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

• URL: http://arxiv.org/abs/2410.19675v1
• Date: Fri, 25 Oct 2024 16:32:11 GMT
• Title: Learning the Regularization Strength for Deep Fine-Tuning via a Data-Emphasized Variational Objective
• Authors: Ethan Harvey, Mikhail Petrov, Michael C. Hughes,
• Abstract summary: grid search is computationally expensive, requires carving out a validation set, and requires practitioners to specify candidate values. 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.
• Score: 4.453137996095194
• License:
• Abstract: 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.

Related papers

• TSDS: Data Selection for Task-Specific Model Finetuning [39.19448080265558]
  The efficacy of task-specific finetuning largely depends on the selection of appropriate training data. We present TSDS (Task-Specific Data Selection), a framework to select data for task-specific model finetuning. We show that instruction tuning using data selected by our method with a 1% selection ratio often outperforms using the full dataset.
  arXiv  Detail & Related papers  (2024-10-15T05:54:17Z)
• Adapt-$\infty$: Scalable Lifelong Multimodal Instruction Tuning via Dynamic Data Selection [89.42023974249122]
  Adapt-$infty$ is a new multi-way and adaptive data selection approach for Lifelong Instruction Tuning. We construct pseudo-skill clusters by grouping gradient-based sample vectors. We select the best-performing data selector for each skill cluster from a pool of selector experts.
  arXiv  Detail & Related papers  (2024-10-14T15:48:09Z)
• SKADA-Bench: Benchmarking Unsupervised Domain Adaptation Methods with Realistic Validation [55.87169702896249]
  Unsupervised Domain Adaptation (DA) consists of adapting a model trained on a labeled source domain to perform well on an unlabeled target domain with some data distribution shift. We propose a framework to evaluate DA methods and present a fair evaluation of existing shallow algorithms, including reweighting, mapping, and subspace alignment. Our benchmark highlights the importance of realistic validation and provides practical guidance for real-life applications.
  arXiv  Detail & Related papers  (2024-07-16T12:52:29Z)
• Towards Free Data Selection with General-Purpose Models [71.92151210413374]
  A desirable data selection algorithm can efficiently choose the most informative samples to maximize the utility of limited annotation budgets. Current approaches, represented by active learning methods, typically follow a cumbersome pipeline that iterates the time-consuming model training and batch data selection repeatedly. FreeSel bypasses the heavy batch selection process, achieving a significant improvement in efficiency and being 530x faster than existing active learning methods.
  arXiv  Detail & Related papers  (2023-09-29T15:50:14Z)
• Complementary Learning Subnetworks for Parameter-Efficient Class-Incremental Learning [40.13416912075668]
  We propose a rehearsal-free CIL approach that learns continually via the synergy between two Complementary Learning Subnetworks. Our method achieves competitive results against state-of-the-art methods, especially in accuracy gain, memory cost, training efficiency, and task-order.
  arXiv  Detail & Related papers  (2023-06-21T01:43:25Z)
• MILO: Model-Agnostic Subset Selection Framework for Efficient Model Training and Tuning [68.12870241637636]
  We propose MILO, a model-agnostic subset selection framework that decouples the subset selection from model training. Our empirical results indicate that MILO can train models $3times - 10 times$ faster and tune hyperparameters $20times - 75 times$ faster than full-dataset training or tuning without performance.
  arXiv  Detail & Related papers  (2023-01-30T20:59:30Z)
• Learning to Learn with Generative Models of Neural Network Checkpoints [71.06722933442956]
  We construct a dataset of neural network checkpoints and train a generative model on the parameters. We find that our approach successfully generates parameters for a wide range of loss prompts. We apply our method to different neural network architectures and tasks in supervised and reinforcement learning.
  arXiv  Detail & Related papers  (2022-09-26T17:59:58Z)
• CAFA: Class-Aware Feature Alignment for Test-Time Adaptation [50.26963784271912]
  Test-time adaptation (TTA) aims to address this challenge by adapting a model to unlabeled data at test time. We propose a simple yet effective feature alignment loss, termed as Class-Aware Feature Alignment (CAFA), which simultaneously encourages a model to learn target representations in a class-discriminative manner.
  arXiv  Detail & Related papers  (2022-06-01T03:02:07Z)
• Finding High-Value Training Data Subset through Differentiable Convex Programming [5.5180456567480896]
  In this paper, we study the problem of selecting high-value subsets of training data. The key idea is to design a learnable framework for online subset selection. Using this framework, we design an online alternating minimization-based algorithm for jointly learning the parameters of the selection model and ML model.
  arXiv  Detail & Related papers  (2021-04-28T14:33:26Z)
• ABM: an automatic supervised feature engineering method for loss based models based on group and fused lasso [0.0]
  A vital problem in solving classification or regression problem is to apply feature engineering and variable selection on data before fed into models. This paper proposes an end-to-end supervised cutting point selection method based on group and lasso fused along with the automatically variable selection effect.
  arXiv  Detail & Related papers  (2020-09-22T12:42:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.