ScoreStop: Gradient-based early stopping using functional score tests

• URL: http://arxiv.org/abs/2606.02740v1
• Date: Mon, 01 Jun 2026 18:05:22 GMT
• Title: ScoreStop: Gradient-based early stopping using functional score tests
• Abstract summary: We propose a gradient-based early-stopping rule that casts the stopping decision at each iteration as a test of the null hypothesis that the current predictor is the population risk minimizer.<n>Because our test uses gradients rather than loss values, the same construction applies to implicit validation losses such as LambdaRank, and data-dependent losses such as Cox regression via influence functions.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Gradient boosted decision trees require a stopping rule to avoid overfitting. The standard rule monitors a validation loss and stops if the loss fails to improve for a fixed patience period. However, the patience parameter has no interpretable scale and validation losses can be noisy or implicitly defined by a user-specified gradient. We propose ScoreStop, a gradient-based early-stopping rule that casts the stopping decision at each iteration as a test of the null hypothesis that the current predictor is the population risk minimizer. We use a functional score test, computed on validation data, with a statistic that is scale-invariant in the update direction, with a known asymptotic distribution under the null. Because our test uses gradients rather than loss values, the same construction applies to implicit losses such as LambdaRank, and data-dependent losses such as Cox regression via influence functions. In synthetic experiments and real-data benchmarks, we show that ScoreStop is competitive with loss-based methods.

Related papers

• Sample-Adaptive Latent Rewards for Uncertainty-Guided Diffusion Post-Training [51.18425726646089]
  We propose textscSURE, a unified latent-space framework for image and video diffusion models.<n>It learns reward distributions and directly uses their reliability to guide dense post-training.<n>textscSURE-REFL achieves the highest VBench quality, semantic, and total scores among the evaluated methods.
  arXiv  Detail & Related papers  (2026-08-06T14:55:42Z)
• General Value Functions for Remaining Useful Life and Failure-Mode Prediction [5.709180757030779]
  We formulate vector General Value Function (GVF) prediction on an absorbing degradation process.<n>We estimate RUL and failure-mode probabilities as temporally consistent targets rather than independent window-level labels.<n>On an event-triggered multimode simulation and NASA C-MAPSS label-scarce stitch data, TD improves RUL and failure-mode prediction relative to a supervised same-backbone Monte Carlo control.
  arXiv  Detail & Related papers  (2026-07-24T13:04:32Z)
• Tailoring Strictly Proper Scoring Rules for Downstream Tasks: An Application to Causal Inference [48.78219918881965]
  We propose a principled framework for deriving task-specific strictly proper scoring rules by matching the local curvature of the downstream error metric.<n>We apply this to the Average Treatment Effect (ATE) estimation, deriving a closed-form loss and its corresponding canonical probability mapping.
  arXiv  Detail & Related papers  (2026-06-02T08:41:25Z)
• Unbiased Gradient Estimation for Event Binning via Functional Backpropagation [64.88399635309918]
  We propose a novel framework for unbiased gradient estimation of arbitrary binning functions by synthesizing weak derivatives during backpropagation.<n>We achieve 9.4% lower EPE in self-supervised optical flow, and 5.1% lower RMS error in SLAM, demonstrating broad benefits for event-based visual perception.
  arXiv  Detail & Related papers  (2026-02-13T04:05:03Z)
• GRADSTOP: Early Stopping of Gradient Descent via Posterior Sampling [4.938367626424121]
  Machine learning models often suffer from overfitting, leading to a decline in predictive performance on unseen data.<n>A standard solution is early stopping using a hold-out validation set, which halts the minimisation when the validation loss stops decreasing.<n>This paper presents GRADSTOP, a novel early stopping method that only uses information in the gradients, which are produced by the gradient descent algorithm.
  arXiv  Detail & Related papers  (2025-08-26T13:44:35Z)
• Centaur: Robust End-to-End Autonomous Driving with Test-Time Training [84.78837437133234]
  We propose Centaur, which updates a planner's behavior via test-time training without relying on hand-engineered rules or cost functions.<n>We develop a novel uncertainty measure, called Cluster Entropy, which is simple, interpretable, and compatible with state-of-the-art planning algorithms.
  arXiv  Detail & Related papers  (2025-03-14T17:59:41Z)
• Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting [65.21599711087538]
  Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and test data by adapting a given model w.r.t. any test sample.<n>Prior methods perform backpropagation for each test sample, resulting in unbearable optimization costs to many applications.<n>We propose an Efficient Anti-Forgetting Test-Time Adaptation (EATA) method which develops an active sample selection criterion to identify reliable and non-redundant samples.
  arXiv  Detail & Related papers  (2024-03-18T05:49:45Z)
• Decision-Focused Learning with Directional Gradients [1.2363103948638432]
  We propose a novel family of decision-aware surrogate losses, called Perturbation Gradient (PG) losses, for the predict-then-optimize framework. Unlike the original decision loss which is typically piecewise constant and discontinuous, our new PG losses is a Lipschitz continuous, difference of concave functions. We provide numerical evidence confirming our PG losses substantively outperform existing proposals when the underlying model is misspecified.
  arXiv  Detail & Related papers  (2024-02-05T18:14:28Z)
• Near-Optimal Non-Parametric Sequential Tests and Confidence Sequences with Possibly Dependent Observations [44.71254888821376]
  We provide the first type-I-error and expected-rejection-time guarantees under general non-data generating processes. We show how to apply our results to inference on parameters defined by estimating equations, such as average treatment effects.
  arXiv  Detail & Related papers  (2022-12-29T18:37:08Z)
• Boosting Active Learning via Improving Test Performance [35.9303900799961]
  We show that selecting unlabeled data of higher gradient norm leads to a lower upper bound of test loss. We propose two schemes, namely expected-gradnorm and entropy-gradnorm. Our method achieves superior performance against the state-of-the-art.
  arXiv  Detail & Related papers  (2021-12-10T17:25:14Z)
• High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails [55.561406656549686]
  We consider non- Hilbert optimization using first-order algorithms for which the gradient estimates may have tails. We show that a combination of gradient, momentum, and normalized gradient descent convergence to critical points in high-probability with best-known iteration for smooth losses.
  arXiv  Detail & Related papers  (2021-06-28T00:17:01Z)
• Fast OSCAR and OWL Regression via Safe Screening Rules [97.28167655721766]
  Ordered $L_1$ (OWL) regularized regression is a new regression analysis for high-dimensional sparse learning. Proximal gradient methods are used as standard approaches to solve OWL regression. We propose the first safe screening rule for OWL regression by exploring the order of the primal solution with the unknown order structure.
  arXiv  Detail & Related papers  (2020-06-29T23:35:53Z)
• A termination criterion for stochastic gradient descent for binary classification [3.216356957608319]
  We propose a new, simple, and inexpensive termination test for constant step-size gradient descent. We show that our test terminates in a finite number of iterations and when the noise in the data is not too large, the expected classifier at termination nearly minimizes the probability of misclassification.
  arXiv  Detail & Related papers  (2020-03-23T15:00:21Z)

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.