cover

Testing ADA on Synthetic and Real-World Data

15 Nov 2024

ADA boosts regression models' robustness through data augmentation, improving performance across real-world and synthetic data with varying hyperparameters.

cover

How Hyperparameter Tuning Enhances Anchor Data Augmentation for Robust Regression

15 Nov 2024

Explore how hyperparameter tuning in ADA affects model performance, robustness, and optimization with a 1D cosine data example and minibatch augmentation.

cover

ADA: A Powerful Data Augmentation Technique for Improved Regression Robustness

15 Nov 2024

ADA (Anchor Data Augmentation) offers a novel approach to data augmentation by mixing multiple samples based on clustering.

cover

ADA's Impact on Out-of-Distribution Robustness

14 Nov 2024

This paper compares ADA's performance on out-of-distribution robustness tasks, highlighting its superiority with datasets like SkillCraft and RCFashionMNIST.

cover

ADA Outperforms ERM and Competes with C-Mixup in In-Distribution Generalization Tasks

14 Nov 2024

This paper evaluates ADA's performance on in-distribution generalization tasks, comparing it to C-Mixup, Mixup, and other strategies.

cover

ADA vs C-Mixup: Performance on California and Boston Housing Datasets

14 Nov 2024

This paper extends ADA’s evaluation to nonlinear regression on the California and Boston housing datasets, comparing its performance against C-Mixup.

cover

Evaluating ADA: Experimental Results on Linear and Housing Datasets

14 Nov 2024

This paper presents experimental evaluations of ADA, comparing it with C-Mixup, vanilla augmentation, and classical risk minimization.

cover

How to Implement ADA for Data Augmentation in Nonlinear Regression Models

14 Nov 2024

This paper presents the ADA algorithm for generating minibatches in nonlinear regression models, using stochastic gradient descent.

cover

Anchor Data Augmentation as a Generalized Variant of C-Mixup

14 Nov 2024

ADA is a generalized version of C-Mixup that mixes multiple samples based on cluster membership, preserving nonlinear relationships in augmented regression data