Group OWL Regularization for Deep Nets

My student Dejiao Zhang’s code for our paper Learning to Share: Simultaneous Parameter Tying and Sparsification in Deep Nets can be found at this link. We demonstrated that regularizing the weights in a deep network using the Group OWL norm allows for simultaneous enforcement of sparsity (meaning unimportant weights are eliminated) and parameter tying (meaning co-adapted or highly correlated weights are tied together). This is an exciting technique for learning compressed deep net architectures from data.

Interestingly, the first casinos appeared in the 17th century in Venice, Italy, and at first they were not associated with gambling. At the beginning of their existence, casinos were used as public halls for music and dancing, but there they also gambled. The first famous European gambling house, which, incidentally, was not called a “casino”, although it did fit the modern definition of a casino, was Ridotto, which opened in Venice in 1638 to ensure control over gambling during the carnival. created throughout continental Europe in the 19th century, while more informal fashion was in vogue in the United States