gribelyuk...
Cheng-Zhi Guo, S. Jiang, Robert Krauthgamer et al.· 0 citations
This paper introduces learning with algebraic rounding (LAR), which applies an explicit integer rounding map to blocks of secret-dependent linear measurements and encodes the result in a lattice quotient, and yields the first post-quantum weak pseudorandom function with joint key-and-input evaluation in $TC^0.
In the weak-strong distance oracle model of Bateni, Dharangutte, Jayaram and Wang (COLT 2024), a metric $(X,d)$ on $n$ points is accessed through two oracles: a cheap weak oracle that returns each queried distance correctly with probability $1-\delta$ and permits arbitrary values on corrupted pairs, chosen by an advers...
Zachary Friggstad, Mahya Jamshidian, A. Vakilian· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.