English
Related papers

Related papers: Escaping the Curse of Dimensionality in Similarity…

200 papers

The aim of this paper is to propose a geometric framework for modelling similarity search in large and multidimensional data spaces of general nature, which seems to be flexible enough to address such issues as analysis of complexity,…

Information Retrieval · Computer Science 2016-11-17 Vladimir Pestov

Frank--Wolfe methods avoid projections, but over curved feasible regions the full-space linear minimization oracle (LMO) can itself become the computational bottleneck. We introduce random-subspace Frank--Wolfe (RSFW), the first…

Optimization and Control · Mathematics 2026-05-26 Pierre-Louis Poirion , Sebastian Pokutta , Akiko Takeda

Curse of Dimensionality is an unavoidable challenge in statistical probability models, yet diffusion models seem to overcome this limitation, achieving impressive results in high-dimensional data generation. Diffusion models assume that…

Machine Learning · Statistics 2025-10-01 Zhenxin Zheng , Zhenjie Zheng

This work approximates high-dimensional density functions with an ANOVA-like sparse structure by the mixture of wrapped Gaussian and von Mises distributions. When the dimension $d$ is very large, it is complex and impossible to train the…

Methodology · Statistics 2022-03-30 Fatima Antarou Ba

Overparameterization and overfitting are common concerns when designing and training deep neural networks, that are often counteracted by pruning and regularization strategies. However, these strategies remain secondary to most learning…

Machine Learning · Computer Science 2020-09-01 Malena Reiners , Kathrin Klamroth , Michael Stiglmayr

High-dimensional statistical learning (HDSL) has wide applications in data analysis, operations research, and decision-making. Despite the availability of multiple theoretical frameworks, most existing HDSL schemes stipulate the following…

Statistics Theory · Mathematics 2021-10-25 Hongcheng Liu , Yinyu Ye , Hung Yi Lee

While the SLIM approach obtained high ranking-accuracy in many experiments in the literature, it is also known for its high computational cost of learning its parameters from data. For this reason, we focus in this paper on variants of…

Information Retrieval · Computer Science 2019-05-01 Harald Steck

This work studies the problem of learning appropriate low dimensional image representations. We propose a generic algorithmic framework, which leverages two classic representation learning paradigms, i.e., sparse representation and the…

Computer Vision and Pattern Recognition · Computer Science 2018-10-09 Xian Wei , Hao Shen , Martin Kleinsteuber

In recent years, a lot of attention has been devoted to efficient nearest neighbor search by means of similarity-preserving hashing. One of the plights of existing hashing techniques is the intrinsic trade-off between performance and…

Computer Vision and Pattern Recognition · Computer Science 2014-02-18 Jonathan Masci , Alex M. Bronstein , Michael M. Bronstein , Pablo Sprechmann , Guillermo Sapiro

Deep learning usually relies on training large-scale data samples to achieve better performance. However, over-fitting based on training data always remains a problem. Scholars have proposed various strategies, such as feature dropping and…

Computer Vision and Pattern Recognition · Computer Science 2022-11-22 Songhao Jiang , Yan Chu , Tianxing Ma , Tianning Zang

Sparsity-constrained optimization is an important and challenging problem that has wide applicability in data mining, machine learning, and statistics. In this paper, we focus on sparsity-constrained optimization in cases where the cost…

Machine Learning · Computer Science 2016-12-19 Feng Chen , Baojian Zhou

Structured constraints in Machine Learning have recently brought the Frank-Wolfe (FW) family of algorithms back in the spotlight. While the classical FW algorithm has poor local convergence properties, the Away-steps and Pairwise FW…

Optimization and Control · Mathematics 2022-09-09 Fabian Pedregosa , Geoffrey Negiar , Armin Askari , Martin Jaggi

Unsupervised feature selection is an important method to reduce dimensions of high dimensional data without labels, which is benefit to avoid ``curse of dimensionality'' and improve the performance of subsequent machine learning tasks, like…

Machine Learning · Computer Science 2020-12-29 Yanyong Huang , Zongxin Shen , Fuxu Cai , Tianrui Li , Fengmao Lv

Complex data mining has wide application value in many fields, especially in the feature extraction and classification tasks of unlabeled data. This paper proposes an algorithm based on self-supervised learning and verifies its…

Machine Learning · Computer Science 2025-04-08 Yingbin Liang , Lu Dai , Shuo Shi , Minghao Dai , Junliang Du , Haige Wang

Conditional Gradient algorithms (aka Frank-Wolfe algorithms) form a classical set of methods for constrained smooth convex minimization due to their simplicity, the absence of projection steps, and competitive numerical performance. While…

Optimization and Control · Mathematics 2021-10-20 Thomas Kerdreux , Alexandre d'Aspremont , Sebastian Pokutta

Online optimization has been a successful framework for solving large-scale problems under computational constraints and partial information. Current methods for online convex optimization require either a projection or exact gradient…

Machine Learning · Statistics 2018-06-15 Lin Chen , Christopher Harshaw , Hamed Hassani , Amin Karbasi

High-dimensional measurements are often correlated which motivates their approximation by factor models. This holds also true when features are engineered via low-dimensional interactions or kernel tricks. This often results in over…

Applications · Statistics 2025-09-03 Xiaonan Zhu , Bingyan Wang , Jianqing Fan

In this paper, we study the problem of speeding up a type of optimization algorithms called Frank-Wolfe, a conditional gradient method. We develop and employ two novel inner product search data structures, improving the prior fastest…

Data Structures and Algorithms · Computer Science 2022-07-20 Zhao Song , Zhaozhuo Xu , Yuanyuan Yang , Lichen Zhang

Frank-Wolfe methods are projection-free algorithms for constrained optimization whose practical performance often depends critically on the choice of step size. Classical closed-loop step-size rules typically require prior knowledge of a…

Optimization and Control · Mathematics 2026-05-29 Khanh-Hung Giang-Tran , Soroosh Shafiee , Nam Ho-Nguyen

We study the integration and approximation problems for monotone and convex bounded functions that depend on $d$ variables, where $d$ can be arbitrarily large. We consider the worst case error for algorithms that use finitely many function…

Numerical Analysis · Mathematics 2013-12-13 Aicke Hinrichs , Erich Novak , Henryk Woźniakowski