中文
相关论文

相关论文: A general learning algorithm for functions between…

200 篇论文

We initiate a program of average smoothness analysis for efficiently learning real-valued functions on metric spaces. Rather than using the Lipschitz constant as the regularizer, we define a local slope at each point and gauge the function…

统计理论 · 数学 2020-11-10 Yair Ashlagi , Lee-Ad Gottlieb , Aryeh Kontorovich

The key issue of few-shot learning is learning to generalize. This paper proposes a large margin principle to improve the generalization capacity of metric based methods for few-shot learning. To realize it, we develop a unified framework…

机器学习 · 计算机科学 2018-09-24 Yong Wang , Xiao-Ming Wu , Qimai Li , Jiatao Gu , Wangmeng Xiang , Lei Zhang , Victor O. K. Li

Let X and Y be separable metrizable spaces, and f:X-->Y be a function. We want to recover f from its values on a small set via a simple algorithm. We show that this is possible if f is Baire class one, and in fact we get a characterization.…

逻辑 · 数学 2007-10-02 Dominique Lecomte

A number of machine learning algorithms are using a metric, or a distance, in order to compare individuals. The Euclidean distance is usually employed, but it may be more efficient to learn a parametric distance such as Mahalanobis metric.…

机器学习 · 计算机科学 2016-12-16 Hoel Le Capitaine

It is often useful to compactly summarize important properties of model parameters and training data so that they can be used later without storing and/or iterating over the entire dataset. As a specific case, we consider estimating the…

机器学习 · 计算机科学 2023-05-30 Nikita Dhawan , Sicong Huang , Juhan Bae , Roger Grosse

We calculate the least upper bounds for approximations in the metric of the space $L_2$ by linear methods of summation of Fourier series on classes of periodic functions $L^\psi_{\bar\beta,1}$ defined by sequences of multipliers…

经典分析与常微分方程 · 数学 2013-03-07 A. S. Serdyuk , I. V. Sokolenko

Given a finite number of samples of a continuous set-valued function F, mapping an interval to non-empty compact subsets of $\mathbb{R}^d$, $F: [a,b] \to K(\mathbb{R}^d)$, we discuss the problem of computing good approximations of F. We…

数值分析 · 数学 2025-01-27 Nira Dyn , David Levin

When using images to locate objects, there is the problem of correcting for distortion and misalignment in the images. An elegant way of solving this problem is to generate an error correcting function that maps points in an image to their…

计算机视觉与模式识别 · 计算机科学 2009-04-28 Christopher O. Ward

A challenging problem in many modern machine learning tasks is to process weight-space features, i.e., to transform or extract information from the weights and gradients of a neural network. Recent works have developed promising…

机器学习 · 计算机科学 2024-02-09 Allan Zhou , Chelsea Finn , James Harrison

Deep metric learning (DML) is a cornerstone of many computer vision applications. It aims at learning a mapping from the input domain to an embedding space, where semantically similar objects are located nearby and dissimilar objects far…

计算机视觉与模式识别 · 计算机科学 2021-09-10 Artsiom Sanakoyeu , Pingchuan Ma , Vadim Tschernezki , Björn Ommer

A very popular model in machine learning is the feedforward neural network (FFN). The FFN can approximate general functions and mitigate the curse of dimensionality. Here we introduce FFNs which represent sections of holomorphic line…

复变函数 · 数学 2021-05-11 Michael R. Douglas

The goal of subspace learning is to find a $k$-dimensional subspace of $\mathbb{R}^d$, such that the expected squared distance between instance vectors and the subspace is as small as possible. In this paper we study subspace learning in a…

机器学习 · 计算机科学 2016-05-27 Alon Gonen , Dan Rosenbaum , Yonina Eldar , Shai Shalev-Shwartz

We study approximation by arbitrary linear combinations of $n$ translates of a single function of periodic functions. We construct some methods of this approximation for functions in a class induced by the convolution with a given function,…

数值分析 · 数学 2017-03-01 Dinh Dũng , Charles A. Micchelli , Vu Nhat Huy

In this paper we discuss approximation of partially smooth functions. The problem arises naturally in the study of laminated currents.

动力系统 · 数学 2015-06-26 John Fornaess , Yinxia Wang , Erlend Fornaess Wold

We consider a generalization of a functional equation that models the learning process in various animal species. The equation can be considered nonlocal, as it is built with a convex combination of the unknown function evaluated at mixed…

Methods have previously been developed for the approximation of Lyapunov functions using radial basis functions. However these methods assume that the evolution equations are known. We consider the problem of approximating a given Lyapunov…

动力系统 · 数学 2016-01-08 Peter Giesl , Boumediene Hamzi , Martin Rasmussen , Kevin N. Webster

We consider approximations of a continuous function on a countable normed Fr\'{e}chet space by analytic and $*$-analytic. Also we found a criterium of the existence of an extension of a continuous function from a dense subspace of a…

泛函分析 · 数学 2015-05-01 M. A. Mytrofanov , A. V. Ravsky

Inspired by recent strides in empirical efficacy of implicit learning in many robotics tasks, we seek to understand the theoretical benefits of implicit formulations in the face of nearly discontinuous functions, common characteristics for…

机器人学 · 计算机科学 2022-04-08 Bibit Bianchini , Mathew Halm , Nikolai Matni , Michael Posa

We investigate a relations of almost isometric embedding and almost isometry between metric spaces and prove that with respect to these relations: (1) There is a countable universal metric space. (2) There may exist fewer than continuum…

逻辑 · 数学 2007-05-23 Menachem Kojman , Saharon Shelah

We investigate the classes of functions whose minimization diagrams can be approximated efficiently in \Re^d. We present a general framework and a data-structure that can be used to approximate the minimization diagram of such functions.…

计算几何 · 计算机科学 2013-04-03 Sariel Har-Peled , Nirman Kumar