Many neural networks deployed in the real world scenarios are trained using cross entropy
based loss functions. From the optimization perspective, it is known that the behavior of first …

Auto-labeling is an important family of techniques that produce labeled training sets with
minimum manual labeling. A prominent variant, threshold-based auto-labeling (TBAL) …

Modern semi-supervised learning (SSL) methods frequently rely on pseudolabeling and
consistency regularization. The main technical challenge in pseudolabeling is identifying the …

Overparameterized deep neural networks (DNNs), if not sufficiently regularized, are
susceptible to overfitting their training examples and not generalizing well to test data. To …

Over the past decade, the field of machine learning has witnessed significant advancements
in artificial intelligence, primarily driven by empirical research. Within this context, we …

In the realm of machine learning, the ability to classify and categorize data has undergone a
remarkable evolution over the past few decades, due in significant part to tremendous …

Double descent has emerged as a fascinating phenomenon that has been observed across
a range of tasks, model architectures, and training paradigms. When double descent occurs …