paper-with-me

홈 › Papers

Tradeoffs in Data Augmentation: An Empirical Study

2021-01-01 · ICLR 2021 1 · Raphael Gontijo-Lopes, Sylvia Smullin, Ekin Dogus Cubuk, Ethan Dyer

Though data augmentation has become a standard component of deep neural network training, the underlying mechanism behind the effectiveness of these techniques remains poorly understood. In practice, augmentation policies are often chosen using heuristics of distribution shift or augmentation diversity. Inspired by these, we conduct an empirical study to quantify how data augmentation improves model generalization. We introduce two interpretable and easy-to-compute measures: Affinity and Diversity. We find that augmentation performance is predicted not by either of these alone but by jointly optimizing the two.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationDiversity

Similar Papers 제목 키워드 기반

Counterfactual Fairness in Text Classification through Robustness

2018-09-27 · Sahaj Garg, Vincent Perot, Nicole Limtiaco, Ankur Taly 외

In this paper, we study counterfactual fairness in text classification, which asks the question: How would the prediction change if the sensitive attribute referenced in the example were different? Toxicity classifiers d…

AttributeClassificationcounterfactualFairness+3

Confounding Tradeoffs for Neural Network Quantization

2021-02-12 · Sahaj Garg, Anirudh Jain, Joe Lou, Mitchell Nahmias

Many neural network quantization techniques have been developed to decrease the computational and memory footprint of deep learning. However, these methods are evaluated subject to confounding tradeoffs that may affect i…

Quantization

How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval

2023-02-15 · Sheng-Chieh Lin, Akari Asai, Minghan Li, Barlas Oguz 외

Various techniques have been developed in recent years to improve dense retrieval (DR), such as unsupervised contrastive learning and pseudo-query generation. Existing DRs, however, often suffer from effectiveness tradeo…

Contrastive LearningData AugmentationPassage RetrievalRetrieval+1

Kolmogorov Arnold Networks (KANs) for Imbalanced Data -- An Empirical Perspective

2025-07-18 · Pankaj Yadav, Vivek Vijay arxiv

Kolmogorov Arnold Networks (KANs) are recent architectural advancement in neural computation that offer a mathematically grounded alternative to standard neural networks. This study presents an empirical evaluation of KA…

Computational EfficiencyData Augmentation

LangProBe: a Language Programs Benchmark

2025-02-27 · Shangyin Tan, Lakshya A Agrawal, Arnav Singhvi, Liheng Lai 외

Composing language models (LMs) into multi-step language programs and automatically optimizing their modular prompts is now a mainstream paradigm for building AI systems, but the tradeoffs in this space have only scarcel…