Timezone: »

Proximal Mapping for Deep Regularization
Mao Li · Yingyi Ma · Xinhua Zhang

Wed Dec 09 08:00 AM -- 08:10 AM (PST) @ Orals & Spotlights: Deep Learning

Underpinning the success of deep learning is effective regularizations that allow a variety of priors in data to be modeled. For example, robustness to adversarial perturbations, and correlations between multiple modalities. However, most regularizers are specified in terms of hidden layer outputs, which are not themselves optimization variables. In contrast to prevalent methods that optimize them indirectly through model weights, we propose inserting proximal mapping as a new layer to the deep network, which directly and explicitly produces well regularized hidden layer outputs. The resulting technique is shown well connected to kernel warping and dropout, and novel algorithms were developed for robust temporal learning and multiview modeling, both outperforming state-of-the-art methods.

Author Information

Mao Li (University of Illinois at Chicago)
Yingyi Ma (University of Illinois at Chicago)
Xinhua Zhang (UIC)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors