On-line Algorithms in Machine Learning

By Avrim Blum. 1996

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

Interpretable Decision Sets: A Joint Framework for Description and Prediction (2016, background): “They will form the basis of our approach to learning.”
Lifelong Generative Modeling (2017, background): “The idea of learning in a continual manner has been explored extensively in machine learning, seeded by the seminal works of lifelong-learning [126, 125, 117], online-learning [32, 9, 11, 12] and sequential linear gaussian models [105, 36] such as the Kalman Filter [56] and its non-linear counterpar”
Learning Cumulatively to Become More Knowledgeable (2016, background): “Our problem is also different from existing research in online learning and incremental learning [1, 6, 42].”
Efficient algorithms for online decision problems (2005, background): “Even in learning, there are too many results to mention (for a survey, see [4]).”
Finite-Time Last-Iterate Convergence for Multi-Agent Learning in Games (2020, background): “In its most basic incarnation, online learning [Blum, 1998, Shalev-Shwartz et al., 2012, Hazan, 2016] can be described as a feedback loop of the following form: 1.”
Toward Attribute Efficient Learning of Decision Lists and Parities (2006, methodology): “Several researchers [5, 8, 10, 25, 28] have since considered this problem; we summarize this previous work in Section 1.”
Attribute-efficient learning of decision lists and linear threshold functions under unconcentrated distributions (2006, background): “This question was first asked by Blum in 1990 [3] and has since been re-posed numerous times [4, 5, 6, 29]; as we now briefly describe, a range of partial results have been obtained along different lines.”
Online Learning and Online Convex Optimization (2012, background): “A more classic treatment can be found in Blum's survey [8].”
Online Learning: A Comprehensive Survey (2018, background): “Readers are also encouraged to read some older related books, surveys and tutorial notes about online learning and online algorithms (Fiat and Woeginger, 1998; Bottou, 1998b; Rakhlin, 2008; Blum, 1998; Albers, 2003).”
Eecient Algorithms for Online Decision Problems (2003, background): “Even in learning, there are too many results to mention (for a survey, see [1]).”
The Multiplicative Weights Update Method: a Meta-Algorithm and Applications (2012, background): “…versions have been independently discovered in operations research and statistical decision making in the context of the On-line decision problem ; see the surveys of Cover [22], Foster and Vohra [25], and also Blum [10] who includes applications of weighted majority to machine learning.”
On-line Boosting and Vision (2006, background): “Hence, the goal of an on-line learner is to forget irrelevant information and specialize to the current situation, which usually is an easier but time dependent sub-problem [9, 127].”