Training machine learning (ML) models typically involves expensive iterative optimization.
Once the model's final parameters are released, there is currently no mechanism for the …

Big data is an important factor almost in all nowadays technologies, such as, social media,
smart cities, and internet of things. Most of standard classifiers tends to be trapped in local …

Data processing is very important in the development of information technology. Almost all
fields of work have information data. Data can be used to help analysis in work. At present …

We propose a class of very simple modifications of gradient descent and stochastic gradient
descent leveraging Laplacian smoothing. We show that when applied to a large variety of …

This paper presents a partial differential equation framework for deep residual neural
networks and for the associated learning problem. This is done by carrying out the …

The previous recommendation system applied the matrix factorization collaborative filtering
(MFCF) technique to only single domains. Due to data sparsity, this approach has a …

Empirical evidence and theoretical results suggest that the proximal point method can be
computed approximately and still converge faster than the corresponding gradient descent …

Enhancing the effectiveness of clustering methods has always been of great interest.
Therefore, inspired by the success story of the gradient descent approach in supervised …

Abstract Pre-trained Language Models (PLMs) have achieved remarkable performance on
diverse NLP tasks through pre-training and fine-tuning. However, fine-tuning the model with …

We propose AEGD, a new algorithm for first-order gradient-based optimization of non-
convex objective functions, based on a dynamically updated energy variable. The method is …