On the Generalization Ability of On-Line Learning Algorithms

Cesa-Bianchi, Nicolò; Conconi, Alex; Gentile, Claudio

doi:10.1109/tit.2004.833339

Cited by 359 publications

(402 citation statements)

References 38 publications

Supporting

Mentioning

398

Contrasting

Order By: Relevance

“…In this section, we briefly introduce the related work on online machine learning (Rosenblatt 1958;Crammer and Singer 2003;Cesa-Bianchi et al 2004;Crammer et al 2006;Fink et al 2006) to have the learning inspiration for our work. Perceptron algorithm (Rosenblatt 1958;Freund and Schapire 1999) is one important online approach which updates the learning function by adding a new example with a constant weight when it is misclassified.…”

Section: Online Learningmentioning

confidence: 99%

PAMR: Passive aggressive mean reversion strategy for portfolio selection

et al. 2012

View full text Add to dashboard Cite

This article proposes a novel online portfolio selection strategy named "Passive Aggressive Mean Reversion" (PAMR). Unlike traditional trend following approaches, the proposed approach relies upon the mean reversion relation of financial markets. Equipped with online passive aggressive learning technique from machine learning, the proposed portfolio selection strategy can effectively exploit the mean reversion property of markets. By analyzing PAMR's update scheme, we find that it nicely trades off between portfolio return and volatility risk and reflects the mean reversion trading principle. We also present several variants of PAMR algorithm, including a mixture algorithm which mixes PAMR and other strategies. We conduct extensive numerical experiments to evaluate the empirical performance of the proposed algorithms on various real datasets. The encouraging results show that in most cases the proposed PAMR strategy outperforms all benchmarks and almost all state-of-the-art portfolio selection strategies under various performance metrics. In addition to its superior performance, the proposed PAMR runs extremely fast and thus is very suitable for real-life online trading applications. The experimental testbed including source codes and data sets is available at http://www.cais.ntu.edu.sg/~chhoi/PAMR/.

show abstract

Section: Online Learningmentioning

confidence: 99%

PAMR: Passive aggressive mean reversion strategy for portfolio selection

et al. 2012

View full text Add to dashboard Cite

show abstract

“…This brings us to our second algorithm: We define an online learning problem that is closely related to the original statistical learning problem. We address this online problem with a modified version of the online Perceptron algorithm (Rosenblatt 1958), and then convert the online algorithm into a statistical learning algorithm using an online-to-batch conversion technique (Cesa-Bianchi et al 2004). This approach benefits from the computational efficiency of the Perceptron, and from the generalization properties and theoretical guarantees provided by the online-to-batch technique.…”

Section: Introductionmentioning

confidence: 99%

Learning to classify with missing and corrupted features

2009

View full text Add to dashboard Cite

A common assumption in supervised machine learning is that the training examples provided to the learning algorithm are statistically identical to the instances encountered later on, during the classification phase. This assumption is unrealistic in many real-world situations where machine learning techniques are used. We focus on the case where features of a binary classification problem, which were available during the training phase, are either deleted or become corrupted during the classification phase. We prepare for the worst by assuming that the subset of deleted and corrupted features is controlled by an adversary, and may vary from instance to instance. We design and analyze two novel learning algorithms that anticipate the actions of the adversary and account for them when training a classifier. Our first technique formulates the learning problem as a linear program. We discuss how the particular structure of this program can be exploited for computational efficiency and we prove statistical bounds on the risk of the resulting classifier. Our second technique addresses the robust learning problem by combining a modified version of the Perceptron algorithm with an online-to-batch conversion technique, and also comes with statistical generalization guarantees. We demonstrate the effectiveness of our approach with a set of experiments.

show abstract

“…This renewed interest for theory naturally boosted the development of performance bounds for learning machines (see e.g. Bartlett and Long 1998;Bousquet 2003;Cesa-Bianchi et al 2004;Cucker and Zhou 2007;Lugosi and Pawlak 1994;Zhou 2003, 2004;Wu and Zhou 2005;Zhou 2003 and references therein). In order to measure the generalization ability of the empirical risk minimization algorithm with i.i.d.…”

Section: Introductionmentioning

confidence: 99%

The generalization performance of ERM algorithm with strongly mixing observations

Zou

Zhao

2009

Mach Learn

View full text Add to dashboard Cite

The generalization performance is the main concern of machine learning theoretical research. The previous main bounds describing the generalization ability of the Empirical Risk Minimization (ERM) algorithm are based on independent and identically distributed (i.i.d.) samples. In order to study the generalization performance of the ERM algorithm with dependent observations, we first establish the exponential bound on the rate of relative uniform convergence of the ERM algorithm with exponentially strongly mixing observations, and then we obtain the generalization bounds and prove that the ERM algorithm with exponentially strongly mixing observations is consistent. The main results obtained in this paper not only extend the previously known results for i.i.d. observations to the case of exponentially strongly mixing observations, but also improve the previous results for strongly mixing samples. Because the ERM algorithm is usually very time-consuming and overfitting may happen when the complexity of the hypothesis space is high, as an application of our main results we also explore a new strategy to implement the ERM algorithm in high complexity hypothesis space.

show abstract

On the Generalization Ability of On-Line Learning Algorithms

Cited by 359 publications

References 38 publications

PAMR: Passive aggressive mean reversion strategy for portfolio selection

PAMR: Passive aggressive mean reversion strategy for portfolio selection

Learning to classify with missing and corrupted features

The generalization performance of ERM algorithm with strongly mixing observations

Contact Info

Product

Resources

About