paper-with-me

Papers

Learning the Regularization Strength for Deep Fine-Tuning via a Data-Emphasized Variational Objective

2024-10-25 · Ethan Harvey, Mikhail Petrov, Michael C. Hughes

A number of popular transfer learning methods rely on grid search to select regularization hyperparameters that control over-fitting. This grid search requirement has several key disadvantages: the search is computationally expensive, requires carving out a validation set that reduces the size of available data for model training, and requires practitioners to specify candidate values. In this paper, we propose an alternative to grid search: directly learning regularization hyperparameters on the full training set via model selection techniques based on the evidence lower bound ("ELBo") objective from variational methods. For deep neural networks with millions of parameters, we specifically recommend a modified ELBo that upweights the influence of the data likelihood relative to the prior while remaining a valid bound on the evidence for Bayesian model selection. Our proposed technique overcomes all three disadvantages of grid search. We demonstrate effectiveness on image classification tasks on several datasets, yielding heldout accuracy comparable to existing approaches with far less compute time.

📄 PDF Abstract BibTeX arXiv:2410.19675

Code (1)

tufts-ml/data-emphasized-ELBo 공식 구현 pytorch

Tasks

image-classificationImage ClassificationModel SelectionTransfer Learningvalid

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

A Comparative Study on Regularization Strategies for Embedding-based Neural Networks

2015-08-15 · EMNLP 2015 9 · Hao Peng, Lili Mou, Ge Li, Yunchuan Chen 외

This paper aims to compare different regularization strategies to address a common phenomenon, severe overfitting, in embedding-based neural networks for NLP. We chose two widely studied neural models and tasks as our te…

Model Balancing Helps Low-data Training and Fine-tuning

2024-10-16 · Zihang Liu, Yuanzhe Hu, Tianyu Pang, Yefan Zhou 외

Recent advances in foundation models have emphasized the need to align pre-trained models with specialized domains using small, curated datasets. Studies on these foundation models underscore the importance of low-data t…

Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models

2019-09-25 · ICLR 2020 1 · Cheolhyoung Lee, Kyunghyun Cho, Wanmo Kang

In natural language processing, it has been observed recently that generalization could be greatly improved by finetuning a large-scale language model pretrained on a large unlabeled corpus. Despite its recent success an…

Language ModelingLanguage Modelling

DeRaDiff: Denoising Time Realignment of Diffusion Models

2026-01-28 · Ratnavibusena Don Shahain Manujith, Teoh Tze Tzun, Kenji Kawaguchi, Yang Zhang arxiv

Recent advances align diffusion models with human preferences to increase aesthetic appeal and mitigate artifacts and biases. Such methods aim to maximize a conditional output distribution aligned with higher rewards whi…

Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models

2025-10-20 · Jiajun Fan, Tong Wei, Chaoran Cheng, Yuxin Chen 외 arxiv

Balancing exploration and exploitation during reinforcement learning fine-tuning of generative models presents a critical challenge, as existing approaches rely on fixed divergence regularization that creates an inherent…

Text-to-Image GenerationReinforcement LearningStyle Transfer