Uncertainty quantification (UQ) methods play a pivotal role in reducing the impact of
uncertainties during both optimization and decision making processes. They have been …

Due to the inherent model uncertainty, learning to infer Bayesian posterior from a few-shot
dataset is an important step towards robust meta-learning. In this paper, we propose a novel …

The vast majority of deep models use multiple gradient signals, typically corresponding to a
sum of multiple loss terms, to update a shared set of trainable weights. However, these …

Recent years have witnessed the rapid progress of generative adversarial networks (GANs).
However, the success of the GAN models hinges on a large amount of training data. This …

Improving the generalization of deep networks is an important open challenge, particularly
in domains without plentiful data. The mixup algorithm improves generalization by linearly …

Meta-learning enables algorithms to quickly learn a newly encountered task with just a few
labeled examples by transferring previously learned knowledge. However, the bottleneck of …

Meta-learning has emerged as a potent paradigm for quick learning of few-shot tasks, by
leveraging the meta-knowledge learned from meta-training tasks. Well-generalized meta …

Recently, Mixture-of-Experts (short as MoE) architecture has achieved remarkable success
in increasing the model capacity of large-scale language models. However, MoE requires …

The success of meta-learning on existing benchmarks is predicated on the assumption that
the distribution of meta-training tasks covers meta-testing tasks. Frequent violation of the …

We propose a memory efficient method, named Stochastic Backpropagation (SBP), for
training deep neural networks on videos. It is based on the finding that gradients from …