Generalization Bounds for Randomized Learning with Application to Stochastic Gradient Descent

How researchers see this paper

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

Stable and Fair Classification (2019, background): “, 2016b), (London, 2016) and (Kuzborskij & Lampert, 2018) showed that the stochastic gradient descent method is stable.”
Generalization Error Bounds for Noisy, Iterative Algorithms (2018, methodology): “Generalization properties of SGD have recently been derived using a different approach involving algorithmic stability [6], [7].”
Data-Dependent Stability of Stochastic Gradient Descent (2017, methodology): “Uniform stability was used to analyze many algorithms, including regularized Empirical Risk Minimization (ERM) (Bousquet and Elisseeﬀ, 2002), randomized aggregation schemes (Elisseeﬀ et al., 2005), and recently SGD by Hardt et al. (2016); London (2016), and Poggio et al. (2011).”
Generalization Bounds of SGLD for Non-convex Learning: Two Theoretical Viewpoints (2017, background): “…leading to optimal population risks; More general cases are studied via uniform stability of parameters under (cid:96) 2 norm (Hardt et al., 2015; London, 2016); From statistical inference aspects, Chen et al. (2016) constructed conﬁdence sets based on the Markov chain induced by SGD for…”