Learning from Synthetic Data: Limitations of ERM

• URL: http://arxiv.org/abs/2601.15468v1
• Date: Wed, 21 Jan 2026 21:07:16 GMT
• Title: Learning from Synthetic Data: Limitations of ERM
• Abstract summary: From review sites to court documents, natural'' content has been contaminated by data points that appear similar to natural data, but are in fact LLM-generated.<n>We model this scenario as a sequence of learning tasks where the input is a mix of natural and synthetic data.<n>We show there are algorithms capable of learning the correct hypothesis for arbitrary VC classes and arbitrary amounts of contamination.
• Score: 19.496543753860944
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The prevalence and low cost of LLMs have led to a rise of synthetic content. From review sites to court documents, ``natural'' content has been contaminated by data points that appear similar to natural data, but are in fact LLM-generated. In this work we revisit fundamental learning theory questions in this, now ubiquitous, setting. We model this scenario as a sequence of learning tasks where the input is a mix of natural and synthetic data, and the learning algorithms are oblivious to the origin of any individual example. We study the possibilities and limitations of ERM in this setting. For the problem of estimating the mean of an arbitrary $d$-dimensional distribution, we find that while ERM converges to the true mean, it is outperformed by an algorithm that assigns non-uniform weights to examples from different generations of data. For the PAC learning setting, the disparity is even more stark. We find that ERM does not always converge to the true concept, echoing the model collapse literature. However, we show there are algorithms capable of learning the correct hypothesis for arbitrary VC classes and arbitrary amounts of contamination.

Related papers

• Proper Learnability and the Role of Unlabeled Data [10.168670899305232]
  We show that there are problems whose proper learnability is logically undecidable, i.e., independent of the ZFC axioms.<n>We then show all impossibility results which obstruct any characterization of proper learnability in the realizable PAC model.
  arXiv  Detail & Related papers  (2025-02-14T18:41:53Z)
• Understanding Self-Supervised Learning via Gaussian Mixture Models [19.51336063093898]
  We analyze self-supervised learning in a natural context: dimensionality reduction in Gaussian Mixture Models.<n>We show that vanilla contrastive learning is able to find the optimal lower-dimensional subspace even when the Gaussians are not isotropic.<n>In this setting we show that contrastive learning learns the subset of fisher-optimal subspace, effectively filtering out all the noise from the learnt representations.
  arXiv  Detail & Related papers  (2024-11-05T21:43:05Z)
• Prospective Learning: Learning for a Dynamic Future [30.449933525877537]
  In real-world applications, the distribution of the data, and our goals evolve over time.<n>Existing strategies to address the dynamic nature of data and goals exhibit poor real-world performance.<n>"Prospective Learning" is tailored for situations when the optimal hypothesis changes over time.
  arXiv  Detail & Related papers  (2024-10-31T18:03:17Z)
• Collapse or Thrive? Perils and Promises of Synthetic Data in a Self-Generating World [19.266191284270793]
  generative machine learning models are pretrained on web-scale datasets containing data generated by earlier models.<n>Some prior work warns of "model collapse" as the web is overwhelmed by synthetic data.<n>We report experiments on three ways of using data (training-workflows) across three generative model task-settings.
  arXiv  Detail & Related papers  (2024-10-22T05:49:24Z)
• Reciprocal Learning [0.0]
  We show that a wide array of machine learning algorithms are specific instances of one single paradigm: reciprocal learning. We introduce reciprocal learning as a generalization of these algorithms using the language of decision theory. We find that reciprocal learning algorithms converge at linear rates to an approximately optimal model under relatively mild assumptions on the loss function.
  arXiv  Detail & Related papers  (2024-08-12T16:14:52Z)
• Entropy Law: The Story Behind Data Compression and LLM Performance [115.70395740286422]
  We find that model performance is negatively correlated to the compression ratio of training data, which usually yields a lower training loss. Based on the findings of the entropy law, we propose a quite efficient and universal data selection method. We also present an interesting application of entropy law that can detect potential performance risks at the beginning of model training.
  arXiv  Detail & Related papers  (2024-07-09T08:14:29Z)
• On the Performance of Empirical Risk Minimization with Smoothed Data [59.3428024282545]
  Empirical Risk Minimization (ERM) is able to achieve sublinear error whenever a class is learnable with iid data. We show that ERM is able to achieve sublinear error whenever a class is learnable with iid data.
  arXiv  Detail & Related papers  (2024-02-22T21:55:41Z)
• From Fake to Real: Pretraining on Balanced Synthetic Images to Prevent Spurious Correlations in Image Recognition [64.59093444558549]
  We propose a simple, easy-to-implement, two-step training pipeline that we call From Fake to Real. By training on real and synthetic data separately, FFR does not expose the model to the statistical differences between real and synthetic data. Our experiments show that FFR improves worst group accuracy over the state-of-the-art by up to 20% over three datasets.
  arXiv  Detail & Related papers  (2023-08-08T19:52:28Z)
• Learning from aggregated data with a maximum entropy model [73.63512438583375]
  We show how a new model, similar to a logistic regression, may be learned from aggregated data only by approximating the unobserved feature distribution with a maximum entropy hypothesis. We present empirical evidence on several public datasets that the model learned this way can achieve performances comparable to those of a logistic model trained with the full unaggregated data.
  arXiv  Detail & Related papers  (2022-10-05T09:17:27Z)
• ReLU Regression with Massart Noise [52.10842036932169]
  We study the fundamental problem of ReLU regression, where the goal is to fit Rectified Linear Units (ReLUs) to data. We focus on ReLU regression in the Massart noise model, a natural and well-studied semi-random noise model. We develop an efficient algorithm that achieves exact parameter recovery in this model.
  arXiv  Detail & Related papers  (2021-09-10T02:13:22Z)
• Mitigating Generation Shifts for Generalized Zero-Shot Learning [52.98182124310114]
  Generalized Zero-Shot Learning (GZSL) is the task of leveraging semantic information (e.g., attributes) to recognize the seen and unseen samples, where unseen classes are not observable during training. We propose a novel Generation Shifts Mitigating Flow framework for learning unseen data synthesis efficiently and effectively. Experimental results demonstrate that GSMFlow achieves state-of-the-art recognition performance in both conventional and generalized zero-shot settings.
  arXiv  Detail & Related papers  (2021-07-07T11:43:59Z)

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.