中文
相关论文

相关论文: Fitting Unknown Number of Hyperplanes with Manifol…

200 篇论文

This work is on constrained large-scale non-convex optimization where the constraint set implies a manifold structure. Solving such problems is important in a multitude of fundamental machine learning tasks. Recent advances on Riemannian…

机器学习 · 计算机科学 2023-02-23 Yian Deng , Tingting Mu

Likelihood-based, or explicit, deep generative models use neural networks to construct flexible high-dimensional densities. This formulation directly contradicts the manifold hypothesis, which states that observed data lies on a…

Bilevel optimization is a central tool in machine learning for high-dimensional hyperparameter tuning. Its applications are vast; for instance, in imaging it can be used for learning data-adaptive regularizers and optimizing forward…

最优化与控制 · 数学 2025-11-11 Mohammad Sadegh Salehi , Subhadip Mukherjee , Lindon Roberts , Matthias J. Ehrhardt

Riemannian optimization is a principled framework for solving optimization problems where the desired optimum is constrained to a smooth manifold $\mathcal{M}$. Algorithms designed in this framework usually require some geometrical…

最优化与控制 · 数学 2022-09-08 Boris Shustin , Haim Avron , Barak Sober

We introduce a novel framework that directly learns a spectral basis for shape and manifold analysis from unstructured data, eliminating the need for traditional operator selection, discretization, and eigensolvers. Grounded in…

计算机视觉与模式识别 · 计算机科学 2025-12-02 Roy Velich , Arkadi Piven , David Bensaïd , Daniel Cremers , Thomas Dagès , Ron Kimmel

Bilevel optimization has been developed for many machine learning tasks with large-scale and high-dimensional data. This paper considers a constrained bilevel optimization problem, where the lower-level optimization problem is convex with…

机器学习 · 计算机科学 2023-08-22 Siyuan Xu , Minghui Zhu

We introduce a machine-learning framework to learn the hyperparameter sequence of first-order methods (e.g., the step sizes in gradient descent) to quickly solve parametric convex optimization problems. Our computational architecture…

最优化与控制 · 数学 2024-12-23 Rajiv Sambharya , Bartolomeo Stellato

We study optimization problems on Hadamard manifolds, motivated by recent advances in geometric approaches to optimization on curved spaces, particularly those involving the structure of Busemann functions. We introduce a projection based…

最优化与控制 · 数学 2026-03-03 R. Díaz Millán , O. P. Ferreira , M. S. Louzeiro , J. Ugon

We consider the problem of classifying data manifolds where each manifold represents invariances that are parameterized by continuous degrees of freedom. Conventional data augmentation methods rely upon sampling large numbers of training…

机器学习 · 计算机科学 2018-10-01 SueYeon Chung , Uri Cohen , Haim Sompolinsky , Daniel D. Lee

We propose a new randomized optimization method for high-dimensional problems which can be seen as a generalization of coordinate descent to random subspaces. We show that an adaptive sampling strategy for the random subspace significantly…

最优化与控制 · 数学 2019-12-19 Jonathan Lacotte , Mert Pilanci , Marco Pavone

In this paper, we present a method for denoising and reconstruction of low-dimensional manifold in high-dimensional space. We suggest a multidimensional extension of the Locally Optimal Projection algorithm which was introduced by Lipman et…

数值分析 · 数学 2022-11-17 Shira Faigenbaum-Golovin , David Levin

Uncertain dynamic obstacles, such as pedestrians or vehicles, pose a major challenge for optimal robot navigation with safety guarantees. Previous work on motion planning has followed two main strategies to provide a safe bound on an…

This paper proposes novel algorithm for non-convex multimodal constrained optimisation problems. It is based on sequential solving restrictions of problem to sections of feasible set by random subspaces (in general, manifolds) of low…

最优化与控制 · 数学 2023-03-28 Dmitry A. Pasechnyuk , Alexander Gornov

We study the sample complexity of stochastic convex optimization when problem parameters, e.g., the distance to optimality, are unknown. We pursue two strategies. First, we develop a reliable model selection method that avoids overfitting…

机器学习 · 计算机科学 2025-06-16 Jared Lawrence , Ari Kalinsky , Hannah Bradfield , Yair Carmon , Oliver Hinder

We introduce a framework based on bilevel programming that unifies gradient-based hyperparameter optimization and meta-learning. We show that an approximate version of the bilevel problem can be solved by taking into explicit account the…

机器学习 · 统计学 2018-07-04 Luca Franceschi , Paolo Frasconi , Saverio Salzo , Riccardo Grazzi , Massimilano Pontil

This paper presents a novel method for reformulating non-differentiable collision avoidance constraints into smooth nonlinear constraints using strong duality of convex optimization. We focus on a controlled object whose goal is to avoid…

最优化与控制 · 数学 2018-06-12 Xiaojing Zhang , Alexander Liniger , Francesco Borrelli

We consider the problem of simultaneously clustering and learning a linear representation of data lying close to a union of low-dimensional manifolds, a fundamental task in machine learning and computer vision. When the manifolds are…

机器学习 · 计算机科学 2023-08-25 Tianjiao Ding , Shengbang Tong , Kwan Ho Ryan Chan , Xili Dai , Yi Ma , Benjamin D. Haeffele

Nonlinear dimensionality reduction methods provide a valuable means to visualize and interpret high-dimensional data. However, many popular methods can fail dramatically, even on simple two-dimensional manifolds, due to problems such as…

机器学习 · 统计学 2020-07-08 Daniel Ting , Michael I. Jordan

Hyperspherical Prototypical Learning (HPL) is a supervised approach to representation learning that designs class prototypes on the unit hypersphere. The prototypes bias the representations to class separation in a scale invariant and known…

机器学习 · 计算机科学 2025-04-18 Martin Lindström , Borja Rodríguez-Gálvez , Ragnar Thobaben , Mikael Skoglund

We present a path planning framework that takes into account the human's safety perception in the presence of a flying robot. The framework addresses two objectives: (i) estimation of the uncertain parameters of the proposed safety…

机器人学 · 计算机科学 2019-03-14 Hyung-Jin Yoon , Christopher Widdowson , Thiago Marinho , Ranxiao Frances Wang , Naira Hovakimyan