Learning the Regularization Strength for Deep Fine-Tuning via a Data-Emphasized Variational Objective
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.
Code (1)
Tasks
image-classificationImage ClassificationModel SelectionTransfer LearningvalidMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Comparative Study on Regularization Strategies for Embedding-based Neural Networks
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
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
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 ModellingDeRaDiff: Denoising Time Realignment of Diffusion Models
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
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