Abstract. Bayesian model averaging also known as the Bayes optimal classifier (BOC) is an ensemble technique used extensively in the statistics literature. However, compared to other ensemble techniques such as bagging and boosting, BOC is less known and rarely used in data mining. This is partly due to model averaging being perceived as being inefficient and because bagging and boosting consistently outperforms a single model, which raises the question: “Do we even need BOC in datamining?”. We show that the answer to this question is “yes ” by illustrating that several recent efficient model averaging approaches can significantly outperform bagging and boosting in realistic difficult situations such as extensive class label noise, sample selection bias and many-class problems. To our knowledge the insights that model averaging can outperform bagging and boosting in these situations has not been published in the machine learning, mining or statistical communities. 1

A substantial school in the philosophy of science identifies Bayesian inference with inductive inference and even rationality as such, and seems to be strengthened by the rise and practical success of Bayesian statistics. We argue that the most successful forms of Bayesian statistics do not actually support that particular philosophy but rather accord much better with sophisticated forms of hypothetico-deductivism. We examine the actual role played by prior distributions in Bayesian models, and the crucial aspects of model checking and model revision, which fall outside the scope of Bayesian confirmation theory. We draw on the literature on the consistency of Bayesian updating and also on our experience of applied work in social science. Clarity about these matters should benefit not just philosophy of science, but also statistical practice. At best, the inductivist view has encouraged researchers to fit and compare models without checking them; at worst, theorists have actively discouraged practitioners from performing model checking because it does not fit into their framework. 1 The usual story—which we don’t like In so far as I have a coherent philosophy of statistics, I hope it is “robust ” enough to cope in principle with the whole of statistics, and sufficiently undogmatic not to imply that all those who may think rather differently from me are necessarily stupid. If at times I do seem dogmatic, it is because it is convenient to give my own views as unequivocally as possible. (Bartlett, 1967, p. 458) Schools of statistical inference are sometimes linked to approaches to the philosophy of science. “Classical ” statistics—as exemplified by Fisher’s p-values, Neyman-Pearson hypothesis tests, and Neyman’s confidence intervals—is associated with the hypotheticodeductive and falsificationist view of science. Scientists devise hypotheses, deduce implications for observations from them, and test those implications. Scientific hypotheses can be rejected (that is, falsified), but never really established or accepted in the same way. Mayo (1996) presents the leading contemporary statement of this view. 1 In

Abstract. In Minimum Message Length (MML) clustering (unsupervised classification, mixture modelling) the aim is to infer a set of classes that best explains the observed data items. There are cases where parts of the observed data do not need to be explained by the inferred classes but can be used to improve the inference and resulting predictions. Our main contribution is to provide a simple and flexible way of using such context data in MML clustering. This is done by replacing the traditional mixing proportion vector with a new context matrix. We show how our method can be used to give evidence regarding the presence of apparent long-term trends in climate-related atmospheric pressure records. Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC) solutions for our model have also been implemented to compare with the MML solution.

We study the tracking problem, namely, estimating the hidden state of an object over time, from unreliable and noisy measurements. The standard framework for the tracking problem is the generative framework, which is the basis of solutions such as the Bayesian algorithm and its approximation, the particle filters. However, these solutions can be very sensitive to model mismatches. In this paper, motivated by online learning, we introduce a new framework for tracking. We provide an efficient tracking algorithm for this framework. We provide experimental results comparing our algorithm to the Bayesian algorithm on simulated data. Our experiments show that when there are slight model mismatches, our algorithm outperforms the Bayesian algorithm. 1

Abstract not found

www.cwi.nl/~pdg From November 1998 until September 1999, Jorma Rissanen and I met on a regular basis. Here I recall some of our stimulating conversations and some of the work that we did together. This work, based almost exclusively on a single page of [12], was left unfinished and has never been published, but it has indirectly had a profound impact on my career. 1 Meet Jorma Rissanen I first met Jorma in November 1998. I had just obtained my Ph.D. in Amsterdam and started a postdoc at Stanford University. These were exciting times: it was at the height of the dot-com boom, and Stanford was right in the middle of it. Since my thesis was all about the MDL Principle, I had suggested that Jorma and I could meet in person during my stay in California. Jorma replied that he would like to. I was delighted, honored but also a bit worried, since I had been forewarned that Jorma was not your “usual ” kind of scientist...

One of the second generation of computer scientists, Chris Wallace completed his tertiary education in 1959 with a Ph.D. in nuclear physics, on cosmic ray showers, under Dr Paul George at Sydney University. Needless to say, computer science was not, at that stage, an established academic discipline. With Max Brennan 1 andJohnMaloshehaddesignedand built a large automatic data logging system for recording cosmic ray air shower events and with Max Brennan also developed a complex computer programme for Bayesian analysis of cosmic ray events on the recently installed SILLIAC computer. Appointed lecturer in Physics at Sydney in 1960 he was sent almost immediately to the University of Illinois to copy the design of ILLIAC II, a duplicate of which was to be built at Sydney. ILLIAC II was not in fact completed at that stage and, after an initial less than warm welcome by a department who seemed unsure exactly what this Australian was doing in their midst, his talents were recognized and he was invited to join their staff (under very generous conditions) to assist in ILLIAC II design 2. He remained there for two years helping in particular to design the input output channels and aspects of the advanced control unit (first stage pipeline). In the event, Sydney decided it would be too expensive to build a copy of ILLIAC II, although a successful copy (the Golem) was built in Israel using circuit designs developed by Wallace and Ken Smith. In spite of the considerable financial and academic inducements to remain in America, Wallace returned to Australia after three months spent in England familiarizing himself with the KDF9 computer being purchased by Sydney University to replace SILLIAC. Returning to the School of Physics he joined the Basser

Abstract not found