Shared Physics Responses Recover Hidden Rankings in Neural Operator Libraries

• URL: http://arxiv.org/abs/2608.20441v1
• Date: Thu, 20 Aug 2026 14:10:09 GMT
• Title: Shared Physics Responses Recover Hidden Rankings in Neural Operator Libraries
• Abstract summary: We show that under a squared Hilbert-space loss, ranking a finite model library depends strictly on the low-dimensional span of candidate differences.<n>This framework enables the reliable and highly efficient deployment of scientific surrogates without requiring ground-truth data.
• Score: 0.5371337604556311
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Selecting the optimal neural-operator prediction during deployment is challenging when high-fidelity reference solutions are unavailable. We demonstrate that under a squared Hilbert-space loss, ranking a finite model library depends strictly on the low-dimensional span of candidate differences, allowing us to score all models simultaneously using a single anchor-based linearized response of the governing equation. This shared physical diagnostic accurately recovered over 99.6\% of pairwise preferences and 99.0\% of optimal checkpoints across diverse Fourier and convolutional operator libraries for fluid, reaction-diffusion, and wave dynamics. Furthermore, the corrected physical proxy frequently outperformed the best individual candidates, and we establish computable sufficient conditions that rigorously certify exact decisions for strongly monotone discretizations. By exploiting the local dynamical response rather than raw defect magnitude, this framework enables the reliable and highly efficient deployment of scientific surrogates without requiring ground-truth data.

Related papers

• Preference Data Selection for Mitigating the Alignment Tax in Large Language Models [52.18310687523229]
  BALIGN is a balanced data selection strategy that mitigates catastrophic forgetting while optimizing alignment efficacy.<n>By aggregating three key data-centric features into a unified composite risk score, BALIGN systematically filters out high-risk preference samples.<n>Experiments on standard human preference datasets demonstrate that BALIGN strongly preserves foundational capabilities without compromising alignment gains.
  arXiv  Detail & Related papers  (2026-08-25T07:58:42Z)
• More Data, Worse Decisions? Preference Reversals in Neural Networks under Gram Incompatibility [9.196757973061198]
  Case-Based Decision Theory (CBDT) formalizes the requirement through its composition axiom.<n>We study when this property holds for fixed-representation neural networks with ordinary least squares (OLS) output heads.<n>We develop a three-stage audit that traces strict pairwise reversals through decision changes to task-defined utility loss.
  arXiv  Detail & Related papers  (2026-07-28T18:52:47Z)
• Robust Conformalized Selection with Noisy Responses [23.306273801765297]
  Conformalized selection has been widely applied to select high-quality candidates from large datasets.<n>We formulate the above tasks as selecting candidates with true predicted labels or with responses exceeding certain values.<n>We propose Robust Conformalized Selection (RCS), a unified framework for selective classification with valid FDR control under general label contamination.
  arXiv  Detail & Related papers  (2026-07-25T01:51:46Z)
• Uncertainty-aware damage identification in short-span bridges via physics-informed variational autoencoder [0.4893345190925178]
  This work proposes a physics-informed Gaussian copula variational autoencoder for structural health monitoring.<n>We replace the conventional independence assumption of latent variables with a Gaussian copula.<n>Results demonstrate that the PI-VAE accurately recovers the true posterior distribution, achieving 77.2% coverage.
  arXiv  Detail & Related papers  (2026-07-06T13:02:36Z)
• Unbiased Alignment for Large Language Models with Noisy Preferences [74.69408994904965]
  We present a theoretical framework for unbiased alignment, introducing the Unbiased Reward Model (URM) loss and the Unbiased Direct Preference Optimization (UDPO) loss.<n>By mathematically correcting the distortion induced by preference noise, our novel objectives enable unbiased model training directly from noisy datasets.
  arXiv  Detail & Related papers  (2026-07-03T12:04:43Z)
• Mind the Residual Gap: Probabilistic Downscaling under Real-World Bias [11.400279490725042]
  Probabilistic downscaling is a central challenge to atmospheric science, climate modeling, and other multiscale physical systems.<n>A widely used paradigm decomposes the problem into a deterministic mean predictor followed by a residual generator.<n>We show that the root cause is residual target miscalibration, the residual distribution induced during training differs systematically from the one required at test time due to downscaling bias.
  arXiv  Detail & Related papers  (2026-06-29T18:47:34Z)
• Learning from Emptiness: De-biasing Listwise Rerankers with Content-Agnostic Probability Calibration [76.08899010904652]
  CapCal is a training-free framework that mechanically decouples positional bias from ranking decisions.<n>It achieves superior performance among training-free methods while preserving single-pass efficiency.
  arXiv  Detail & Related papers  (2026-04-11T10:47:22Z)
• ODAR: Principled Adaptive Routing for LLM Reasoning via Active Inference [60.958331943869126]
  ODAR-Expert is an adaptive routing framework that optimize the accuracy-efficiency trade-off via principled resource allocation.<n>We show strong and consistent gains, including 98.2% accuracy on MATH and 54.8% on Humanity's Last Exam.
  arXiv  Detail & Related papers  (2026-02-27T05:22:01Z)
• Partial Soft-Matching Distance for Neural Representational Comparison with Partial Unit Correspondence [6.914720821302567]
  We extend the soft-matching distance to a partial optimal transport setting that allows some neurons to remain unmatched.<n>It preserves correct matches under outliers and reliably selects the correct model in noise-corrupted identification tasks.<n>It achieves higher alignment precision across brain areas than standard soft-matching, which is forced to match all units regardless of quality.
  arXiv  Detail & Related papers  (2026-02-22T20:31:35Z)
• Reference-Free Rating of LLM Responses via Latent Information [53.463883683503106]
  We study the common practice of asking a judge model to assign Likert-scale scores to free-text responses.<n>We then propose and evaluate Latent Judges, which derive scalar ratings from internal model signals.<n>Across a broad suite of pairwise and single-rating benchmarks, latent methods match or surpass standard prompting.
  arXiv  Detail & Related papers  (2025-09-29T12:15:52Z)
• Accelerated zero-order SGD under high-order smoothness and overparameterized regime [79.85163929026146]
  We present a novel gradient-free algorithm to solve convex optimization problems. Such problems are encountered in medicine, physics, and machine learning. We provide convergence guarantees for the proposed algorithm under both types of noise.
  arXiv  Detail & Related papers  (2024-11-21T10:26:17Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)

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.