Proximal Mapping for Deep Regularization
Abstract
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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers1
Related papers
- Calibrating Multimodal LearningHuan Ma, Qingyang Zhang, Changqing Zhang, Bingzhe Wu et al.ICML 2023 · 42 citations
- Effective Meta-Regularization by Kernelized Proximal RegularizationWeisen Jiang, James T. Kwok, Yu ZhangNeurIPS 2021 · 9 citations
- Multi-task Learning with 3D-Aware RegularizationWei-Hong Li, Steven McDonagh, Ales Leonardis, Hakan BilenICLR 2024 · 10 citations
- Dropout Prompt Learning: Towards Robust and Adaptive Vision-Language ModelsBiao Chen, Lin Zuo, Mengmeng Jing, Kunbin He et al.AAAI 2026
- ICON: Learning Regular Maps Through Inverse ConsistencyThomas Hastings Greer, Roland Kwitt, François-Xavier Vialard, Marc NiethammerICCV 2021 · 38 citations
