咨询与建议

限定检索结果

文献类型

  • 18 篇 期刊文献
  • 8 篇 会议

馆藏范围

  • 26 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 18 篇 工学
    • 17 篇 计算机科学与技术...
    • 1 篇 软件工程
    • 1 篇 生物工程
  • 17 篇 理学
    • 16 篇 数学
    • 1 篇 生物学
    • 1 篇 统计学(可授理学、...
  • 1 篇 农学
    • 1 篇 作物学

主题

  • 26 篇 linear threshold...
  • 5 篇 boolean function...
  • 4 篇 halfspaces
  • 3 篇 computational le...
  • 3 篇 neural networks
  • 2 篇 fourier analysis
  • 2 篇 complexity measu...
  • 2 篇 low-degree polyn...
  • 2 篇 chow parameters
  • 2 篇 perceptron algor...
  • 2 篇 threshold circui...
  • 2 篇 complexity of le...
  • 2 篇 learning with no...
  • 2 篇 boosting
  • 2 篇 communication co...
  • 2 篇 lower bounds
  • 2 篇 property testing
  • 1 篇 mistake bounds
  • 1 篇 unate functions
  • 1 篇 tree rank

机构

  • 6 篇 columbia univ de...
  • 2 篇 univ texas austi...
  • 1 篇 ibm corp almaden...
  • 1 篇 univ wisconsin m...
  • 1 篇 vilnius univ fac...
  • 1 篇 eecs and csail
  • 1 篇 harvard univ div...
  • 1 篇 yale univ dept m...
  • 1 篇 google mountain ...
  • 1 篇 univ helsinki de...
  • 1 篇 carnegie mellon ...
  • 1 篇 duquesne univ pi...
  • 1 篇 univ calif san d...
  • 1 篇 ci homi bhabha n...
  • 1 篇 georgia inst tec...
  • 1 篇 mit elect engn &...
  • 1 篇 mit dept math ca...
  • 1 篇 mit csail cambri...
  • 1 篇 mit csail 32 vas...
  • 1 篇 carnegie mellon ...

作者

  • 5 篇 servedio rocco a...
  • 2 篇 diakonikolas ili...
  • 2 篇 o'donnell ryan
  • 2 篇 siu ky
  • 2 篇 sherstov alexand...
  • 2 篇 blais eric
  • 1 篇 sreenivasaiah ka...
  • 1 篇 mahajan meena
  • 1 篇 warmuth mk
  • 1 篇 de anindya
  • 1 篇 bruck j
  • 1 篇 rabani yuval
  • 1 篇 gershenson danie...
  • 1 篇 carmosino marco ...
  • 1 篇 vempala s
  • 1 篇 servedio ra
  • 1 篇 schober steffen
  • 1 篇 potechin aaron
  • 1 篇 kannan r
  • 1 篇 bun mark

语言

  • 23 篇 英文
  • 3 篇 其他
检索条件"主题词=linear threshold functions"
26 条 记 录,以下是1-10 订阅
排序:
linear threshold functions in decision lists, decision trees, and depth-2 circuits
收藏 引用
INFORMATION PROCESSING LETTERS 2024年 183卷
作者: Dahiya, Yogesh Vignesh, K. Mahajan, Meena Sreenivasaiah, Karteek CI Homi Bhabha Natl Inst Inst Math Sci CIT Campus Chennai 600113 Tamil Nadu India Indian Inst Technol Hyderabad Hyderabad 502285 Telangana India
We show that polynomial-size constant-rank linear decision trees (LDTs) can be converted to polynomial-size depth-2 threshold circuits LTF o LTF. An intermediate construct is polynomial-size decision lists that query ... 详细信息
来源: 评论
Monotone Boolean formulas can approximate monotone linear threshold functions
收藏 引用
DISCRETE APPLIED MATHEMATICS 2004年 第1-3期142卷 181-187页
作者: Servedio, RA Columbia Univ Dept Comp Sci New York NY 10027 USA
We show that any monotone linear threshold function on n Boolean variables can be approximated to within any constant accuracy by a monotone Boolean formula of poly(n) size. (C) 2004 Elsevier B.V. All rights reserved.
来源: 评论
A polynomial-time algorithm for learning noisy linear threshold functions
收藏 引用
ALGORITHMICA 1998年 第1-2期22卷 35-52页
作者: Blum, A Frieze, A Kannan, R Vempala, S Carnegie Mellon Univ Sch Comp Sci Pittsburgh PA 15213 USA Carnegie Mellon Univ Dept Math Sci Pittsburgh PA 15213 USA
In this paper we consider the problem of learning a linear threshold function (a half-space in n dimensions, also called a "perceptron"). Methods for solving this problem generally fall into two categories. ... 详细信息
来源: 评论
On the Approximation Resistance of Balanced linear threshold functions  2019
On the Approximation Resistance of Balanced Linear Threshold...
收藏 引用
51st Annual ACM SIGACT Symposium on Theory of Computing (STOC)
作者: Potechin, Aaron Univ Chicago Chicago IL 60637 USA
In this paper, we show that there exists a balanced linear threshold function (LTF) which is unique games hard to approximate, refuting a conjecture of Austrin, Benabbas, and Magen. We also show that the almost monarc... 详细信息
来源: 评论
Polynomial regression under arbitrary product distributions
收藏 引用
MACHINE LEARNING 2010年 第2-3期80卷 273-294页
作者: Blais, Eric O'Donnell, Ryan Wimmer, Karl Carnegie Mellon Univ Pittsburgh PA 15213 USA Duquesne Univ Pittsburgh PA 15219 USA
In recent work, Kalai, Klivans, Mansour, and Servedio (2005) studied a variant of the "Low-Degree (Fourier) Algorithm" for learning under the uniform probability distribution on {0, 1}(n). They showed that t... 详细信息
来源: 评论
EXPLICIT DIMENSION REDUCTION AND ITS APPLICATIONS
收藏 引用
SIAM JOURNAL ON COMPUTING 2012年 第1期41卷 219-249页
作者: Karnin, Zohar S. Rabani, Yuval Shpilka, Amir Technion Israel Inst Technol Fac Comp Sci IL-32000 Haifa Israel Hebrew Univ Jerusalem Rachel & Selim Benin Sch Comp Sci & Engn IL-91904 Jerusalem Israel Microsoft Res Cambridge MA 02142 USA
We construct a small set of explicit linear transformations mapping R-n to R-t, where t = O(log(gamma(-1))epsilon(-2)), such that the L-2 norm of any vector in R-n is distorted by at most 1 +/- epsilon in at least a f... 详细信息
来源: 评论
A ROBUST KHINTCHINE INEQUALITY, AND ALGORITHMS FOR COMPUTING OPTIMAL CONSTANTS IN FOURIER ANALYSIS AND HIGH-DIMENSIONAL GEOMETRY
收藏 引用
SIAM JOURNAL ON DISCRETE MATHEMATICS 2016年 第2期30卷 1058-1094页
作者: De, Anindya Diakonikolas, Ilias Servedio, Rocco A. Univ Calif Berkeley Berkeley CA 94720 USA Univ Edinburgh Edinburgh EH8 9YL Midlothian Scotland Columbia Univ Dept Comp Sci New York NY 10027 USA
This paper makes two contributions towards determining some well-studied optimal constants in Fourier analysis of Boolean functions and high-dimensional geometry. It has been known since 1994 [C. Gotsman and N. Linial... 详细信息
来源: 评论
PAC analogues of perceptron and winnow via boosting the margin
收藏 引用
MACHINE LEARNING 2002年 第2-3期47卷 133-151页
作者: Servedio, R Harvard Univ Div Engn & Appl Sci Cambridge MA 02138 USA
We describe a novel family of PAC model algorithms for learning linear threshold functions. The new algorithms work by boosting a simple weak learner and exhibit sample complexity bounds remarkably similar to those of... 详细信息
来源: 评论
ON THE WEIGHT OF HALFSPACES OVER HAMMING BALLS
收藏 引用
SIAM JOURNAL ON DISCRETE MATHEMATICS 2014年 第3期28卷 1035-1061页
作者: Long, Philip M. Servedio, Rocco A. Google Mountain View CA 94043 USA Columbia Univ Dept Comp Sci New York NY 10027 USA
For S subset of {0, 1}(n), a Boolean function f : S -> {-1, 1} is a halfspace over S if there exist w is an element of R-n and theta is an element of R such that f(x) = sign(w . x - theta) for all x is an element o... 详细信息
来源: 评论
The Perceptron algorithm versus Winnow: linear versus logarithmic mistake bounds when few input variables are relevant
收藏 引用
ARTIFICIAL INTELLIGENCE 1997年 第1-2期97卷 325-343页
作者: Kivinen, J Warmuth, MK Auer, P Graz Univ Technol Inst Theoret Comp Sci A-8010 Graz Austria Univ Helsinki Dept Comp Sci FIN-00014 Helsinki Finland Univ Calif Santa Cruz Santa Cruz CA 95064 USA
We give an adversary strategy that forces the Perceptron algorithm to make Omega(kN) mistakes in learning monotone disjunctions over N variables with at most k literals. In contrast, Littlestone's algorithm Winnow... 详细信息
来源: 评论