Reducing cross-sample prediction churn in scientific machine learning

• URL: http://arxiv.org/abs/2605.13826v1
• Date: Wed, 13 May 2026 17:50:57 GMT
• Title: Reducing cross-sample prediction churn in scientific machine learning
• Abstract summary: Cross-sample prediction deserves a column alongside predictive performance in scientific-ML benchmark reports, because without it the parameter-side and data-side methods are indistinguishable on the metric they actually differ on.
• Score: 0.155963096715749
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Scientific machine learning reports predictive performance. It does not report whether the same prediction would survive a different draw of training data. Across $9$ chemistry benchmarks, two classifiers trained on independent bootstraps of the same training set agree on aggregate accuracy to within $1.3\text{--}4.2$ percentage points but disagree on the class label of $8.0\text{--}21.8\%$ of test molecules. We call this gap \emph{cross-sample prediction churn}. The standard parameter-side techniques (deep ensembles, MC dropout, stochastic weight averaging) do not reduce this gap; two data-side methods do. The first is $K$-bootstrap bagging, which cuts the rate $40\text{--}54\%$ on every dataset at no accuracy cost ($K{\times}$-ERM compute). The second is \emph{twin-bootstrap}, our proposal: two networks trained jointly on independent bootstraps with a sym-KL consistency loss between their predictions, which at matched $2{\times}$-ERM compute reduces churn a further median $45\%$ beyond bagging-$K{=}2$. Cross-sample prediction churn deserves a column alongside predictive performance in scientific-ML benchmark reports, because without it the parameter-side and data-side methods are indistinguishable on the metric they actually differ on.

Related papers

• A Spectral Phase Diagram for Binary Few-Shot Classification: Intrinsic Dimensionality, Geometric Saturation, and Representational Diagnosis [0.0]
  The saturation index $S(K) = operatornameerank(widehat_W(K)) / K$ measures the ratio of the effective rank of the pooled within-class sample covariance to the shot count.<n>The index is computable in $O(d3)$ time from support features alone, requiring no test labels or trained classifier.
  arXiv  Detail & Related papers  (2026-06-12T16:46:24Z)
• Optimal Unconstrained Self-Distillation in Ridge Regression: Strict Improvements, Precise Asymptotics, and One-Shot Tuning [61.07540493350384]
  Self-distillation (SD) is the process of retraining a student on a mixture of ground-truth and the teacher's own predictions.<n>We show that for any prediction risk, the optimally mixed student improves upon the ridge teacher for every regularization level.<n>We propose a consistent one-shot tuning method to estimate $star$ without grid search, sample splitting, or refitting.
  arXiv  Detail & Related papers  (2026-02-19T17:21:15Z)
• Blackbox Dataset Inference for LLM [27.02176845242058]
  Training large language models can involve personally identifiable information and copyrighted material.<n>This paper explores textitdataset inference, which aims to detect if a suspect model used a victim dataset $mathcalD$ in training.
  arXiv  Detail & Related papers  (2025-07-04T14:45:41Z)
• Conformal Predictions under Markovian Data [50.24983453990065]
  We study the split Conformal Prediction method when applied to Markovian data. We quantify the gap in terms of coverage induced by the correlations in the data. We present $K$-split CP, a method that adapts to the mixing properties of the chain.
  arXiv  Detail & Related papers  (2024-07-21T22:01:09Z)
• Exploiting Pre-trained Models for Drug Target Affinity Prediction with Nearest Neighbors [58.661454334877256]
  Drug-Target binding Affinity (DTA) prediction is essential for drug discovery. Despite the application of deep learning methods to DTA prediction, the achieved accuracy remain suboptimal. We propose $k$NN-DTA, a non-representation embedding-based retrieval method adopted on a pre-trained DTA prediction model.
  arXiv  Detail & Related papers  (2024-07-21T15:49:05Z)
• Semidefinite programming relaxations and debiasing for MAXCUT-based clustering [1.9761774213809036]
  We consider the problem of partitioning a small data sample of size $n$ drawn from a mixture of 2 sub-gaussian distributions in $mathbbRp$.<n>We use semidefinite programming relaxations of an integer quadratic program that is formulated as finding the maximum cut on a graph.
  arXiv  Detail & Related papers  (2024-01-16T03:14:24Z)
• Kernel-Based Tests for Likelihood-Free Hypothesis Testing [21.143798051525646]
  Given $n$ observations from two balanced classes, consider the task of labeling an additional $m$ inputs that are known to all belong to emphone of the two classes. Special cases of this problem are well-known; when $m=1$ it corresponds to binary classification; and when $mapprox n$ it is equivalent to two-sample testing. In recent work it was discovered that there is a fundamental trade-off between $m$ and $n$: increasing the data sample $m$ reduces the amount $n$ of training/simulation data needed.
  arXiv  Detail & Related papers  (2023-08-17T15:24:03Z)
• Statistical Learning under Heterogeneous Distribution Shift [71.8393170225794]
  Ground-truth predictor is additive $mathbbE[mathbfz mid mathbfx,mathbfy] = f_star(mathbfx) +g_star(mathbfy)$.
  arXiv  Detail & Related papers  (2023-02-27T16:34:21Z)
• Beyond Invariance: Test-Time Label-Shift Adaptation for Distributions with "Spurious" Correlations [44.99833362998488]
  Changes in the data distribution at test time can have deleterious effects on the performance of predictive models. We propose a test-time label shift correction that adapts to changes in the joint distribution $p(y, z)$ using EM applied to unlabeled samples.
  arXiv  Detail & Related papers  (2022-11-28T18:52:33Z)
• Bias Mimicking: A Simple Sampling Approach for Bias Mitigation [57.17709477668213]
  We introduce a new class-conditioned sampling method: Bias Mimicking. Bias Mimicking improves underrepresented groups' accuracy of sampling methods by 3% over four benchmarks.
  arXiv  Detail & Related papers  (2022-09-30T17:33:00Z)
• An Improved Analysis of Gradient Tracking for Decentralized Machine Learning [34.144764431505486]
  We consider decentralized machine learning over a network where the training data is distributed across $n$ agents. The agent's common goal is to find a model that minimizes the average of all local loss functions. We improve the dependency on $p$ from $mathcalO(p-1)$ to $mathcalO(p-1)$ in the noiseless case.
  arXiv  Detail & Related papers  (2022-02-08T12:58:14Z)
• Mediated Uncoupled Learning: Learning Functions without Direct Input-output Correspondences [80.95776331769899]
  We consider the task of predicting $Y$ from $X$ when we have no paired data of them. A naive approach is to predict $U$ from $X$ using $S_X$ and then $Y$ from $U$ using $S_Y$. We propose a new method that avoids predicting $U$ but directly learns $Y = f(X)$ by training $f(X)$ with $S_X$ to predict $h(U)$.
  arXiv  Detail & Related papers  (2021-07-16T22:13:29Z)
• Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction [63.41789556777387]
  Asynchronous Q-learning aims to learn the optimal action-value function (or Q-function) of a Markov decision process (MDP) We show that the number of samples needed to yield an entrywise $varepsilon$-accurate estimate of the Q-function is at most on the order of $frac1mu_min (1-gamma)5varepsilon2+ fract_mixmu_min (1-gamma)$ up to some logarithmic factor.
  arXiv  Detail & Related papers  (2020-06-04T17:51:00Z)

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.