Supervised Models Can Generalize Also When Trained on Random Labels

• URL: http://arxiv.org/abs/2505.11006v2
• Date: Thu, 22 May 2025 06:49:56 GMT
• Title: Supervised Models Can Generalize Also When Trained on Random Labels
• Authors: Oskar Allerbo, Thomas B. Schön,
• Abstract summary: unsupervised learning raises the question of whether also supervised models can be trained without using the information in the output $y$.<n>We formulate the model as a smoother, i.e. on the form $hatf=Sy$, and to construct the smoother matrix $S$ independently of $y$.<n>We demonstrate that $y$-free trained versions of linear and kernel ridge regression, smoothing splines, and neural networks perform similarly to their standard, $y$-based, versions and, most importantly, significantly better than random guessing.
• Score: 11.11462289882034
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The success of unsupervised learning raises the question of whether also supervised models can be trained without using the information in the output $y$. In this paper, we demonstrate that this is indeed possible. The key step is to formulate the model as a smoother, i.e. on the form $\hat{f}=Sy$, and to construct the smoother matrix $S$ independently of $y$, e.g. by training on random labels. We present a simple model selection criterion based on the distribution of the out-of-sample predictions and show that, in contrast to cross-validation, this criterion can be used also without access to $y$. We demonstrate on real and synthetic data that $y$-free trained versions of linear and kernel ridge regression, smoothing splines, and neural networks perform similarly to their standard, $y$-based, versions and, most importantly, significantly better than random guessing.

Related papers

• Aligning Model Properties via Conformal Risk Control [4.710921988115686]
  Post-training alignment via human feedback shows promise, but is often limited to generative AI settings. In traditional non-generative settings with numerical or categorical outputs, detecting misalignment through single-sample outputs remains challenging. We propose interpreting model alignment through property testing, defining an aligned model $f$ as one belonging to a subset $mathcalP$ of functions.
  arXiv  Detail & Related papers  (2024-06-26T22:24:46Z)
• Towards a statistical theory of data selection under weak supervision [7.540077751816086]
  Given a sample of size $N$, it is often useful to select a subsample of smaller size $nN$ to be used for statistical estimation or learning. We assume to be given $N$ unlabeled samples $bold x_i_ile N$, and to be given access to a surrogate model' that can predict labels $y_i$ better than random guessing.
  arXiv  Detail & Related papers  (2023-09-25T22:23:27Z)
• Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels [61.97359362447732]
  Learning from noisy labels is an important and long-standing problem in machine learning for real applications. In this paper, we reformulate the label-noise problem from a generative-model perspective. Our model achieves new state-of-the-art (SOTA) results on all the standard real-world benchmark datasets.
  arXiv  Detail & Related papers  (2023-05-31T03:01:36Z)
• CARD: Classification and Regression Diffusion Models [51.0421331214229]
  We introduce classification and regression diffusion (CARD) models, which combine a conditional generative model and a pre-trained conditional mean estimator. We demonstrate the outstanding ability of CARD in conditional distribution prediction with both toy examples and real-world datasets.
  arXiv  Detail & Related papers  (2022-06-15T03:30:38Z)
• What Makes A Good Fisherman? Linear Regression under Self-Selection Bias [32.6588421908864]
  In the classical setting of self-selection, the goal is to learn $k$ models, simultaneously from observations $(x(i), y(i))$. In this work, we present the first computationally and statistically efficient estimation algorithms for the most standard setting of this problem where the models are linear.
  arXiv  Detail & Related papers  (2022-05-06T14:03:05Z)
• $p$-Generalized Probit Regression and Scalable Maximum Likelihood Estimation via Sketching and Coresets [74.37849422071206]
  We study the $p$-generalized probit regression model, which is a generalized linear model for binary responses. We show how the maximum likelihood estimator for $p$-generalized probit regression can be approximated efficiently up to a factor of $(1+varepsilon)$ on large data.
  arXiv  Detail & Related papers  (2022-03-25T10:54:41Z)
• Datamodels: Predicting Predictions from Training Data [86.66720175866415]
  We present a conceptual framework, datamodeling, for analyzing the behavior of a model class in terms of the training data. We show that even simple linear datamodels can successfully predict model outputs.
  arXiv  Detail & Related papers  (2022-02-01T18:15:24Z)
• Cross-Model Pseudo-Labeling for Semi-Supervised Action Recognition [98.25592165484737]
  We propose a more effective pseudo-labeling scheme, called Cross-Model Pseudo-Labeling (CMPL) CMPL achieves $17.6%$ and $25.1%$ Top-1 accuracy on Kinetics-400 and UCF-101 using only the RGB modality and $1%$ labeled data, respectively.
  arXiv  Detail & Related papers  (2021-12-17T18:59:41Z)
• Analysis of One-Hidden-Layer Neural Networks via the Resolvent Method [0.0]
  Motivated by random neural networks, we consider the random matrix $M = Y Yast$ with $Y = f(WX)$. We prove that the Stieltjes transform of the limiting spectral distribution satisfies a quartic self-consistent equation up to some error terms. In addition, we extend the previous results to the case of additive bias $Y=f(WX+B)$ with $B$ being an independent rank-one Gaussian random matrix.
  arXiv  Detail & Related papers  (2021-05-11T15:17:39Z)
• Improving Robustness and Generality of NLP Models Using Disentangled Representations [62.08794500431367]
  Supervised neural networks first map an input $x$ to a single representation $z$, and then map $z$ to the output label $y$. We present methods to improve robustness and generality of NLP models from the standpoint of disentangled representation learning. We show that models trained with the proposed criteria provide better robustness and domain adaptation ability in a wide range of supervised learning tasks.
  arXiv  Detail & Related papers  (2020-09-21T02:48:46Z)

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.