Generalization vs. Specialization under Concept Shift

• URL: http://arxiv.org/abs/2409.15582v2
• Date: Thu, 03 Jul 2025 05:05:13 GMT
• Title: Generalization vs. Specialization under Concept Shift
• Authors: Alex Nguyen, David J. Schwab, Vudtiwat Ngampruetikorn,
• Abstract summary: We analyze ridge regression under concept shift.<n>We derive an exact expression for prediction risk in the thermodynamic limit.<n>Our experiments on MNIST and FashionMNIST suggest that this intriguing behavior is present also in classification problems.
• Score: 12.196508752999797
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine learning models are often brittle under distribution shift, i.e., when data distributions at test time differ from those during training. Understanding this failure mode is central to identifying and mitigating safety risks of mass adoption of machine learning. Here we analyze ridge regression under concept shift -- a form of distribution shift in which the input-label relationship changes at test time. We derive an exact expression for prediction risk in the thermodynamic limit. Our results reveal nontrivial effects of concept shift on generalization performance, including a phase transition between weak and strong concept shift regimes and nonmonotonic data dependence of test performance even when double descent is absent. Our theoretical results are in good agreement with experiments based on transformers pretrained to solve linear regression; under concept shift, too long context length can be detrimental to generalization performance of next token prediction. Finally, our experiments on MNIST and FashionMNIST suggest that this intriguing behavior is present also in classification problems.

Related papers

• One-Layer Transformers are Provably Optimal for In-context Reasoning and Distributional Association Learning in Next-Token Prediction Tasks [11.06955946904705]
  We study the approximation capabilities and on-convergence behaviors of one-layer transformers on the noiseless and noisy in-context reasoning of next-token prediction.<n>Our work addresses gaps by showing that there exists a class of one-layer transformers that are provably Bayes-optimal with both linear and ReLU attention.
  arXiv  Detail & Related papers  (2025-05-21T01:26:44Z)
• Beyond Progress Measures: Theoretical Insights into the Mechanism of Grokking [50.465604300990904]
  Grokking refers to the abrupt improvement in test accuracy after extended overfitting.<n>In this work, we investigate the grokking mechanism underlying the Transformer in the task of prime number operations.
  arXiv  Detail & Related papers  (2025-04-04T04:42:38Z)
• Multiple Descents in Unsupervised Learning: The Role of Noise, Domain Shift and Anomalies [14.399035468023161]
  We study the presence of double descent in unsupervised learning, an area that has received little attention and is not yet fully understood. We use synthetic and real data and identify model-wise, epoch-wise, and sample-wise double descent for various applications.
  arXiv  Detail & Related papers  (2024-06-17T16:24:23Z)
• Exploring Data Augmentations on Self-/Semi-/Fully- Supervised Pre-trained Models [24.376036129920948]
  We investigate how data augmentation affects performance of vision pre-trained models. We apply 4 types of data augmentations termed with Random Erasing, CutOut, CutMix and MixUp. We report their performance on vision tasks such as image classification, object detection, instance segmentation, and semantic segmentation.
  arXiv  Detail & Related papers  (2023-10-28T23:46:31Z)
• GIT: Detecting Uncertainty, Out-Of-Distribution and Adversarial Samples using Gradients and Invariance Transformations [77.34726150561087]
  We propose a holistic approach for the detection of generalization errors in deep neural networks. GIT combines the usage of gradient information and invariance transformations. Our experiments demonstrate the superior performance of GIT compared to the state-of-the-art on a variety of network architectures.
  arXiv  Detail & Related papers  (2023-07-05T22:04:38Z)
• Even Small Correlation and Diversity Shifts Pose Dataset-Bias Issues [19.4921353136871]
  We study two types of distribution shifts: diversity shifts, which occur when test samples exhibit patterns unseen during training, and correlation shifts, which occur when test data present a different correlation between seen invariant and spurious features. We propose an integrated protocol to analyze both types of shifts using datasets where they co-exist in a controllable manner.
  arXiv  Detail & Related papers  (2023-05-09T23:40:23Z)
• Adapting to Continuous Covariate Shift via Online Density Ratio Estimation [64.8027122329609]
  Dealing with distribution shifts is one of the central challenges for modern machine learning. We propose an online method that can appropriately reuse historical information. Our density ratio estimation method is proven to perform well by enjoying a dynamic regret bound.
  arXiv  Detail & Related papers  (2023-02-06T04:03:33Z)
• Modeling Uncertain Feature Representation for Domain Generalization [49.129544670700525]
  We show that our method consistently improves the network generalization ability on multiple vision tasks. Our methods are simple yet effective and can be readily integrated into networks without additional trainable parameters or loss constraints.
  arXiv  Detail & Related papers  (2023-01-16T14:25:02Z)
• A Learning Based Hypothesis Test for Harmful Covariate Shift [3.1406146587437904]
  Machine learning systems in high-risk domains need to identify when predictions should not be made on out-of-distribution test examples. In this work, we use the discordance between an ensemble of classifiers trained to agree on training data and disagree on test data to determine when a model should be removed from the deployment setting.
  arXiv  Detail & Related papers  (2022-12-06T04:15:24Z)
• Blessings and Curses of Covariate Shifts: Adversarial Learning Dynamics, Directional Convergence, and Equilibria [6.738946307589742]
  Covariate distribution shifts and adversarial perturbations present challenges to the conventional statistical learning framework. This paper precisely characterizes the extrapolation region, examining both regression and classification in an infinite-dimensional setting.
  arXiv  Detail & Related papers  (2022-12-05T18:00:31Z)
• Tracking changes using Kullback-Leibler divergence for the continual learning [2.0305676256390934]
  This article introduces a novel method for monitoring changes in the probabilistic distribution of multi-dimensional data streams. As a measure of the rapidity of changes, we analyze the popular Kullback-Leibler divergence. We show how to use this metric to predict the concept drift occurrence and understand its nature.
  arXiv  Detail & Related papers  (2022-10-10T17:30:41Z)
• Uncertainty Modeling for Out-of-Distribution Generalization [56.957731893992495]
  We argue that the feature statistics can be properly manipulated to improve the generalization ability of deep learning models. Common methods often consider the feature statistics as deterministic values measured from the learned features. We improve the network generalization ability by modeling the uncertainty of domain shifts with synthesized feature statistics during training.
  arXiv  Detail & Related papers  (2022-02-08T16:09:12Z)
• A heteroencoder architecture for prediction of failure locations in porous metals using variational inference [1.2722697496405462]
  We employ an encoder-decoder convolutional neural network to predict the failure locations of porous metal tension specimens. The objective of predicting failure locations presents an extreme case of class imbalance since most of the material in the specimens do not fail. We demonstrate that the resulting predicted variances are effective in ranking the locations that are most likely to fail in any given specimen.
  arXiv  Detail & Related papers  (2022-01-31T20:26:53Z)
• SLA$^2$P: Self-supervised Anomaly Detection with Adversarial Perturbation [77.71161225100927]
  Anomaly detection is a fundamental yet challenging problem in machine learning. We propose a novel and powerful framework, dubbed as SLA$2$P, for unsupervised anomaly detection.
  arXiv  Detail & Related papers  (2021-11-25T03:53:43Z)
• Covariate Shift in High-Dimensional Random Feature Regression [44.13449065077103]
  Covariate shift is a significant obstacle in the development of robust machine learning models. We present a theoretical understanding in context of modern machine learning.
  arXiv  Detail & Related papers  (2021-11-16T05:23:28Z)
• Evaluating Predictive Uncertainty and Robustness to Distributional Shift Using Real World Data [0.0]
  We propose metrics for general regression tasks using the Shifts Weather Prediction dataset. We also present an evaluation of the baseline methods using these metrics.
  arXiv  Detail & Related papers  (2021-11-08T17:32:10Z)
• Tracking the risk of a deployed model and detecting harmful distribution shifts [105.27463615756733]
  In practice, it may make sense to ignore benign shifts, under which the performance of a deployed model does not degrade substantially. We argue that a sensible method for firing off a warning has to both (a) detect harmful shifts while ignoring benign ones, and (b) allow continuous monitoring of model performance without increasing the false alarm rate.
  arXiv  Detail & Related papers  (2021-10-12T17:21:41Z)
• Training on Test Data with Bayesian Adaptation for Covariate Shift [96.3250517412545]
  Deep neural networks often make inaccurate predictions with unreliable uncertainty estimates. We derive a Bayesian model that provides for a well-defined relationship between unlabeled inputs under distributional shift and model parameters. We show that our method improves both accuracy and uncertainty estimation.
  arXiv  Detail & Related papers  (2021-09-27T01:09:08Z)
• Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Tests [87.60900567941428]
  A spurious correlation' is the dependence of a model on some aspect of the input data that an analyst thinks shouldn't matter. In machine learning, these have a know-it-when-you-see-it character. We study stress testing using the tools of causal inference.
  arXiv  Detail & Related papers  (2021-05-31T14:39:38Z)
• Balance-Subsampled Stable Prediction [55.13512328954456]
  We propose a novel balance-subsampled stable prediction (BSSP) algorithm based on the theory of fractional factorial design. A design-theoretic analysis shows that the proposed method can reduce the confounding effects among predictors induced by the distribution shift. Numerical experiments on both synthetic and real-world data sets demonstrate that our BSSP algorithm significantly outperforms the baseline methods for stable prediction across unknown test data.
  arXiv  Detail & Related papers  (2020-06-08T07:01:38Z)
• Regularizing Class-wise Predictions via Self-knowledge Distillation [80.76254453115766]
  We propose a new regularization method that penalizes the predictive distribution between similar samples. This results in regularizing the dark knowledge (i.e., the knowledge on wrong predictions) of a single network. Our experimental results on various image classification tasks demonstrate that the simple yet powerful method can significantly improve the generalization ability.
  arXiv  Detail & Related papers  (2020-03-31T06:03:51Z)

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.