Pruning is a model compression method that removes redundant parameters and accelerates the inference speed of deep neural networks while maintaining accuracy. Most available pruning methods impose various conditions on parameters or features directly.

Inspired by the simple two-step threshold dynamics algorithm which iteratively does convolution and thresholding to simulate the motion of grain boundaries, we developed an algorithm to approach the minimal compliance problem in topology optimization with

With the increasing usage of the electronic limit order book (LOB) in modern financial markets, high-frequency algorithmic trading has captured over 70 percent of the whole trading volume in various financial markets.

Deep generative models are a category of machine learning models that utilizes deep neural networks to model data distributions and generate new samples.

Early stopping is a widely-used regularization technique to avoid overfitting in iterative algorithms.

Normalizing flow (NF) has gained popularity over traditional maximum likelihood based methods due to its strong capability to model complex data distributions.

Spatial transcriptomics (ST) is a groundbreaking method that allows scientists to measure gene activity in a tissue sample and retain spatial information. However, most spatial ST technologies are limited by their resolution.

In the Euclidean setting, the proximal gradient method and its accelerated variants are a class of efficient algorithms for optimization problems with decomposable objective.