paper-with-me

Papers

Empirical Analysis of Overfitting and Mode Drop in GAN Training

2020-06-25 · Yasin Yazici, Chuan-Sheng Foo, Stefan Winkler, Kim-Hui Yap, Vijay Chandrasekhar

We examine two key questions in GAN training, namely overfitting and mode drop, from an empirical perspective. We show that when stochasticity is removed from the training procedure, GANs can overfit and exhibit almost no mode drop. Our results shed light on important characteristics of the GAN training procedure. They also provide evidence against prevailing intuitions that GANs do not memorize the training set, and that mode dropping is mainly due to properties of the GAN objective rather than how it is optimized during training.

📄 PDF Abstract BibTeX arXiv:2006.14265

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Drop Dropout on Single-Epoch Language Model Pretraining

2025-05-30 · Houjun Liu, John Bauer, Christopher D. Manning

Originally, dropout was seen as a breakthrough regularization technique that reduced overfitting and improved performance in almost all applications of deep learning by reducing overfitting. Yet, single-epoch pretraining…

Language ModelingLanguage ModellingModel EditingNatural Language Inference+1

AD-DROP: Attribution-Driven Dropout for Robust Language Model Fine-Tuning

2022-10-12 · Tao Yang, Jinghao Deng, Xiaojun Quan, Qifan Wang 외

Fine-tuning large pre-trained language models on downstream tasks is apt to suffer from overfitting when limited training data is available. While dropout proves to be an effective antidote by randomly dropping a proport…

Language ModelingLanguage Modelling

GraphConnect: A Regularization Framework for Neural Networks

2015-12-21 · Jiaji Huang, Qiang Qiu, Robert Calderbank, Guillermo Sapiro

Deep neural networks have proved very successful in domains where large training sets are available, but when the number of training samples is small, their performance suffers from overfitting. Prior methods of reducing…

FedLoDrop: Federated LoRA with Dropout for Generalized LLM Fine-tuning

2025-10-14 · Sijing Xie, Dingzhu Wen, Changsheng You, Qimei Chen 외 arxiv

Fine-tuning (FT) large language models (LLMs) is crucial for adapting general-purpose models to specific tasks, enhancing accuracy and relevance with minimal resources. To further enhance generalization ability while red…

ZeroLiers: Diminishing Large Outliers in ReLU-like Activations

2021-09-29 · Yeha Kim, Wookeun Jung, Jaejin Lee

As the number of learnable parameters is getting bigger and bigger, overfitting is still one of the main challenges in training DNNs. Even though DNNs with billions or even a few hundred billions of parameters are propos…