Search Results for author:
Found 9 papers, 5 papers with code
Geometric Insights into Focal Loss: Reducing Curvature for Enhanced Model Calibration
One of the simplest techniques to tackle this task is focal loss, a generalization of cross-entropy by introducing one positive parameter.
Augmenting NER Datasets with LLMs: Towards Automated and Refined Annotation
In the field of Natural Language Processing (NLP), Named Entity Recognition (NER) is recognized as a critical technology, employed across a wide array of applications.
Towards Understanding Variants of Invariant Risk Minimization through the Lens of Calibration
This approach should move beyond traditional metrics, such as accuracy and F1 scores, which fail to account for the model's degree of over-confidence, and instead focus on the nuanced interplay between accuracy, calibration, and model invariance.
An Empirical Study of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibration
In out-of-distribution (OOD) generalization tasks, fine-tuning pre-trained models has become a prevalent strategy.
No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths
Understanding the optimization dynamics of neural networks is necessary for closing the gap between theory and practice.
Empirical Study on Optimizer Selection for Out-of-Distribution Generalization
Modern deep learning systems do not generalize well when the test data distribution is slightly different to the training data distribution.
Optimal transport meets noisy label robust loss and MixUp regularization for domain adaptation
It is common in computer vision to be confronted with domain shift: images which have the same class but different acquisition conditions.
Conjugate Gradient Method for Generative Adversarial Networks
Since data distribution is unknown, generative adversarial networks (GANs) formulate this problem as a game between two models, a generator and a discriminator.
Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime
Generalization measures are intensively studied in the machine learning community for better modeling generalization gaps.
