Accelerated Neural Network Training with Rooted Logistic Objectives
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 …
based loss functions. From the optimization perspective, it is known that the behavior of first …
Pearls from Pebbles: Improved Confidence Functions for Auto-labeling
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) …
minimum manual labeling. A prominent variant, threshold-based auto-labeling (TBAL) …
[PDF][PDF] PabLO: Improving Semi-Supervised Learning with Pseudolabeling Optimization
Modern semi-supervised learning (SSL) methods frequently rely on pseudolabeling and
consistency regularization. The main technical challenge in pseudolabeling is identifying the …
consistency regularization. The main technical challenge in pseudolabeling is identifying the …
Minimizing Chebyshev Prototype Risk Magically Mitigates the Perils of Overfitting
N Dean, D Sarkar - arXiv preprint arXiv:2404.07083, 2024 - arxiv.org
Overparameterized deep neural networks (DNNs), if not sufficiently regularized, are
susceptible to overfitting their training examples and not generalizing well to test data. To …
susceptible to overfitting their training examples and not generalizing well to test data. To …
[图书][B] Surprising Empirical Phenomena of Deep Learning and Kernel Machines
L Hui - 2023 - search.proquest.com
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 artificial intelligence, primarily driven by empirical research. Within this context, we …
[PDF][PDF] Novel Feature Measures for Deep Neural Network Training and Evaluation
N Dean - 2024 - scholarship.miami.edu
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 …
remarkable evolution over the past few decades, due in significant part to tremendous …
Understanding the Role of Optimization and Loss Function in Double Descent
CY Liu - 2023 - search.proquest.com
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 …
a range of tasks, model architectures, and training paradigms. When double descent occurs …