Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Quantifying Uncertainty in Online Regression Forests
KTH, Skolan för elektroteknik och datavetenskap (EECS), Datavetenskap, Beräkningsvetenskap och beräkningsteknik (CST). RISE.ORCID-id: 0000-0002-8180-7521
ISI Foundation.
KTH, Skolan för elektroteknik och datavetenskap (EECS), Datavetenskap, Programvaruteknik och datorsystem, SCS.ORCID-id: 0000-0001-8382-0300
(engelsk)Manuskript (preprint) (Annet vitenskapelig)
Abstract [en]

Accurately quantifying uncertainty in predictions is essential for the deployment of machine learning algorithms in critical applications where mistakes are costly. Most approaches to quantifying prediction uncertainty have focused on settings where the data is static, or bounded. In this paper, we investigate methods that quantify the prediction uncertainty in a streaming setting, where the data is potentially unbounded.

We propose two meta-algorithms that produce prediction intervals for online regression forests of arbitrary tree models; one based on conformal prediction theory, and the other based on quantile regression. We show that the approaches are able to maintain specified error rates, with constant computational cost per example and bounded memory usage. We provide empirical evidence that the methods outperform the state-of-the-art in terms of maintaining error guarantees, while being an order of magnitude faster. We also investigate how the algorithms are able to recover from concept drift.

Emneord [en]
Online learning, Uncertainty, Decision Trees, Regression
HSV kategori
Identifikatorer
URN: urn:nbn:se:kth:diva-250039OAI: oai:DiVA.org:kth-250039DiVA, id: diva2:1307121
Forskningsfinansiär
Swedish Foundation for Strategic Research , BD15-0006
Merknad

QC 20190426

Tilgjengelig fra: 2019-04-25 Laget: 2019-04-25 Sist oppdatert: 2022-12-12bibliografisk kontrollert
Inngår i avhandling
1. Scalable Machine Learning through Approximation and Distributed Computing
Åpne denne publikasjonen i ny fane eller vindu >>Scalable Machine Learning through Approximation and Distributed Computing
2019 (engelsk)Doktoravhandling, med artikler (Annet vitenskapelig)
Abstract [en]

Machine learning algorithms are now being deployed in practically all areas of our lives. Part of this success can be attributed to the ability to learn complex representations from massive datasets. However, computational speed increases have not kept up with the increase in the sizes of data we want to learn from, leading naturally to algorithms that need to be resource-efficient and parallel. As the proliferation of machine learning continues, the ability for algorithms to adapt to a changing environment and deal with uncertainty becomes increasingly important.

In this thesis we develop scalable machine learning algorithms, with a focus on efficient, online, and distributed computation. We make use of approximations to dramatically reduce the computational cost of exact algorithms, and develop online learning algorithms to deal with a constantly changing environment under a tight computational budget. We design parallel and distributed algorithms to ensure that our methods can scale to massive datasets.

We first propose a scalable algorithm for graph vertex similarity calculation and concept discovery. We demonstrate its applicability to multiple domains, including text, music, and images, and demonstrate its scalability by training on one of the largest text corpora available. Then, motivated by a real-world use case of predicting the session length in media streaming, we propose improvements to several aspects of learning with decision trees. We propose two algorithms to estimate the uncertainty in the predictions of online random forests. We show that our approach can achieve better accuracy than the state of the art while being an order of magnitude faster. We then propose a parallel and distributed online tree boosting algorithm that maintains the correctness guarantees of serial algorithms while providing an order of magnitude speedup on average. Finally, we propose an algorithm that allows for gradient boosted trees training to be distributed across both the data point and feature dimensions. We show that we can achieve communication savings of several orders of magnitude for sparse datasets, compared to existing approaches that can only distribute the computation across the data point dimension and use dense communication.

sted, utgiver, år, opplag, sider
KTH Royal Institute of Technology, 2019. s. 120
Serie
TRITA-EECS-AVL ; 2019:43
Emneord
Online Learning, Distributed Computing, Graph Similarity, Decision Trees, Gradient Boosting
HSV kategori
Identifikatorer
urn:nbn:se:kth:diva-250038 (URN)978-91-7873-181-7 (ISBN)
Disputas
2019-05-28, Sal B, Kistagången 16, våningsplan 2, Electrum 1, KTH Kista, Kista, 14:00 (engelsk)
Opponent
Veileder
Forskningsfinansiär
Swedish Foundation for Strategic Research , RIT10-0043Swedish Foundation for Strategic Research , BD15-0006
Merknad

QC 20190426

Tilgjengelig fra: 2019-04-26 Laget: 2019-04-25 Sist oppdatert: 2022-12-12bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Søk i DiVA

Av forfatter/redaktør
Vasiloudis, TheodoreBoström, Henrik
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric

urn-nbn
Totalt: 166 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf