Understanding Optimal Feature Transfer via a Fine-Grained Bias-Variance Analysis

• URL: http://arxiv.org/abs/2404.12481v1
• Date: Thu, 18 Apr 2024 19:33:55 GMT
• Title: Understanding Optimal Feature Transfer via a Fine-Grained Bias-Variance Analysis
• Authors: Yufan Li, Subhabrata Sen, Ben Adlam,
• Abstract summary: We explore transfer learning with the goal of optimizing downstream performance. We introduce a simple linear model that takes as input an arbitrary pretrained feature. We identify the optimal pretrained representation by minimizing the downstream risk averaged over an ensemble of downstream tasks.
• Score: 10.79615566320291
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In the transfer learning paradigm models learn useful representations (or features) during a data-rich pretraining stage, and then use the pretrained representation to improve model performance on data-scarce downstream tasks. In this work, we explore transfer learning with the goal of optimizing downstream performance. We introduce a simple linear model that takes as input an arbitrary pretrained feature transform. We derive exact asymptotics of the downstream risk and its fine-grained bias-variance decomposition. Our finding suggests that using the ground-truth featurization can result in "double-divergence" of the asymptotic risk, indicating that it is not necessarily optimal for downstream performance. We then identify the optimal pretrained representation by minimizing the asymptotic downstream risk averaged over an ensemble of downstream tasks. Our analysis reveals the relative importance of learning the task-relevant features and structures in the data covariates and characterizes how each contributes to controlling the downstream risk from a bias-variance perspective. Moreover, we uncover a phase transition phenomenon where the optimal pretrained representation transitions from hard to soft selection of relevant features and discuss its connection to principal component regression.

Related papers

• Non-asymptotic Convergence of Training Transformers for Next-token Prediction [48.9399496805422]
  Transformers have achieved extraordinary success in modern machine learning due to their excellent ability to handle sequential data. This paper provides a fine-grained non-asymptotic analysis of the training dynamics of a one-layer transformer. We show that the trained transformer presents non-token prediction ability with dataset shift.
  arXiv  Detail & Related papers  (2024-09-25T20:22:06Z)
• Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization [77.62516752323207]
  We introduce an orthogonal fine-tuning method for efficiently fine-tuning pretrained weights and enabling enhanced robustness and generalization. A self-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs, dubbed OrthSR. For the first time, we revisit the CLIP and CoOp with our method to effectively improve the model on few-shot image classficiation scenario.
  arXiv  Detail & Related papers  (2024-07-11T10:35:53Z)
• Learning on Transformers is Provable Low-Rank and Sparse: A One-layer Analysis [63.66763657191476]
  We show that efficient numerical training and inference algorithms as low-rank computation have impressive performance for learning Transformer-based adaption. We analyze how magnitude-based models affect generalization while improving adaption. We conclude that proper magnitude-based has a slight on the testing performance.
  arXiv  Detail & Related papers  (2024-06-24T23:00:58Z)
• Out of the Ordinary: Spectrally Adapting Regression for Covariate Shift [12.770658031721435]
  We propose a method for adapting the weights of the last layer of a pre-trained neural regression model to perform better on input data originating from a different distribution. We demonstrate how this lightweight spectral adaptation procedure can improve out-of-distribution performance for synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2023-12-29T04:15:58Z)
• On the Trade-off of Intra-/Inter-class Diversity for Supervised Pre-training [72.8087629914444]
  We study the impact of the trade-off between the intra-class diversity (the number of samples per class) and the inter-class diversity (the number of classes) of a supervised pre-training dataset. With the size of the pre-training dataset fixed, the best downstream performance comes with a balance on the intra-/inter-class diversity.
  arXiv  Detail & Related papers  (2023-05-20T16:23:50Z)
• The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning [32.15608637930748]
  We show that there exists a trade-off between the two desiderata so that one may not be able to achieve both simultaneously. We provide analysis using a theoretical data model and show that, while more diverse pre-training data result in more diverse features for different tasks, it puts less emphasis on task-specific features.
  arXiv  Detail & Related papers  (2023-02-28T22:14:33Z)
• Estimation and inference for transfer learning with high-dimensional quantile regression [3.4510296013600374]
  We propose a transfer learning procedure in the framework of high-dimensional quantile regression models. We establish error bounds of transfer learning estimator based on delicately selected transferable source domains. By adopting data-splitting technique, we advocate a transferability detection approach that guarantees to circumvent negative transfer.
  arXiv  Detail & Related papers  (2022-11-26T14:40:19Z)
• SynBench: Task-Agnostic Benchmarking of Pretrained Representations using Synthetic Data [78.21197488065177]
  Recent success in fine-tuning large models, that are pretrained on broad data at scale, on downstream tasks has led to a significant paradigm shift in deep learning. This paper proposes a new task-agnostic framework, textitSynBench, to measure the quality of pretrained representations using synthetic data.
  arXiv  Detail & Related papers  (2022-10-06T15:25:00Z)
• Self-Distillation for Further Pre-training of Transformers [83.84227016847096]
  We propose self-distillation as a regularization for a further pre-training stage. We empirically validate the efficacy of self-distillation on a variety of benchmark datasets for image and text classification tasks.
  arXiv  Detail & Related papers  (2022-09-30T02:25:12Z)
• Last Layer Marginal Likelihood for Invariance Learning [12.00078928875924]
  We introduce a new lower bound to the marginal likelihood, which allows us to perform inference for a larger class of likelihood functions. We work towards bringing this approach to neural networks by using an architecture with a Gaussian process in the last layer.
  arXiv  Detail & Related papers  (2021-06-14T15:40:51Z)
• Transfer Learning for High-dimensional Linear Regression: Prediction, Estimation, and Minimax Optimality [6.230751621285322]
  It is shown that Trans-Lasso leads to improved performance in gene expression prediction in a target tissue by incorporating the data from multiple different tissues as auxiliary samples.
  arXiv  Detail & Related papers  (2020-06-18T14:55:29Z)

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.