kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Investigation of Information-Theoretic Bounds on Generalization Error
KTH, School of Electrical Engineering and Computer Science (EECS).
KTH, School of Electrical Engineering and Computer Science (EECS).
2022 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

Generalization error describes how well a supervised machine learning algorithm predicts the labels of input data that it has not been trained with. This project aims to explore two different methods for bounding generalization error, f-CMI and ISMI, which explicitly use mutual information. Our experiments are based on the experiments in the papers in which the methods were proposed. The experiments implement and validate the accuracy of the mathematically derived bounds. Each methodology also has a different method for calculating mutual information. The ISMI bound experiment used a multivariate normal distribution dataset, whereas a dataset consisting of cats and dogs was used for the experiment using f-CMI. Our results show that both methods are capable of bounding the generalization error of a binary classification algorithm and provide bounds that closely follow the true generalization error. The results of the experiments agree with the original experiments, indicating that the proposed methods also work for similar applications with different datasets.

Abstract [sv]

Generaliseringsfel beskriver hur väl en övervakad maskininlärnings algoritm förutspår etiketter av indata som den inte har blivit tränad med. Syftet med projektet är att utforska två olika metoder för att begränsa generaliseringsfelet, f-CMI och ISMI som explicit använder ömsesidig information. Vårt experiment är baserat på experimenten i artiklarna som tog fram metoderna. Experimenten implementerade och validerade noggrannheten av de matematiskt härleda gränserna. Varje metod har olika sätt att beräkna den ömsesidiga informationen. ISMI gräns experimentet använde en flerdimensionell normalfördelning som data set, medan en datauppsättning med katter och hundar användes för f-CMI gränsen. Våra resultat visar att båda metoder kan begränsa generaliseringsfelet av en binär klassificerings algoritm och förse gränser som nära följer det sanna generaliseringsfelet. Resultatet av experimenten instämmer med de ursprungliga författarnas experiment vilket indikerar att de föreslagna metoderna också fungerar for liknande tillämpningar med andra data set.

Place, publisher, year, edition, pages
2022. , p. 557-563
Series
TRITA-EECS-EX ; 2022:171
Keywords [en]
Generalization error, ISMI, functional conditional mutual information, Generalization bound
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
URN: urn:nbn:se:kth:diva-323728OAI: oai:DiVA.org:kth-323728DiVA, id: diva2:1736009
Supervisors
Examiners
Projects
Kandidatexjobb i elektroteknik 2022, KTH, StockholmAvailable from: 2023-02-10 Created: 2023-02-10

Open Access in DiVA

fulltext(146281 kB)517 downloads
File information
File name FULLTEXT01.pdfFile size 146281 kBChecksum SHA-512
6ef8ac5f57bfa731be6b63752e35a8ad576eee3fa90434c6241186b62dff01f689b0a22454b6d600dd2dfa06cfe9b879bd9a8193673765e6a41ac9b51260faf0
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Electrical Engineering, Electronic Engineering, Information Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 517 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 466 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf