How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?
- URL: http://arxiv.org/abs/2310.08391v2
- Date: Fri, 15 Mar 2024 02:01:17 GMT
- Title: How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?
- Authors: Jingfeng Wu, Difan Zou, Zixiang Chen, Vladimir Braverman, Quanquan Gu, Peter L. Bartlett,
- Abstract summary: Transformers pretrained on diverse tasks exhibit remarkable in-context learning (ICL) capabilities.
We study ICL in one of its simplest setups: pretraining a linearly parameterized single-layer linear attention model for linear regression.
- Score: 92.90857135952231
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Transformers pretrained on diverse tasks exhibit remarkable in-context learning (ICL) capabilities, enabling them to solve unseen tasks solely based on input contexts without adjusting model parameters. In this paper, we study ICL in one of its simplest setups: pretraining a linearly parameterized single-layer linear attention model for linear regression with a Gaussian prior. We establish a statistical task complexity bound for the attention model pretraining, showing that effective pretraining only requires a small number of independent tasks. Furthermore, we prove that the pretrained model closely matches the Bayes optimal algorithm, i.e., optimally tuned ridge regression, by achieving nearly Bayes optimal risk on unseen tasks under a fixed context length. These theoretical findings complement prior experimental research and shed light on the statistical foundations of ICL.
Related papers
- Asymptotic theory of in-context learning by linear attention [33.53106537972063]
In-context learning is a cornerstone of Transformers' success.
Questions about the necessary sample complexity, pretraining task diversity, and context length for successful ICL remain unresolved.
arXiv Detail & Related papers (2024-05-20T03:24:24Z) - The Fine Line: Navigating Large Language Model Pretraining with Down-streaming Capability Analysis [60.52921835351632]
This paper undertakes a comprehensive comparison of model capabilities at various pretraining intermediate checkpoints.
We confirm that specific downstream metrics exhibit similar training dynamics across models of different sizes.
In addition to our core findings, we've reproduced Amber and OpenLLaMA, releasing their intermediate checkpoints.
arXiv Detail & Related papers (2024-04-01T16:00:01Z) - Towards Stable Machine Learning Model Retraining via Slowly Varying Sequences [6.067007470552307]
We propose a methodology for finding sequences of machine learning models that are stable across retraining iterations.
We develop a mixed-integer optimization formulation that is guaranteed to recover optimal models.
Our method shows stronger stability than greedily trained models with a small, controllable sacrifice in predictive power.
arXiv Detail & Related papers (2024-03-28T22:45:38Z) - Pretraining task diversity and the emergence of non-Bayesian in-context
learning for regression [31.950737940558984]
Pretrained transformers exhibit the remarkable ability of in-context learning (ICL)
Can ICL solve fundamentally $textitnew$ tasks that are very different from those seen during pretraining?
arXiv Detail & Related papers (2023-06-26T21:05:20Z) - Theoretical Characterization of the Generalization Performance of
Overfitted Meta-Learning [70.52689048213398]
This paper studies the performance of overfitted meta-learning under a linear regression model with Gaussian features.
We find new and interesting properties that do not exist in single-task linear regression.
Our analysis suggests that benign overfitting is more significant and easier to observe when the noise and the diversity/fluctuation of the ground truth of each training task are large.
arXiv Detail & Related papers (2023-04-09T20:36:13Z) - 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) - Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than
In-Context Learning [81.3514358542452]
Few-shot in-context learning (ICL) incurs substantial computational, memory, and storage costs because it involves processing all of the training examples every time a prediction is made.
parameter-efficient fine-tuning offers an alternative paradigm where a small set of parameters are trained to enable a model to perform the new task.
In this paper, we rigorously compare few-shot ICL and parameter-efficient fine-tuning and demonstrate that the latter offers better accuracy as well as dramatically lower computational costs.
arXiv Detail & Related papers (2022-05-11T17:10:41Z) - Training Data Subset Selection for Regression with Controlled
Generalization Error [19.21682938684508]
We develop an efficient majorization-minimization algorithm for data subset selection.
SELCON trades off accuracy and efficiency more effectively than the current state-of-the-art.
arXiv Detail & Related papers (2021-06-23T16:03:55Z) - Active Learning for Sequence Tagging with Deep Pre-trained Models and
Bayesian Uncertainty Estimates [52.164757178369804]
Recent advances in transfer learning for natural language processing in conjunction with active learning open the possibility to significantly reduce the necessary annotation budget.
We conduct an empirical study of various Bayesian uncertainty estimation methods and Monte Carlo dropout options for deep pre-trained models in the active learning framework.
We also demonstrate that to acquire instances during active learning, a full-size Transformer can be substituted with a distilled version, which yields better computational performance.
arXiv Detail & Related papers (2021-01-20T13:59:25Z) - Meta Learning MPC using Finite-Dimensional Gaussian Process
Approximations [0.9539495585692008]
Two key factors that hinder the practical applicability of learning methods in control are their high computational complexity and limited generalization capabilities to unseen conditions.
This paper makes use of a meta-learning approach for adaptive model predictive control, by learning a system model that leverages data from previous related tasks.
arXiv Detail & Related papers (2020-08-13T15:59:38Z)
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.