English
Related papers

Related papers: Optimally compressing VC classes

200 papers

This paper considers completions of COMs (complexes oriented matroids) to ample partial cubes of the same VC-dimension. We show that these exist for OMs (oriented matroids) and CUOMs (complexes of uniform oriented matroids). This implies…

Combinatorics · Mathematics 2021-09-22 Victor Chepoi , Kolja Knauer , Manon Philibert

We introduce the following variant of the VC-dimension. Given $S \subseteq \{0, 1\}^n$ and a positive integer $d$, we define $\mathbb{U}_d(S)$ to be the size of the largest subset $I \subseteq [n]$ such that the projection of $S$ on every…

Computational Complexity · Computer Science 2022-06-28 Peter Frankl , Svyatoslav Gryaznov , Navid Talebanfard

In lossy image compression, the objective is to achieve minimal signal distortion while compressing images to a specified bit rate. The increasing demand for visual analysis applications, particularly in classification tasks, has emphasized…

Multimedia · Computer Science 2024-05-07 Yuefeng Zhang

This work develops compressive sampling strategies for computing the dynamic mode decomposition (DMD) from heavily subsampled or output-projected data. The resulting DMD eigenvalues are equal to DMD eigenvalues from the full-state data. It…

Dynamical Systems · Mathematics 2013-12-19 Steven L. Brunton , Joshua L. Proctor , J. Nathan Kutz

We study the problem of representing all distances between $n$ points in $\mathbb R^d$, with arbitrarily small distortion, using as few bits as possible. We give asymptotically tight bounds for this problem, for Euclidean metrics, for…

Computational Geometry · Computer Science 2021-10-08 Piotr Indyk , Tal Wagner

This work continues the study of the relationship between sample compression schemes and statistical learning, which has been mostly investigated within the framework of binary classification. The central theme of this work is establishing…

Machine Learning · Computer Science 2017-01-02 Ofir David , Shay Moran , Amir Yehudayoff

Motivated by the need for communication-efficient distributed learning, we investigate the method for compressing a unit norm vector into the minimum number of bits, while still allowing for some acceptable level of distortion in recovery.…

Information Theory · Computer Science 2024-02-06 Heng Zhu , Avishek Ghosh , Arya Mazumdar

We establish a tight characterization of the worst-case rates for the excess risk of agnostic learning with sample compression schemes and for uniform convergence for agnostic sample compression schemes. In particular, we find that the…

Machine Learning · Computer Science 2018-05-22 Steve Hanneke , Aryeh Kontorovich

We prove that, for any $d$ linearly independent functions from some set into a $d$-dimensional vector space over any field, the family of zero sets of all non-trivial linear combination of these functions has VC-dimension and Littlestone…

Logic · Mathematics 2021-09-13 Vincent Guingona , Alexei Kolesnikov , Julie Nierwinski , Richard Soucy

We derive an algorithm for compression of the currents and varifolds representations of shapes, using ridge leverage score (RLS) sampling, and the theory of Nystrom approximation in Reproducing Kernel Hilbert Spaces. Our method is faster…

Numerical Analysis · Mathematics 2026-03-18 Allen Paul , Neill Campbell , Tony Shardlow

We analyze the coordinate descent method with a new coordinate selection strategy, called volume sampling. This strategy prescribes selecting subsets of variables of certain size proportionally to the determinants of principal submatrices…

Optimization and Control · Mathematics 2020-04-30 Anton Rodomanov , Dmitry Kropotov

We prove that $\tilde{\Theta}(k d^2 / \varepsilon^2)$ samples are necessary and sufficient for learning a mixture of $k$ Gaussians in $\mathbb{R}^d$, up to error $\varepsilon$ in total variation distance. This improves both the known upper…

Machine Learning · Computer Science 2020-07-23 Hassan Ashtiani , Shai Ben-David , Nick Harvey , Christopher Liaw , Abbas Mehrabian , Yaniv Plan

We study the complexity of computing (and approximating) VC Dimension and Littlestone's Dimension when we are given the concept class explicitly. We give a simple reduction from Maximum (Unbalanced) Biclique problem to approximating VC…

Computational Complexity · Computer Science 2022-11-04 Pasin Manurangsi

Gradient compression is of growing interests for solving constrained optimization problems including compressed sensing, noisy recovery and matrix completion under limited communication resources and storage costs. Convergence analysis of…

Optimization and Control · Mathematics 2024-10-30 Zhaoyue Xia , Jun Du , Chunxiao Jiang , H. Vincent Poor , Yong Ren

While the optimal sample complexity of binary classification in terms of the VC dimension is well-established, determining the optimal sample complexity of multiclass classification has remained open. The appropriate complexity parameter…

Machine Learning · Computer Science 2026-04-28 Chirag Pabbaraju

Suppose an $n \times d$ design matrix in a linear regression problem is given, but the response for each point is hidden unless explicitly requested. The goal is to sample only a small number $k \ll n$ of the responses, and then produce a…

Machine Learning · Computer Science 2018-09-06 Michał Dereziński , Manfred K. Warmuth , Daniel Hsu

In this paper, we provide a computable characterization of the geometry of optimal representations in Contrastive Learning (CL) when the classes are imbalanced. When classes are balanced and the representation dimension is greater than the…

Machine Learning · Computer Science 2026-05-13 Thuan Nguyen , Shuchin Aeron , D. Richard Brown , Prakash Ishwar

We provide guarantees for learning latent variable models emphasizing on the overcomplete regime, where the dimensionality of the latent space can exceed the observed dimensionality. In particular, we consider multiview mixtures, spherical…

Machine Learning · Computer Science 2014-12-18 Animashree Anandkumar , Rong Ge , Majid Janzamin

A set-system $S\subseteq \{0,1\}^n$ is cube-ideal if its convex hull can be described by capacity and generalized set covering inequalities. In this paper, we use combinatorics, convex geometry, and polyhedral theory to give exponential…

Combinatorics · Mathematics 2026-04-21 Ahmad Abdi , Gérard Cornuéjols , Daniel Dadush , Mahsa Dalirrooyfard

The Poisson-sampling technique eliminates dependencies among symbol appearances in a random sequence. It has been used to simplify the analysis and strengthen the performance guarantees of randomized algorithms. Applying this method to…

Information Theory · Computer Science 2014-05-30 Jayadev Acharya , Ashkan Jafarpour , Alon Orlitsky , Ananda Theertha Suresh