Scientific ML

ML: Machine Learning

Follow this topic Ask about this topic

Momentum

9 papers in the last four weeks, against 2 the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 82

All topics

Reducing cross-sample prediction churn in scientific machine learning
May 13, 2026Gordan Prastalo, Kevin Maik JablonkaEnsemble Learning Classification
Helmholtz-Zentrum Berlin für Materialien und Energie GmbH, Hahn-Meitner-Platz 1, 14109 Berlin, Germany · HIPOLE Jena (Helmholtz Institute for Polymers in Energy Applications Jena), Lessingstrasse 12–14, 077432026 Jena, Germany · Laboratory of Organic and Macromolecular Chemistry (IOMC), Friedrich Schiller University Jena, Humboldtstrasse 10, 07743 Jena, Germany +2
ShardTensor: Domain Parallelism for Scientific Machine Learning
May 11, 2026Corey Adams, Peter Harrington, Akshay Subramaniam +4Scientific ML Distributed Training
NVIDIA · Santa Clara, CA, USA
Anatomy of a failure: When, how, and why deep vision fails in scientific domains
May 5, 2026Ji-Hun Oh, Dou Hoon Kwark, Kianoush Falahkheirkhah +4Scientific ML
Department of Mechanical Science and Engineering, University of Illinois Urbana-Champaign, IL, US · Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign, IL, US · Beckman Institute for Advanced Science and Technology, University of Illinois Urbana-Champaign, IL, US +8
PODiff: Latent Diffusion in Proper Orthogonal Decomposition Space for Scientific Super-Resolution
May 5, 2026Onkar Jadhav, Tim French, Matthew Rayson +1Uncertainty Quantification Proper Orthogonal Decomposition
School of Earth and Oceans, UWA Oceans Institute, University of Western Australia, Crawley, WA, Australia · School of Physics, Mathematics and Computing, Computer Science and Software Engineering, University of Western Australia, Crawley, WA, Australia.
AdaGraph: A Graph-Native Clustering Algorithm That Overcomes the Curse of Dimensionality and Enables Scientific Discovery
May 5, 2026Ahmed ElmahdiClustering Graph Clustering
Independent Researcher
RamanBench: A Large-Scale Benchmark for Machine Learning on Raman Spectroscopy
May 3, 2026Mario Koddenbrock, Christoph Lange, Robin Legner +6Benchmark Design Scientific ML
HTW Berlin · TU Berlin · KWS SAAT, Einbeck +5
Mesh Field Theory: Port-Hamiltonian Formulation of Mesh-Based Physics
May 1, 2026Satoshi Noguchi, Yoshinobu KawaharaDynamical Systems Scientific ML
Center for Mathematical Science and Advanced Technology, JAMSTEC · Center for Advanced Intelligence Project, RIKEN · Graduate School of Information Science and Technology, The University of Osaka.
Learning Structure, Energy, and Dynamics: A Survey of Artificial Intelligence for Protein Dynamics
Apr 28, 2026Haocheng Tang, Liang Shi, Ya-Shi Zhang +3Scientific ML Molecular Dynamics Simulation
Mila – Quebec AI Institute · University of Pittsburgh · Work conducted during an internship at Mila +4
Transferable SCF-Acceleration through Solver-Aligned Initialization Learning
Apr 23, 2026Eike S. Eberhard, Viktor Kotsev, Timm Güthle +1Quantum Chemistry Learning to Optimize
1Technical University of Munich (TUM) · 2Munich Data Science Institute (MDSI) · 3Munich Center for Machine Learning (MCML)
Assessing Emulator Design and Training for Modal Aerosol Microphysics Parameterizations in E3SMv2
Apr 23, 2026Shady E. Ahmed, Hui Wan, Saad Qadeer +5Neural Surrogate Modeling Scientific ML
Advanced Computing, Mathematics, and Data Division Pacific Northwest National Laboratory Richland, WA 99354 · Earth and Biological Sciences Directorate Pacific Northwest National Laboratory Richland, WA 99354 · Equifax Inc., Atlanta, GA +2
AI models of unstable flow exhibit hallucination
Apr 22, 2026Ramdhan Wibawa, Birendra JhaScientific ML Neural Operators
Department of Chemical Engineering and Materials Science, University of Southern California, 925 Bloom Walk, Los Angeles, 90089, CA, USA.
Machine learning moment closure models for the radiative transfer equation IV: enforcing symmetrizable hyperbolicity in two dimensions
Apr 22, 2026Juntao HuangReduced-Order Modeling Scientific ML
Department of Mathematical Sciences, University of Delaware, Newark, DE, 19716, USA.
Design Rules for Extreme-Edge Scientific Computing on AI Engines
Apr 21, 2026Zhenghua Ma, G Abarajithan, Dimitrios Danopoulos +3Scientific ML Edge ML
University of California San Diego, La Jolla, CA, USA · European Organization for Nuclear Research (CERN), Geneva, Switzerland
Physics-Informed Neural Networks with Learnable Loss Balancing and Transfer Learning
Apr 17, 2026Reza PirayeshshirazinezhadSelf-Supervised Learning Adaptive Loss Weighting
Texas A&M University College Station, TX, USA
How Can Machine Learning Emulators Best Support Climate Science?
Mar 20, 2026Luca Schmidt, Nina Effenberger, Vitus Benson +5Surrogate Modeling Climate Science
Institute for Atmospheric and Climate Science ETH Zurich · Seminar for Statistics ETH Zurich
Clifford Kolmogorov-Arnold Networks
Feb 5, 2026Matthias Wolff, Francesco Alesiani, Christof Duhme +1Kolmogorov-Arnold Networks Neural Network Approximation Theory
Data Science Div. NEC Labs Europe Heidelberg, Germany
OpFML: Pipeline for ML-based Operational Inference
Jan 16, 2026Shahbaz Alvi, Giusy Fedele, Gabriele Accarino +3Wildfire Forecasting Scientific ML
CMCC Foundation - Euro-Mediterranean Center on Climate Change, Lecce, 73100, Italy · Columbia University, Department of Earth and Environmental Engineering, New York, USA · University of Salento,Department of Innovation Engineering, Lecce, 73100, Italy
ATHENA: Agentic Team for Hierarchical Evolutionary Numerical Algorithms
Dec 3, 2025Juan Diego Toscano, Daniel T. Chen, George Em KarniadakisScientific Code Generation Scientific ML
Division of Applied Mathematics, Brown University, Providence, 02912, RI, USA
Siamese Neural Network for Label-Efficient Critical Phenomena Prediction in 3D Percolation Models
Jul 5, 2025Shanshan Wang, Dian Xu, Jianmin Shen +3Phase Transitions Siamese Neural Networks
Key Laboratory of Quark and Lepton Physics (MOE) and Institute of Particle Physics, Central China Normal University, , Wuhan, 430079, Hubei, China · School of Engineering and Technology, Baoshan University, , Baoshan, 678000, Yunnan, China · Ecole Superieure d’Informatique Electronique Automatique, , Ivry-sur-Seine, 94200, , France
Interpretability and Generalization Bounds for Learning Spatial Physics
Jun 18, 2025Alejandro Francisco Queiruga, Theo Gutman-Solo, Shuai JiangNeural Network Generalization Mechanistic Interpretability
OpenAI, San Francisco, CA, USA · Google, Mountain View, CA, USA · Sandia National Laboratories, Albuquerque, NM, USA
Learning thermodynamic master equations for open quantum systems
Jun 2, 2025Peter Sentz, Stanley Nicholson, Yujin Cho +3Quantum System Identification Interpretable ML
Department of Data and Decision Sciences, Emory University, Atlanta, GA 30322 · 2Division of Applied Mathematics, Brown University, Providence, RI 02912 · 3Lawrence Livermore National Laboratory, Livermore, CA 94550
Autoencoders in Function Space
Aug 2, 2024Justin Bunker, Mark Girolami, Hefin Lambley +2Variational Autoencoders Autoencoders
Department of Engineering University of Cambridge Cambridge, CB2 1TN, United Kingdom · Department of Engineering, University of Cambridge · and Alan Turing Institute +3

May 13, 2026, cs.LGJ/K move · Enter open · S save

Reducing cross-sample prediction churn in scientific machine learning

Gordan Prastalo, Kevin Maik Jablonka

Helmholtz-Zentrum Berlin für Materialien und Energie GmbH, Hahn-Meitner-Platz 1, 14109 Berlin, Germany · HIPOLE Jena (Helmholtz Institute for Polymers in Energy Applications Jena), Lessingstrasse 12–14, 077432026 Jena, Germany · Laboratory of Organic and Macromolecular Chemistry (IOMC), Friedrich Schiller University Jena, Humboldtstrasse 10, 07743 Jena, Germany+2

Ensemble Learning Classification Scientific ML Consistency Regularization

Open paper AskPDF arXiv

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.

Momentum

Related topics

Latest papers 82