paper-with-me

Papers

Deterministic Coreset Construction via Adaptive Sensitivity Trimming

2025-08-25 · Faruk Alpay, Taylan Alpay arxiv

We develop a rigorous framework for deterministic coreset construction in empirical risk minimization (ERM). Our central contribution is the Adaptive Deterministic Uniform-Weight Trimming (ADUWT) algorithm, which constructs a coreset by excising points with the lowest sensitivity bounds and applying a data-dependent uniform weight to the remainder. The method yields a uniform $(1\pm\varepsilon)$ relative-error approximation for the ERM objective over the entire hypothesis space. We provide complete analysis, including (i) a minimax characterization proving the optimality of the adaptive weight, (ii) an instance-dependent size analysis in terms of a \emph{Sensitivity Heterogeneity Index}, and (iii) tractable sensitivity oracles for kernel ridge regression, regularized logistic regression, and linear SVM. Reproducibility is supported by precise pseudocode for the algorithm, sensitivity oracles, and evaluation pipeline. Empirical results align with the theory. We conclude with open problems on instance-optimal oracles, deterministic streaming, and fairness-constrained ERM.

📄 PDF Abstract BibTeX arXiv:2508.18340

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Improving Model Classification by Optimizing the Training Dataset

2025-07-22 · Morad Tukan, Loay Mualem, Eitan Netzer, Liran Sigalat arxiv

In the era of data-centric AI, the ability to curate high-quality training data is as crucial as model design. Coresets offer a principled approach to data reduction, enabling efficient learning on large datasets through…

Training Support Vector Machines using Coresets

2017-08-13 · Cenk Baykal, Lucas Liebenwein, Wilko Schwarting

We present a novel coreset construction algorithm for solving classification tasks using Support Vector Machines (SVMs) in a computationally efficient manner. A coreset is a weighted subset of the original data points th…

Deterministic Coreset for Lp Subspace

2026-01-01 · Rachit Chhaya, Anirban Dasgupta, Dan Feldman, Supratim Shit arxiv

We introduce the first iterative algorithm for constructing a $\varepsilon$-coreset that guarantees deterministic $\ell_p$ subspace embedding for any $p \in [1,\infty)$ and any $\varepsilon > 0$. For a given full rank ma…

Tight Sensitivity Bounds For Smaller Coresets

2019-07-02 · Alaa Maalouf, Adiel Statman, Dan Feldman

An $\varepsilon$-coreset for Least-Mean-Squares (LMS) of a matrix $A\in{\mathbb{R}}^{n\times d}$ is a small weighted subset of its rows that approximates the sum of squared distances from its rows to every affine $k$-dim…

Sensitivity

Tuning-Free Coreset Markov Chain Monte Carlo via Hot DoG

2024-10-24 · Naitong Chen, Jonathan H. Huggins, Trevor Campbell

A Bayesian coreset is a small, weighted subset of a data set that replaces the full data during inference to reduce computational cost. The state-of-the-art coreset construction algorithm, Coreset Markov chain Monte Carl…

Stochastic Optimization