Rademacher Complexity Bounds for Non-I.I.D. Processes

By Mehryar Mohri, Afshin Rostamizadeh. 2008

185 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

Continual Learning through Retrieval and Imagination (2022, methodology): “In this section, we analyze the generalization of our learning framework based on robustness theory in machine learning (Bellet et al. 2015; Mohri et al. 2009; Yin et al. 2020; Guo et al. 2022).”
Minimax Weight and Q-Function Learning for Off-Policy Evaluation (2019, methodology): “The only difference is we use Theorem 2 (Mohri and Rostamizadeh, 2009) to bound the term supf∈F,w∈W ||Lw,n(w, f)| − |Lw(w, f)||.”
Chromatic PAC-Bayes Bounds for Non-IID Data (2009, methodology): “The bound that we propose is in the same vein as the one proposed by Mohri and Rostamizadeh (2009), with the difference that our bound is a PAC-Bayes bound and theirs a Rademacher-complexitybased bounds.”
Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification (2018, methodology): “While this approach has been successfully used to develop generalization bounds for time-series data [Mohri and Rostamizadeh, 2007a], a fundamental limitation of mixing-time arguments is that the bounds deteriorate when the underlying process is slower to mix.”
Time series prediction and online learning (2016, background): “…of several recent publications (Yu, 1994; Vidyasagar, 1997; Berti and Rigo, 1997; Modha and Masry, 1998; Meir, 2000; Steinwart and Christmann, 2009; Mohri and Rostamizadeh, 2009; Alquier and Wintenberger, 2010; Pestov, 2010; Mohri and Rostamizadeh, 2010; Shalizi and Kontorovitch, 2013; Alquier et…”
From Predictive to Prescriptive Analytics (2014, methodology): “(2001), Mohri et al. (2012)). Statistical decision theory is generally concerned with the optimal selection of statistical estimators (cf. Berger (1985), Lehmann and Casella (1998)).”
Iterative Value-Aware Model Learning (2018, background): “One can then provide statistical guarantees for learning algorithms under various mixing conditions [Yu, 1994, Meir, 2000, Steinwart and Christmann, 2009, Mohri and Rostamizadeh, 2009, 2010, Farahmand and Szepesvári, 2012].”
Stability and Generalization in Structured Prediction (2016, methodology): “Proposition 1 builds on work by Samson (2000), Chazottes et al.”
PAC-Bayesian Collective Stability (2014, methodology): “(2006) and Ralaivola et al. (2010) used fractional coloring to analyze the generalization error of local predictors.”