CoChat
Sign Up
Cited by 3,115Machine Learning and AlgorithmsStochastic Gradient Optimization TechniquesNeural Networks and Applications

Understanding Machine Learning: From Theory to Algorithms

Shalev-Shwartz, Shai, Ben-David, Shai·2014·Cambridge University Press eBooks
DOI 10.1017/cbo9781107298019
Open this paper in CoChat — free account

Abstract

Machine learning is one of the fastest growing areas of computer science, with far-reaching applications. The aim of this textbook is to introduce machine learning, and the algorithmic paradigms it offers, in a principled way. The book provides a theoretical account of the fundamentals underlying machine learning and the mathematical derivations that transform these principles into practical algorithms. Following a presentation of the basics, the book covers a wide array of central topics unaddressed by previous textbooks. These include a discussion of the computational complexity of learning and the concepts of convexity and stability; important algorithmic paradigms including stochastic gradient descent, neural networks, and structured output learning; and emerging theoretical concepts such as the PAC-Bayes approach and compression-based bounds. Designed for advanced undergraduates or beginning graduates, the text makes the fundamentals and algorithms of machine learning accessible to students and non-expert readers in statistics, computer science, mathematics and engineering.

Integrity signals

Registry

Crossref · 10.1017/cbo9781107298019

Cites

2 of 2 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • MAE and MAPE are commonly used measures in machine learning and provide a more natural and intuitive measure of model performance.

    “MAE and MAPE are commonly used measures in ML [9] and provide a more natural and intuitive measure of model performance [12,13].”

    From Turnaround time prediction for clinical chemistry samples using machine learning (2022) · cites this paper as [9]

  • The fundamental principle in statistical learning is that in great generality it suffices to approximately minimize the empirical loss.

    “The fundamental principle in statistical learning is that in great generality it suffices to approximately minimize the empirical loss, which is L n ( θ ) = 1 n ∑ n i =1 ℓ ( Z i , θ ) .”

    From Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence (2025) · cites this paper as Shalev-Shwartz and Ben-David, 2014

  • There is an elementary upper bound that matches the lower bound up to an O(log|H|) factor.

    “Note that there is an elementary upper bound that matches the lower bound up to an O (log |H| ) factor (Shalev-Shwartz and Ben-David, 2014).”

    From Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence (2025) · cites this paper as Shalev-Shwartz and Ben-David, 2014

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Authors
Shalev-Shwartz, S., & Ben-David, S.
Affiliations
University of Waterloo (CA)
Venue
Cambridge University Press eBooks
Publisher
Cambridge University Press
Published
2014-05-19
DOI
10.1017/cbo9781107298019
OpenAlex
W4236362309
Cited by
3,115
References
2
Citations by year
2026: 223 · 2025: 388 · 2024: 404 · 2023: 431 · 2022: 439 · 2021: 379 · 2020: 383 · 2019: 192 · 2018: 150 · 2017: 70 · 2016: 35 · 2015: 17 · 2014: 3 · 2013: 1
FWCI
17.97
Type
book
Language
en
Open access
closed
Licence
www.cambridge.org/core/terms (unspecified, 47 d)
Locations
Cambridge University Press eBooks (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
  • Physical Sciences › Computer Science › Artificial Intelligence › Stochastic Gradient Optimization Techniques
  • Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
Keywords
machine learning theory, computational complexity of learning, convexity, stability, stochastic gradient descent, artificial neural networks, structured prediction, PAC-Bayes, learning algorithms

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review