Robust learning of inhomogeneous PMMs

Ralf Eggeling, Teemu Roos, Petri Myllymäki, Ivo Grosse
Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, PMLR 33:229-237, 2014.

Abstract

Inhomogeneous parsimonious Markov models have recently been introduced for modeling symbolic sequences, with a main application being DNA sequence analysis. Structure and parameter learning of these models has been proposed using a Bayesian approach, which entails the practically challenging choice of the prior distribution. Cross validation is a possible way of tuning the prior hyperparameters towards a specific task such as prediction or classification, but it is overly time-consuming. On this account, robust learning methods, which do not require explicit prior specification and – in the absence of prior knowledge – no hyperparameter tuning, are of interest. In this work, we empirically investigate the performance of robust alternatives for structure and parameter learning that extend the practical applicability of inhomogeneous parsimonious Markov models to more complex settings than before.

Cite this Paper

BibTeX
@InProceedings{pmlr-v33-eggeling14, title = {{Robust learning of inhomogeneous PMMs}}, author = {Eggeling, Ralf and Roos, Teemu and Myllymäki, Petri and Grosse, Ivo}, booktitle = {Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics}, pages = {229--237}, year = {2014}, editor = {Kaski, Samuel and Corander, Jukka}, volume = {33}, series = {Proceedings of Machine Learning Research}, address = {Reykjavik, Iceland}, month = {22--25 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v33/eggeling14.pdf}, url = {https://proceedings.mlr.press/v33/eggeling14.html}, abstract = {Inhomogeneous parsimonious Markov models have recently been introduced for modeling symbolic sequences, with a main application being DNA sequence analysis. Structure and parameter learning of these models has been proposed using a Bayesian approach, which entails the practically challenging choice of the prior distribution. Cross validation is a possible way of tuning the prior hyperparameters towards a specific task such as prediction or classification, but it is overly time-consuming. On this account, robust learning methods, which do not require explicit prior specification and – in the absence of prior knowledge – no hyperparameter tuning, are of interest. In this work, we empirically investigate the performance of robust alternatives for structure and parameter learning that extend the practical applicability of inhomogeneous parsimonious Markov models to more complex settings than before.} }
Endnote
%0 Conference Paper %T Robust learning of inhomogeneous PMMs %A Ralf Eggeling %A Teemu Roos %A Petri Myllymäki %A Ivo Grosse %B Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2014 %E Samuel Kaski %E Jukka Corander %F pmlr-v33-eggeling14 %I PMLR %P 229--237 %U https://proceedings.mlr.press/v33/eggeling14.html %V 33 %X Inhomogeneous parsimonious Markov models have recently been introduced for modeling symbolic sequences, with a main application being DNA sequence analysis. Structure and parameter learning of these models has been proposed using a Bayesian approach, which entails the practically challenging choice of the prior distribution. Cross validation is a possible way of tuning the prior hyperparameters towards a specific task such as prediction or classification, but it is overly time-consuming. On this account, robust learning methods, which do not require explicit prior specification and – in the absence of prior knowledge – no hyperparameter tuning, are of interest. In this work, we empirically investigate the performance of robust alternatives for structure and parameter learning that extend the practical applicability of inhomogeneous parsimonious Markov models to more complex settings than before.
RIS
TY - CPAPER TI - Robust learning of inhomogeneous PMMs AU - Ralf Eggeling AU - Teemu Roos AU - Petri Myllymäki AU - Ivo Grosse BT - Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics DA - 2014/04/02 ED - Samuel Kaski ED - Jukka Corander ID - pmlr-v33-eggeling14 PB - PMLR DP - Proceedings of Machine Learning Research VL - 33 SP - 229 EP - 237 L1 - http://proceedings.mlr.press/v33/eggeling14.pdf UR - https://proceedings.mlr.press/v33/eggeling14.html AB - Inhomogeneous parsimonious Markov models have recently been introduced for modeling symbolic sequences, with a main application being DNA sequence analysis. Structure and parameter learning of these models has been proposed using a Bayesian approach, which entails the practically challenging choice of the prior distribution. Cross validation is a possible way of tuning the prior hyperparameters towards a specific task such as prediction or classification, but it is overly time-consuming. On this account, robust learning methods, which do not require explicit prior specification and – in the absence of prior knowledge – no hyperparameter tuning, are of interest. In this work, we empirically investigate the performance of robust alternatives for structure and parameter learning that extend the practical applicability of inhomogeneous parsimonious Markov models to more complex settings than before. ER -
APA
Eggeling, R., Roos, T., Myllymäki, P. & Grosse, I.. (2014). Robust learning of inhomogeneous PMMs. Proceedings of the Seventeenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 33:229-237 Available from https://proceedings.mlr.press/v33/eggeling14.html.

Related Material