Differentially private (DP) training preserves the data privacy usually at the cost of slower
convergence (and thus lower accuracy), as well as more severe mis-calibration than its non …

Abstract Few-Shot Learning (FSL) is a challenging task, ie, how to recognize novel classes
with few examples? Pre-training based methods effectively tackle the problem by pre …

Interpretable machine learning has demonstrated impressive performance while preserving
explainability. In particular, neural additive models (NAM) offer the interpretability to the …

In this paper, we consider the problem of prototype-based vision-language reasoning
problem. We observe that existing methods encounter three major challenges: 1) escalating …

Momentum methods, such as heavy ball method (HB) and Nesterov's accelerated gradient
method (NAG), have been widely used in training neural networks by incorporating the …

As the training process of deep neural networks involves expensive computational cost,
speeding up the convergence is of great importance. Nesterov's accelerated gradient (NAG) …

Estimating treatment effects is of great importance for many biomedical applications with
observational data. Particularly, interpretability of the treatment effects is preferable for many …

Due to the simplicity and efficiency of the first-order gradient method, it has been widely
used in training neural networks. Although the optimization problem of the neural network is …

Due to its simplicity and efficiency, the first-order gradient method has been extensively
employed in training neural networks. Although the optimization problem of the neural …

The momentum method has become the workhorse in the deep learning community. To
theoretical understand its success, researchers put efforts in demystifying its convergence …