Theory-Practice Interplay in Machine Learning – Emerging Theoretical Challenges View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2009

AUTHORS

Shai Ben-David

ABSTRACT

Theoretical analysis has played a major role in some of the most prominent practical successes of statistical machine learning. However, mainstream machine learning theory assumes some strong simplifying assumptions which are often unrealistic. In the past decade, the practice of machine learning has led to the development of various heuristic paradigms that answer the needs of a vastly growing range of applications. Many useful such paradigms fall beyond the scope of the currently available analysis. Will theory play a similar pivotal role in the newly emerging sub areas of machine learning? In this talk, I will survey some such application-motivated theoretical challenges. In particular, I will discuss recent developments in the theoretical analysis of semi-supervised learning, multi-task learning, “learning to learn”, privacy-preserving learning and more. More... »

PAGES

1-1

Book

TITLE

Machine Learning and Knowledge Discovery in Databases

ISBN

978-3-642-04179-2
978-3-642-04180-8

Author Affiliations

Identifiers

URI

http://scigraph.springernature.com/pub.10.1007/978-3-642-04180-8_1

DOI

http://dx.doi.org/10.1007/978-3-642-04180-8_1

DIMENSIONS

https://app.dimensions.ai/details/publication/pub.1002529006


Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
Incoming Citations Browse incoming citations for this publication using opencitations.net

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Artificial Intelligence and Image Processing", 
        "type": "DefinedTerm"
      }, 
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/08", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "name": "Information and Computing Sciences", 
        "type": "DefinedTerm"
      }
    ], 
    "author": [
      {
        "affiliation": {
          "alternateName": "University of Waterloo", 
          "id": "https://www.grid.ac/institutes/grid.46078.3d", 
          "name": [
            "University of Waterloo, Canada"
          ], 
          "type": "Organization"
        }, 
        "familyName": "Ben-David", 
        "givenName": "Shai", 
        "id": "sg:person.014114404075.46", 
        "sameAs": [
          "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014114404075.46"
        ], 
        "type": "Person"
      }
    ], 
    "datePublished": "2009", 
    "datePublishedReg": "2009-01-01", 
    "description": "Theoretical analysis has played a major role in some of the most prominent practical successes of statistical machine learning. However, mainstream machine learning theory assumes some strong simplifying assumptions which are often unrealistic. In the past decade, the practice of machine learning has led to the development of various heuristic paradigms that answer the needs of a vastly growing range of applications. Many useful such paradigms fall beyond the scope of the currently available analysis. Will theory play a similar pivotal role in the newly emerging sub areas of machine learning? In this talk, I will survey some such application-motivated theoretical challenges. In particular, I will discuss recent developments in the theoretical analysis of semi-supervised learning, multi-task learning, \u201clearning to learn\u201d, privacy-preserving learning and more.", 
    "editor": [
      {
        "familyName": "Buntine", 
        "givenName": "Wray", 
        "type": "Person"
      }, 
      {
        "familyName": "Grobelnik", 
        "givenName": "Marko", 
        "type": "Person"
      }, 
      {
        "familyName": "Mladeni\u0107", 
        "givenName": "Dunja", 
        "type": "Person"
      }, 
      {
        "familyName": "Shawe-Taylor", 
        "givenName": "John", 
        "type": "Person"
      }
    ], 
    "genre": "chapter", 
    "id": "sg:pub.10.1007/978-3-642-04180-8_1", 
    "inLanguage": [
      "en"
    ], 
    "isAccessibleForFree": true, 
    "isPartOf": {
      "isbn": [
        "978-3-642-04179-2", 
        "978-3-642-04180-8"
      ], 
      "name": "Machine Learning and Knowledge Discovery in Databases", 
      "type": "Book"
    }, 
    "name": "Theory-Practice Interplay in Machine Learning \u2013 Emerging Theoretical Challenges", 
    "pagination": "1-1", 
    "productId": [
      {
        "name": "doi", 
        "type": "PropertyValue", 
        "value": [
          "10.1007/978-3-642-04180-8_1"
        ]
      }, 
      {
        "name": "readcube_id", 
        "type": "PropertyValue", 
        "value": [
          "0c0a97e5a66c64bc508acdd31fef2222aa1dedc8ee29d3415ee8e2bab70999d9"
        ]
      }, 
      {
        "name": "dimensions_id", 
        "type": "PropertyValue", 
        "value": [
          "pub.1002529006"
        ]
      }
    ], 
    "publisher": {
      "location": "Berlin, Heidelberg", 
      "name": "Springer Berlin Heidelberg", 
      "type": "Organisation"
    }, 
    "sameAs": [
      "https://doi.org/10.1007/978-3-642-04180-8_1", 
      "https://app.dimensions.ai/details/publication/pub.1002529006"
    ], 
    "sdDataset": "chapters", 
    "sdDatePublished": "2019-04-15T20:46", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000001_0000000264/records_8690_00000004.jsonl", 
    "type": "Chapter", 
    "url": "http://link.springer.com/10.1007/978-3-642-04180-8_1"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-04180-8_1'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-04180-8_1'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-04180-8_1'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-642-04180-8_1'


 

This table displays all metadata directly associated to this object as RDF triples.

80 TRIPLES      22 PREDICATES      27 URIs      20 LITERALS      8 BLANK NODES

Subject Predicate Object
1 sg:pub.10.1007/978-3-642-04180-8_1 schema:about anzsrc-for:08
2 anzsrc-for:0801
3 schema:author Nc8059b5755f749328bdffc42c8cae91d
4 schema:datePublished 2009
5 schema:datePublishedReg 2009-01-01
6 schema:description Theoretical analysis has played a major role in some of the most prominent practical successes of statistical machine learning. However, mainstream machine learning theory assumes some strong simplifying assumptions which are often unrealistic. In the past decade, the practice of machine learning has led to the development of various heuristic paradigms that answer the needs of a vastly growing range of applications. Many useful such paradigms fall beyond the scope of the currently available analysis. Will theory play a similar pivotal role in the newly emerging sub areas of machine learning? In this talk, I will survey some such application-motivated theoretical challenges. In particular, I will discuss recent developments in the theoretical analysis of semi-supervised learning, multi-task learning, “learning to learn”, privacy-preserving learning and more.
7 schema:editor Nf5f4e4bc5d0a4087b3639a3560a2f725
8 schema:genre chapter
9 schema:inLanguage en
10 schema:isAccessibleForFree true
11 schema:isPartOf N6d7334c2dc8b4b9099c254d5a5a71d74
12 schema:name Theory-Practice Interplay in Machine Learning – Emerging Theoretical Challenges
13 schema:pagination 1-1
14 schema:productId N55aa33c516b743cf8cb16c1a8cece189
15 N9732434983d942189fa6f9c84c59650d
16 Nbc7562e4d6ac4fc8941a5d5488b3fca8
17 schema:publisher N9c4aaf3072d24536bd02be133d22dccf
18 schema:sameAs https://app.dimensions.ai/details/publication/pub.1002529006
19 https://doi.org/10.1007/978-3-642-04180-8_1
20 schema:sdDatePublished 2019-04-15T20:46
21 schema:sdLicense https://scigraph.springernature.com/explorer/license/
22 schema:sdPublisher Nae82a93e1eb64acab140ee3ac2111c41
23 schema:url http://link.springer.com/10.1007/978-3-642-04180-8_1
24 sgo:license sg:explorer/license/
25 sgo:sdDataset chapters
26 rdf:type schema:Chapter
27 N11a272f5822445858f881bebee366430 rdf:first Ne99ea227a29546a9b0d0010cc4d54eca
28 rdf:rest rdf:nil
29 N55aa33c516b743cf8cb16c1a8cece189 schema:name doi
30 schema:value 10.1007/978-3-642-04180-8_1
31 rdf:type schema:PropertyValue
32 N5cb947261ca64201879a610c646e4365 schema:familyName Grobelnik
33 schema:givenName Marko
34 rdf:type schema:Person
35 N6d7334c2dc8b4b9099c254d5a5a71d74 schema:isbn 978-3-642-04179-2
36 978-3-642-04180-8
37 schema:name Machine Learning and Knowledge Discovery in Databases
38 rdf:type schema:Book
39 N7a7a1802999d41b3bf0275f3185a3ba0 schema:familyName Mladenić
40 schema:givenName Dunja
41 rdf:type schema:Person
42 N8709e15b50594c3f99c237b542af1c97 schema:familyName Buntine
43 schema:givenName Wray
44 rdf:type schema:Person
45 N8e5c604092744ca6961c35e09acda333 rdf:first N7a7a1802999d41b3bf0275f3185a3ba0
46 rdf:rest N11a272f5822445858f881bebee366430
47 N9732434983d942189fa6f9c84c59650d schema:name readcube_id
48 schema:value 0c0a97e5a66c64bc508acdd31fef2222aa1dedc8ee29d3415ee8e2bab70999d9
49 rdf:type schema:PropertyValue
50 N9c4aaf3072d24536bd02be133d22dccf schema:location Berlin, Heidelberg
51 schema:name Springer Berlin Heidelberg
52 rdf:type schema:Organisation
53 Nae82a93e1eb64acab140ee3ac2111c41 schema:name Springer Nature - SN SciGraph project
54 rdf:type schema:Organization
55 Nbc7562e4d6ac4fc8941a5d5488b3fca8 schema:name dimensions_id
56 schema:value pub.1002529006
57 rdf:type schema:PropertyValue
58 Nc8059b5755f749328bdffc42c8cae91d rdf:first sg:person.014114404075.46
59 rdf:rest rdf:nil
60 Ne99ea227a29546a9b0d0010cc4d54eca schema:familyName Shawe-Taylor
61 schema:givenName John
62 rdf:type schema:Person
63 Nf5f4e4bc5d0a4087b3639a3560a2f725 rdf:first N8709e15b50594c3f99c237b542af1c97
64 rdf:rest Nfc83c388fc354a0981304f5c1cab3675
65 Nfc83c388fc354a0981304f5c1cab3675 rdf:first N5cb947261ca64201879a610c646e4365
66 rdf:rest N8e5c604092744ca6961c35e09acda333
67 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
68 schema:name Information and Computing Sciences
69 rdf:type schema:DefinedTerm
70 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
71 schema:name Artificial Intelligence and Image Processing
72 rdf:type schema:DefinedTerm
73 sg:person.014114404075.46 schema:affiliation https://www.grid.ac/institutes/grid.46078.3d
74 schema:familyName Ben-David
75 schema:givenName Shai
76 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014114404075.46
77 rdf:type schema:Person
78 https://www.grid.ac/institutes/grid.46078.3d schema:alternateName University of Waterloo
79 schema:name University of Waterloo, Canada
80 rdf:type schema:Organization
 




Preview window. Press ESC to close (or click here)


...