English
Related papers

Related papers: Lower bounds for oblivious subspace embeddings

200 papers

A graph $G=(V,E)$ is geometrically embeddable into a normed space $X$ when there is a mapping $\zeta: V\to X$ such that $\|\zeta(v)-\zeta(w)\|_X\leqslant 1$ if and only if $\{v,w\}\in E$, for all distinct $v,w\in V$. Our result is the…

Combinatorics · Mathematics 2026-04-20 Dylan J. Altschuler , Pandelis Dodos , Konstantin Tikhomirov , Konstantinos Tyros

The quality of self-supervised pre-trained embeddings on out-of-distribution (OOD) data is poor without fine-tuning. A straightforward and simple approach to improving the generalization of pre-trained representation to OOD data is the use…

Machine Learning · Computer Science 2024-11-21 Shuman Peng , Arash Khoeini , Sharan Vaswani , Martin Ester

We study the problem of minimum enclosing rectangle with outliers, which asks to find, for a given set of $n$ planar points, a rectangle with minimum area that encloses at least $(n-t)$ points. The uncovered points are regarded as outliers.…

Computational Geometry · Computer Science 2021-09-16 Zhengyang Guo , Yi Li

A subspace partition $\Pi$ of $V=V(n,q)$ is a collection of subspaces of $V$ such that each 1-dimensional subspace of $V$ is in exactly one subspace of $\Pi$. The size of $\Pi$ is the number of its subspaces. Let $\sigma_q(n,t)$ denote the…

Combinatorics · Mathematics 2011-04-15 Olof Heden , Juliane Lehmann , Esmeralda Nastase , Papa Sissokho

We show optimal lower bounds for spanning forest computation in two different models: * One wants a data structure for fully dynamic spanning forest in which updates can insert or delete edges amongst a base set of $n$ vertices. The sole…

Data Structures and Algorithms · Computer Science 2019-11-27 Jelani Nelson , Huacheng Yu

We show hardness of improperly learning halfspaces in the agnostic model, both in the distribution-independent as well as the distribution-specific setting, based on the assumption that worst-case lattice problems, such as GapSVP or SIVP,…

Machine Learning · Computer Science 2023-02-21 Stefan Tiegel

We study first-order optimization algorithms under the constraint that the descent direction is quantized using a pre-specified budget of $R$-bits per dimension, where $R \in (0 ,\infty)$. We propose computationally efficient optimization…

Machine Learning · Computer Science 2022-08-17 Rajarshi Saha , Mert Pilanci , Andrea J. Goldsmith

For an undirected unweighted graph G = (V, E) with n vertices and m edges, let d(u, v) denote the distance from u in V to v in V in G. An (alpha, beta)-stretch approximate distance oracle (ADO) for G is a data structure that, given u, v in…

Data Structures and Algorithms · Computer Science 2024-10-02 Tsvi Kopelowitz , Ariel Korin , Liam Roditty

Suppose that we are given a string $s$ of length $n$ over an alphabet $\{0,1,\ldots,n^{O(1)}\}$ and $\delta$ is the string complexity of $s$, a known compression measure. We describe an index on $s$ with $O(\delta\log\frac{n}{\delta})$…

Data Structures and Algorithms · Computer Science 2026-04-15 Dmitry Kosolobov

A major open problem in the field of metric embedding is the existence of dimension reduction for $n$-point subsets of Euclidean space, such that both distortion and dimension depend only on the {\em doubling constant} of the pointset, and…

Computational Geometry · Computer Science 2013-08-26 Yair Bartal , Lee-Ad Gottlieb , Ofer Neiman

We consider the problem of stochastic convex optimization with exp-concave losses using Empirical Risk Minimization in a convex class. Answering a question raised in several prior works, we provide a $O( d / n + \log( 1 / \delta) / n )$…

Machine Learning · Computer Science 2023-07-06 Nikita Puchkin , Nikita Zhivotovskiy

Let $(P,E)$ be a $(d+1)$-uniform geometric hypergraph, where $P$ is an $n$-point set in general position in $\mathbb{R}^d$ and $E\subseteq {P\choose d+1}$ is a collection of $\epsilon{n\choose d+1}$ $d$-dimensional simplices with vertices…

Combinatorics · Mathematics 2024-03-04 Natan Rubin

Is it possible to find the sparsest vector (direction) in a generic subspace $\mathcal{S} \subseteq \mathbb{R}^p$ with $\mathrm{dim}(\mathcal{S})= n < p$? This problem can be considered a homogeneous variant of the sparse recovery problem,…

Information Theory · Computer Science 2016-09-21 Qing Qu , Ju Sun , John Wright

If a single particle obeys non-relativistic QM in R^d and has the Hamiltonian H = - Delta + f(r), where f(r)=sum_{i = 1}^{k}a_ir^{q_i}, 2\leq q_i < q_{i+1}, a_i \geq 0$, then the eigenvalues E = E_{n\ell}^{(d)}(\lambda) are given…

Mathematical Physics · Physics 2009-11-13 Qutaibeh D. Katatbeh , Richard L. Hall , Nasser Saad

We prove better lower bounds on additive spanners and emulators, which are lossy compression schemes for undirected graphs, as well as lower bounds on shortcut sets, which reduce the diameter of directed graphs. We show that any $O(n)$-size…

Data Structures and Algorithms · Computer Science 2019-07-23 Shang-En Huang , Seth Pettie

Consider an m by N matrix Phi with the Restricted Isometry Property of order k and level delta, that is, the norm of any k-sparse vector in R^N is preserved to within a multiplicative factor of 1 +- delta under application of Phi. We show…

Information Theory · Computer Science 2011-02-14 Felix Krahmer , Rachel Ward

A classic problem in unsupervised learning and data analysis is to find simpler and easy-to-visualize representations of the data that preserve its essential properties. A widely-used method to preserve the underlying hierarchical structure…

Data Structures and Algorithms · Computer Science 2020-08-18 Vincent Cohen-Addad , Karthik C. S. , Guillaume Lagarde

Ordinary differential equations (ODEs), via their induced flow maps, provide a powerful framework to parameterize invertible transformations for the purpose of representing complex probability distributions. While such models have achieved…

Statistics Theory · Mathematics 2023-09-06 Youssef Marzouk , Zhi Ren , Sven Wang , Jakob Zech

Most linear dimension reduction methods proposed in the literature can be formulated using an appropriate pair of scatter matrices, see e.g. Ye and Weiss (2003), Tyler et al. (2009), Bura and Yang (2011), Liski et al. (2014) and Luo and Li…

Methodology · Statistics 2024-04-12 Klaus Nordhausen , Hannu Oja , David E. Tyler

We study the problem of PAC learning halfspaces with Massart noise. Given labeled samples $(x, y)$ from a distribution $D$ on $\mathbb{R}^{d} \times \{ \pm 1\}$ such that the marginal $D_x$ on the examples is arbitrary and the label $y$ of…

Machine Learning · Computer Science 2021-11-09 Ilias Diakonikolas , Daniel M. Kane