Bayes' Power for Explaining In-Context Learning Generalizations
- URL: http://arxiv.org/abs/2410.01565v1
- Date: Wed, 2 Oct 2024 14:01:34 GMT
- Title: Bayes' Power for Explaining In-Context Learning Generalizations
- Authors: Samuel Müller, Noah Hollmann, Frank Hutter,
- Abstract summary: In this paper, we argue that a more useful interpretation of neural network behavior in this era is as an approximation of the true posterior.
We show how models become robust in-context learners by effectively composing knowledge from their training data.
- Score: 46.17844703369127
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Traditionally, neural network training has been primarily viewed as an approximation of maximum likelihood estimation (MLE). This interpretation originated in a time when training for multiple epochs on small datasets was common and performance was data bound; but it falls short in the era of large-scale single-epoch trainings ushered in by large self-supervised setups, like language models. In this new setup, performance is compute-bound, but data is readily available. As models became more powerful, in-context learning (ICL), i.e., learning in a single forward-pass based on the context, emerged as one of the dominant paradigms. In this paper, we argue that a more useful interpretation of neural network behavior in this era is as an approximation of the true posterior, as defined by the data-generating process. We demonstrate this interpretations' power for ICL and its usefulness to predict generalizations to previously unseen tasks. We show how models become robust in-context learners by effectively composing knowledge from their training data. We illustrate this with experiments that reveal surprising generalizations, all explicable through the exact posterior. Finally, we show the inherent constraints of the generalization capabilities of posteriors and the limitations of neural networks in approximating these posteriors.
Related papers
- Simplicity Bias of Two-Layer Networks beyond Linearly Separable Data [4.14360329494344]
We characterize simplicity bias for general datasets in the context of two-layer neural networks with small weights and trained with gradient flow.
For datasets with an XOR-like pattern, we precisely identify the learned features and demonstrate that simplicity bias intensifies during later training stages.
These results indicate that features learned in the middle stages of training may be more useful for OOD transfer.
arXiv Detail & Related papers (2024-05-27T16:00:45Z) - A Dynamical Model of Neural Scaling Laws [79.59705237659547]
We analyze a random feature model trained with gradient descent as a solvable model of network training and generalization.
Our theory shows how the gap between training and test loss can gradually build up over time due to repeated reuse of data.
arXiv Detail & Related papers (2024-02-02T01:41:38Z) - Relearning Forgotten Knowledge: on Forgetting, Overfit and Training-Free
Ensembles of DNNs [9.010643838773477]
We introduce a novel score for quantifying overfit, which monitors the forgetting rate of deep models on validation data.
We show that overfit can occur with and without a decrease in validation accuracy, and may be more common than previously appreciated.
We use our observations to construct a new ensemble method, based solely on the training history of a single network, which provides significant improvement without any additional cost in training time.
arXiv Detail & Related papers (2023-10-17T09:22:22Z) - Learn, Unlearn and Relearn: An Online Learning Paradigm for Deep Neural
Networks [12.525959293825318]
We introduce Learn, Unlearn, and Relearn (LURE) an online learning paradigm for deep neural networks (DNNs)
LURE interchanges between the unlearning phase, which selectively forgets the undesirable information in the model, and the relearning phase, which emphasizes learning on generalizable features.
We show that our training paradigm provides consistent performance gains across datasets in both classification and few-shot settings.
arXiv Detail & Related papers (2023-03-18T16:45:54Z) - Neural networks trained with SGD learn distributions of increasing
complexity [78.30235086565388]
We show that neural networks trained using gradient descent initially classify their inputs using lower-order input statistics.
We then exploit higher-order statistics only later during training.
We discuss the relation of DSB to other simplicity biases and consider its implications for the principle of universality in learning.
arXiv Detail & Related papers (2022-11-21T15:27:22Z) - Harnessing the Power of Explanations for Incremental Training: A
LIME-Based Approach [6.244905619201076]
In this work, model explanations are fed back to the feed-forward training to help the model generalize better.
The framework incorporates the custom weighted loss with Elastic Weight Consolidation (EWC) to maintain performance in sequential testing sets.
The proposed custom training procedure results in a consistent enhancement of accuracy ranging from 0.5% to 1.5% throughout all phases of the incremental learning setup.
arXiv Detail & Related papers (2022-11-02T18:16:17Z) - Dynamic Inference with Neural Interpreters [72.90231306252007]
We present Neural Interpreters, an architecture that factorizes inference in a self-attention network as a system of modules.
inputs to the model are routed through a sequence of functions in a way that is end-to-end learned.
We show that Neural Interpreters perform on par with the vision transformer using fewer parameters, while being transferrable to a new task in a sample efficient manner.
arXiv Detail & Related papers (2021-10-12T23:22:45Z) - Reasoning-Modulated Representations [85.08205744191078]
We study a common setting where our task is not purely opaque.
Our approach paves the way for a new class of data-efficient representation learning.
arXiv Detail & Related papers (2021-07-19T13:57:13Z) - Omni-supervised Facial Expression Recognition via Distilled Data [120.11782405714234]
We propose omni-supervised learning to exploit reliable samples in a large amount of unlabeled data for network training.
We experimentally verify that the new dataset can significantly improve the ability of the learned FER model.
To tackle this, we propose to apply a dataset distillation strategy to compress the created dataset into several informative class-wise images.
arXiv Detail & Related papers (2020-05-18T09:36:51Z)
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.