Understanding Machine Learning: From Theory to Algorithms

By Shai Shalev-Shwartz, Shai Ben-David. 2014

458 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Differentially Private Meta-Learning (2019, methodology): “In Setting A.1 we have Similarly to Lemma 3.3 in Bassily et al. (2019), applying standard OGD analysis (e.g. Lemmas 14.1 and 14.9 of Shalev-Shwartz and Ben-David (2014)) to noisy gradient vectors and taking expectations yields where n is the number of steps in noisy SGD and σ 2 is the variance of…”
Taking Advantage of Multitask Learning for Fair Classification (2018, neutral): “[32]), which is defined as l(f (x , s),y) = max ( 0, 1−y f (x , s) ) .”
On the Equivalence between Kernel Quadrature Rules and Random Feature Expansions (2015, methodology): “We have the usual generalization bound for the minimizer ˆ f of ˆ L ( f ) with respect to f F F , based on Rademacher complexity (see, e.g., Shalev-Shwartz and Ben-David, 2014): We now consider learning by sampling n features from the optimized distribution from Section 4.2, leading to a function…”
Big Data for Development: A Review of Promises and Challenges (2016, unknown): “Machine-learning and data-mining methods, which enable algorithms to learn from data (Shalev-Shwartz and Ben-David, 2014), have often been belittled during the 1990s and early 2000s, but have proven their point forcefully during the 2010s, once they were applied to vast amounts of data.”
Fast Convergence Rates of Distributed Subgradient Methods With Adaptive Quantization (2018, methodology): “Thus, using the preceding equation and α (0) = a ≥ 1 / μ gives (30), i.e., In this section, we apply Algorithm 1 for solving linear regression problems, the most popular technique for data ﬁtting [32], [33] in statistical machine learning, over a network of processors under random quantization.”
Effect of data encoding on the expressive power of variational quantum-machine-learning models (2020, background): “[38] Shai Shalev-Shwartz and Shai Ben-David, Understanding machine learning: From theory to algorithms (Cambridge university press, 2014).”
Machine Learning for Cultural Heritage: A Survey (2020, background): “In each of the following sections we draw a generalised formulation based on familiar ML publications, Bishop [6] , Hastie et al. [21] , Shalev-Shwartz and Ben-David [38] or referenced literature, which we reﬂect or extend on throughout the section.”
A Survey of Privacy Attacks in Machine Learning (2020, background): “Several textbooks such as [7, 24, 64, 81] provide a more thorough coverage of the topic.”
Learning to Localize Sound Sources in Visual Scenes: Analysis and Applications (2019, methodology): “These may imply that, by the definition of learnability [12], the task is not a fully learnable problem only with unsupervised data in our setting, which is static-image based single-channel audio”
Is your dataset big enough? Sample size requirements when using artificial neural networks for discrete choice analysis (2018, methodology): “A common approach to test for under-and over ﬁ tting is to randomly separate the available data into three subsets: one each for training, validation and testing (Ripley, 2007; Shalev-Shwartz and Ben-David, 2014).”
Do Subsampled Newton Methods Work for High-Dimensional Data? (2019, background): “We ﬁrst consider the simple case where r ( · ) is zero, i.e., (2) Problem (2) arises frequently in machining learning (Shalev Shwartz and Ben David 2014).”