Predicting Deep Neural Network Training Outcomes from Early Training Telemetry

• URL: http://arxiv.org/abs/2608.03709v1
• Date: Tue, 04 Aug 2026 14:13:21 GMT
• Title: Predicting Deep Neural Network Training Outcomes from Early Training Telemetry
• Abstract summary: We study whether a single training run's own early telemetry can predict that run's eventual outcome without reference to other runs.<n>Across 23,788 training runs spanning six architecture/dataset combinations, gradient-boosted trees using only the first five epochs of telemetry achieve R2 = 0.92-0.99 for final-accuracy regression.<n>These results suggest that early-training telemetry can provide a practical decision-support signal for compute allocation.
• Score: 2.310157248304176
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large hyperparameter sweeps for deep neural networks spend substantial compute on configurations that are effectively doomed from the first few epochs. We study whether a single training run's own early telemetry - per-epoch loss, training accuracy, gradient signal-to-noise ratio, weight-norm growth, and an activation-saturation snapshot - together with its sampled hyperparameters, can predict that run's eventual outcome without reference to other runs. We evaluate three prediction tasks: final test accuracy, relative performance within a domain, and training-dynamics failure, including numerical divergence. Across 23,788 training runs spanning six architecture/dataset combinations, gradient-boosted trees using only the first five epochs of telemetry achieve R^2 = 0.92-0.99 for final-accuracy regression and ROC-AUC = 0.983-0.998 for relative classification on a permanently held-out set of hyperparameter configurations. Useful prediction is already available after a single epoch. A paired ablation shows that gradient- and weight-level telemetry provides a statistically consistent improvement over loss and accuracy curves alone, although the practical gain varies by domain. Transfer is strong between similar architectures, while cross-dataset transfer is limited mainly by differences in accuracy scale rather than loss of the underlying relationship. These results suggest that early-training telemetry can provide a practical decision-support signal for compute allocation while motivating human oversight for any automated intervention.

Related papers

• The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions [51.68215326304272]
  We show that even small perturbations reliably cause otherwise identical training trajectories to diverge-an effect that diminishes rapidly over training time.<n>Our findings provide insights into neural network training stability, with practical implications for fine-tuning, model merging, and diversity of model ensembles.
  arXiv  Detail & Related papers  (2025-06-16T08:35:16Z)
• The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws [51.608402959163925]
  We present the first systematic exploration of optimal sparse pre-training configurations for large language models.<n>We find that initiating pruning at 25% of total training compute and concluding at 75% achieves near-optimal final evaluation loss.<n>We propose a new scaling law that modifies the Chinchilla scaling law to use the average parameter count over pre-training.
  arXiv  Detail & Related papers  (2025-01-21T20:23:22Z)
• Just How Flexible are Neural Networks in Practice? [89.80474583606242]
  It is widely believed that a neural network can fit a training set containing at least as many samples as it has parameters. In practice, however, we only find solutions via our training procedure, including the gradient and regularizers, limiting flexibility.
  arXiv  Detail & Related papers  (2024-06-17T12:24:45Z)
• Adaptive Sampling for Deep Learning via Efficient Nonparametric Proxies [35.29595714883275]
  We develop an efficient sketch-based approximation to the Nadaraya-Watson estimator. Our sampling algorithm outperforms the baseline in terms of wall-clock time and accuracy on four datasets.
  arXiv  Detail & Related papers  (2023-11-22T18:40:18Z)
• Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection [58.789823426981044]
  We propose a novel auxiliary loss formulation that aims to align the class confidence of bounding boxes with the accurateness of predictions. Our results reveal that our train-time loss surpasses strong calibration baselines in reducing calibration error for both in and out-domain scenarios.
  arXiv  Detail & Related papers  (2023-03-25T08:56:21Z)
• Efficient Parametric Approximations of Neural Network Function Space Distance [6.117371161379209]
  It is often useful to compactly summarize important properties of model parameters and training data so that they can be used later without storing and/or iterating over the entire dataset. We consider estimating the Function Space Distance (FSD) over a training set, i.e. the average discrepancy between the outputs of two neural networks. We propose a Linearized Activation TRick (LAFTR) and derive an efficient approximation to FSD for ReLU neural networks.
  arXiv  Detail & Related papers  (2023-02-07T15:09:23Z)
• Confidence-Nets: A Step Towards better Prediction Intervals for regression Neural Networks on small datasets [0.0]
  We propose an ensemble method that attempts to estimate the uncertainty of predictions, increase their accuracy and provide an interval for the expected variation. The proposed method is tested on various datasets, and a significant improvement in the performance of the neural network model is seen.
  arXiv  Detail & Related papers  (2022-10-31T06:38:40Z)
• Towards an Understanding of Benign Overfitting in Neural Networks [104.2956323934544]
  Modern machine learning models often employ a huge number of parameters and are typically optimized to have zero training loss. We examine how these benign overfitting phenomena occur in a two-layer neural network setting. We show that it is possible for the two-layer ReLU network interpolator to achieve a near minimax-optimal learning rate.
  arXiv  Detail & Related papers  (2021-06-06T19:08:53Z)
• Robust Learning via Persistency of Excitation [4.674053902991301]
  We show that network training using gradient descent is equivalent to a dynamical system parameter estimation problem. We provide an efficient technique for estimating the corresponding Lipschitz constant using extreme value theory. Our approach also universally increases the adversarial accuracy by 0.1% to 0.3% points in various state-of-the-art adversarially trained models.
  arXiv  Detail & Related papers  (2021-06-03T18:49:05Z)
• Predicting Training Time Without Training [120.92623395389255]
  We tackle the problem of predicting the number of optimization steps that a pre-trained deep network needs to converge to a given value of the loss function. We leverage the fact that the training dynamics of a deep network during fine-tuning are well approximated by those of a linearized model. We are able to predict the time it takes to fine-tune a model to a given loss without having to perform any training.
  arXiv  Detail & Related papers  (2020-08-28T04:29:54Z)

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.