M.A.J. van Gerven, and T. Heskes. L1/Lp regularization of Differences. Technical report: ICIS-R08009, May, Radboud University Nijmegen, 2008.
In this paper, we introduce $L_1/L_p$ regularization of differences as a new regularization approach that can directly regularize models such as the naive Bayes classifier and (autoregressive) hidden Markov models. An algorithm is developed that selects values of the regularization parameter based on a derived stability condition. for the regularized naive Bayes classifier, we show that the method performs comparably to a filtering algorithm based on mutual information for eight datasets that have been selected from the UCI machine learning repository.
T. Heskes, and M.A.J. van Gerven. Stability Conditions for L1/Lp Regularization. Technical report: ICIS-R08002, February, Radboud University Nijmegen, 2008.
This working note derives the stability conditions for L1/Lp regularization.
Cezary Kaliszyk, Femke van Raamsdonk, Freek Wiedijk, Hanno Wupper, Maxim Hendriks, and Roel de Vrijer. Deduction using the ProofWeb system. Technical report: ICIS-R08016, September, Radboud University Nijmegen, 2008.
This is the manual of the ProofWeb system that was implemented at the Radboud University Nijmegen and the Free University Amsterdam in the SURF education innovation project Web deduction for education in formal thinking.