Retraining Seeks Stable Signals

• URL: http://arxiv.org/abs/2607.15623v1
• Date: Fri, 17 Jul 2026 04:48:02 GMT
• Title: Retraining Seeks Stable Signals
• Abstract summary: We show that when a nonzero stable signal exists, repeated risk minimization converges geometrically to the direction of this stable signal.<n>This is true even if the model's influence on the target is arbitrarily large relative to the stable signal.<n>Regularization emerges naturally as a force to control performativity, rather than to promote generalization.
• Score: 36.28189225382996
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Predictive models deployed at scale influence future data, a phenomenon called performativity. And there is always one way to cope: Train the model on new data, deploy it again, and repeat. This process, called retraining or repeated risk minimization, creates a feedback loop between model and data that real-world learning systems can't avoid. Results on performative prediction shed light on this dynamic: If the model's influence on the data is small, retraining reaches a fixed point. What remains open is why fixed points should naturally exist, and what governs retraining when the model's influence is strong. In this work we develop a new perspective on retraining -- the stable signal principle -- that addresses these questions. We start from the assumption that the prediction target has at least some small model-independent component, a stable signal, such as the intrinsic quality of an item. We prove that when a nonzero stable signal exists, repeated risk minimization, suitably regularized, converges geometrically to the direction of this stable signal. This is true even if the model's influence on the target is arbitrarily large relative to the stable signal. Regularization emerges naturally as a force to control performativity, rather than to promote generalization, revealing a new facet of an old concept. We extend the analysis to a broad family of affine retraining operators under arbitrary model-induced feature changes, heterogeneous time-varying effects, and nonlinear responses. The stable signal perspective also applies to data feedback loops in language modeling, providing new explanations for the stability of language model training from model-generated data.

Related papers

• Symbolic Neural ODEs: Learning interpretable models from time-series data [0.0]
  We present a machine learning framework for identifying sparse, interpretable models of dynamical systems from time-series data.<n>Our approach parameterizes the underlying vector field using a neural architecture and trains it by minimizing a multi-step prediction loss over a finite horizon.<n>We show that multi-step training yields models with accurate short-term dynamics and strong agreement in long-time statistical properties.
  arXiv  Detail & Related papers  (2026-08-22T21:31:07Z)
• Joint Model and Data Sparsification via the Marginal Likelihood [53.29070892356214]
  We propose jointly learning individual feature and sample relevancies, enabling simultaneous model and data sparsification.<n>This symmetric pruning of model and data offers a natural extension that preserves conjugacy.<n> Empirical results across diverse regression tasks affirm that a joint ARD approach consistently yields both sparse and robust prediction models.
  arXiv  Detail & Related papers  (2026-05-28T13:26:53Z)
• Self-Improving Tabular Language Models via Iterative Group Alignment [76.43372236405664]
  We introduce TabGRAA, the first self-improving framework for data generation via automated feedback.<n>It partitions newly generated samples into high- and low-quality groups, then prioritizes a group-relative advantage objective.<n>Experiments show TabGRAA outperforms existing methods in fidelity, utility, and privacy.
  arXiv  Detail & Related papers  (2026-04-21T01:29:52Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• A Probabilistic Perspective on Model Collapse [9.087950471621653]
  This paper aims to characterize the conditions under which model collapse occurs and, crucially, how it can be mitigated.<n>Under mild conditions, we rigorously show that progressively increasing the sample size at each training step is necessary to prevent model collapse.<n>We also investigate the probability that training on synthetic data yields models that outperform those trained solely on real data.
  arXiv  Detail & Related papers  (2025-05-20T05:25:29Z)
• Real-time Adaptation for Condition Monitoring Signal Prediction using Label-aware Neural Processes [3.10770247120758]
  Building a predictive model that rapidly adapts to real-time condition monitoring (CM) signals is critical for engineering systems/units. Current methods suffer from a trade-off between representation power and agility in online settings. We propose a neural process-based approach that addresses this trade-off.
  arXiv  Detail & Related papers  (2024-03-25T02:47:29Z)
• Model Collapse Demystified: The Case of Regression [12.115359951879462]
  We study the phenomenon of "model collapse" in the era of proliferation of large language and image generation models. We obtain analytic formulae which quantitatively outline this phenomenon in a broad range of regimes. We propose a simple strategy based on adaptive regularization to mitigate model collapse.
  arXiv  Detail & Related papers  (2024-02-12T15:26:01Z)
• Time-series Generation by Contrastive Imitation [87.51882102248395]
  We study a generative framework that seeks to combine the strengths of both: Motivated by a moment-matching objective to mitigate compounding error, we optimize a local (but forward-looking) transition policy. At inference, the learned policy serves as the generator for iterative sampling, and the learned energy serves as a trajectory-level measure for evaluating sample quality.
  arXiv  Detail & Related papers  (2023-11-02T16:45:25Z)
• Transfer Learning with Uncertainty Quantification: Random Effect Calibration of Source to Target (RECaST) [1.8047694351309207]
  We develop a statistical framework for model predictions based on transfer learning, called RECaST. We mathematically and empirically demonstrate the validity of our RECaST approach for transfer learning between linear models. We examine our method's performance in a simulation study and in an application to real hospital data.
  arXiv  Detail & Related papers  (2022-11-29T19:39:47Z)
• Data Feedback Loops: Model-driven Amplification of Dataset Biases [9.773315369593876]
  We formalize a system where interactions with one model are recorded as history and scraped as training data in the future. We analyze its stability over time by tracking changes to a test-time bias statistic. We find that the degree of bias amplification is closely linked to whether the model's outputs behave like samples from the training distribution.
  arXiv  Detail & Related papers  (2022-09-08T17:35:51Z)
• Probing Model Signal-Awareness via Prediction-Preserving Input Minimization [67.62847721118142]
  We evaluate models' ability to capture the correct vulnerability signals to produce their predictions. We measure the signal awareness of models using a new metric we propose- Signal-aware Recall (SAR) The results show a sharp drop in the model's Recall from the high 90s to sub-60s with the new metric.
  arXiv  Detail & Related papers  (2020-11-25T20:05:23Z)

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.