Generalization error

Results: 82



#Item
1A Comparison of Tight Generalization Error Bounds  Matti K¨ a¨ ari¨ ainen

A Comparison of Tight Generalization Error Bounds Matti K¨ a¨ ari¨ ainen

Add to Reading List

Source URL: hunch.net

Language: English - Date: 2005-06-01 23:11:48
    2Margin-based Generalization Error Bounds for Threshold Decision Lists Martin Anthony Department of Mathematics and Centre for Discrete and Applicable Mathematics London School of Economics

    Margin-based Generalization Error Bounds for Threshold Decision Lists Martin Anthony Department of Mathematics and Centre for Discrete and Applicable Mathematics London School of Economics

    Add to Reading List

    Source URL: www.cdam.lse.ac.uk

    Language: English - Date: 2017-04-12 10:30:30
      3We show that any model trained by a stochastic gradient method with few iterations has vanishing generalization error. We prove this by showing the method is algorithmically stable in the sense of Bousquet and Elisseeff.

      We show that any model trained by a stochastic gradient method with few iterations has vanishing generalization error. We prove this by showing the method is algorithmically stable in the sense of Bousquet and Elisseeff.

      Add to Reading List

      Source URL: mmds-data.org

      - Date: 2016-06-23 15:50:48
        4Generalization Error Bounds for the Logical Analysis of Data Martin Anthony Department of Mathematics, The London School of Economics and Political Science, Houghton Street, London WC2A2AE, U.K.

        Generalization Error Bounds for the Logical Analysis of Data Martin Anthony Department of Mathematics, The London School of Economics and Political Science, Houghton Street, London WC2A2AE, U.K.

        Add to Reading List

        Source URL: www.maths.lse.ac.uk

        - Date: 2013-01-25 06:10:29
          5A Few Useful Things to Know about Machine Learning Pedro Domingos Department of Computer Science and Engineering University of Washington Seattle, WA, U.S.A.

          A Few Useful Things to Know about Machine Learning Pedro Domingos Department of Computer Science and Engineering University of Washington Seattle, WA, U.S.A.

          Add to Reading List

          Source URL: homes.cs.washington.edu

          Language: English - Date: 2015-08-13 22:08:12
          6Optimal Gradient-Based Learning Using Importance Weights Sepp Hochreiter and Klaus Obermayer Bernstein Center for Computational Neuroscience and Technische Universit¨at Berlin

          Optimal Gradient-Based Learning Using Importance Weights Sepp Hochreiter and Klaus Obermayer Bernstein Center for Computational Neuroscience and Technische Universit¨at Berlin

          Add to Reading List

          Source URL: www.bioinf.jku.at

          Language: English - Date: 2013-01-23 02:39:45
          7Cross-validation for binary classification by real-valued functions: theoretical analysis Martin Anthony Department of Mathematics London School of Economics Houghton Street

          Cross-validation for binary classification by real-valued functions: theoretical analysis Martin Anthony Department of Mathematics London School of Economics Houghton Street

          Add to Reading List

          Source URL: www.maths.lse.ac.uk

          Language: English - Date: 2000-04-03 14:24:41
          8Towards Anytime Active Learning: Interrupting Experts to Reduce Annotation Costs Maria E. Ramirez-Loaiza   Aron Culotta

          Towards Anytime Active Learning: Interrupting Experts to Reduce Annotation Costs Maria E. Ramirez-Loaiza Aron Culotta

          Add to Reading List

          Source URL: poloclub.gatech.edu

          Language: English - Date: 2013-07-08 06:03:55
          9Machine learning techniques available in pRoloc Laurent Gatto∗ June 14, 2016 Contents 1 Introduction

          Machine learning techniques available in pRoloc Laurent Gatto∗ June 14, 2016 Contents 1 Introduction

          Add to Reading List

          Source URL: www.bioconductor.org

          Language: English - Date: 2016-06-14 23:40:44
          10Semi-Supervised Learning with Adversarially Missing Label Information Umar Syed Ben Taskar Department of Computer and Information Science

          Semi-Supervised Learning with Adversarially Missing Label Information Umar Syed Ben Taskar Department of Computer and Information Science

          Add to Reading List

          Source URL: www.seas.upenn.edu

          Language: English - Date: 2010-11-04 10:51:45