Stabilizing Test-Time Adaptation of High-Dimensional Simulation Surrogates via D-Optimal Statistics

• URL: http://arxiv.org/abs/2602.15820v1
• Date: Tue, 17 Feb 2026 18:55:18 GMT
• Title: Stabilizing Test-Time Adaptation of High-Dimensional Simulation Surrogates via D-Optimal Statistics
• Authors: Anna Zimmel, Paul Setinek, Gianluca Galletti, Johannes Brandstetter, Werner Zellinger,
• Abstract summary: Test-Time Adaptation (TTA) can mitigate distribution shifts between training and deployment of machine learning surrogates.<n>We propose a TTA framework based on storing maximally informative (D-optimal) statistics.<n>Our method yields up to 7% out-of-distribution improvements at negligible computational cost.
• Score: 23.824598203175455
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine learning surrogates are increasingly used in engineering to accelerate costly simulations, yet distribution shifts between training and deployment often cause severe performance degradation (e.g., unseen geometries or configurations). Test-Time Adaptation (TTA) can mitigate such shifts, but existing methods are largely developed for lower-dimensional classification with structured outputs and visually aligned input-output relationships, making them unstable for the high-dimensional, unstructured and regression problems common in simulation. We address this challenge by proposing a TTA framework based on storing maximally informative (D-optimal) statistics, which jointly enables stable adaptation and principled parameter selection at test time. When applied to pretrained simulation surrogates, our method yields up to 7% out-of-distribution improvements at negligible computational cost. To the best of our knowledge, this is the first systematic demonstration of effective TTA for high-dimensional simulation regression and generative design optimization, validated on the SIMSHIFT and EngiBench benchmarks.

Related papers

• ARTIS: Agentic Risk-Aware Test-Time Scaling via Iterative Simulation [72.78362530982109]
  ARTIS, Agentic Risk-Aware Test-Time Scaling via Iterative Simulation, is a framework that decouples exploration from commitment.<n>We show that naive LLM-based simulators struggle to capture rare but high-impact failure modes.<n>We introduce a risk-aware tool simulator that emphasizes fidelity on failure-inducing actions.
  arXiv  Detail & Related papers  (2026-02-02T06:33:22Z)
• Not All Preferences Are Created Equal: Stability-Aware and Gradient-Efficient Alignment for Reasoning Models [52.48582333951919]
  We propose a dynamic framework designed to enhance alignment reliability by maximizing the Signal-to-Noise Ratio of policy updates.<n>SAGE (Stability-Aware Gradient Efficiency) integrates a coarse-grained curriculum mechanism that refreshes candidate pools based on model competence.<n> Experiments on multiple mathematical reasoning benchmarks demonstrate that SAGE significantly accelerates convergence and outperforms static baselines.
  arXiv  Detail & Related papers  (2026-02-01T12:56:10Z)
• Calibrating Agent-Based Financial Markets Simulators with Pretrainable Automatic Posterior Transformation-Based Surrogates [5.002657036975061]
  Calibrating Agent-Based Models (ABMs) is an important optimization problem for simulating the complex social systems.<n>The goal is to identify the optimal parameter of a given ABM by minimizing the discrepancy between the simulated data and the real-world observations.<n>Existing methods face two key limitations: 1) surrogating the original evaluation function is hard due the nonlinear yet multi-modal nature of the ABMs, and 2) the commonly used surrogates cannot share the optimization experience among multiple calibration tasks.<n>This work proposes Automatic posterior transformation with Negatively Correlated Search and Adaptive Trust-Region.
  arXiv  Detail & Related papers  (2026-01-11T14:05:26Z)
• Adaptive Reinforcement Learning for Dynamic Configuration Allocation in Pre-Production Testing [4.370892281528124]
  We introduce a novel reinforcement learning framework that recasts configuration allocation as a sequential decision-making problem.<n>Our method is the first to integrate Q-learning with a hybrid reward design that fuses simulated outcomes and real-time feedback.
  arXiv  Detail & Related papers  (2025-10-02T05:12:28Z)
• Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning [77.92320830700797]
  Reinforcement Learning has played a central role in enabling reasoning capabilities of Large Language Models.<n>We propose a tractable computational framework that tracks and leverages curvature information during policy updates.<n>The algorithm, Curvature-Aware Policy Optimization (CAPO), identifies samples that contribute to unstable updates and masks them out.
  arXiv  Detail & Related papers  (2025-10-01T12:29:32Z)
• Flow Matching for Robust Simulation-Based Inference under Model Misspecification [11.172752919335394]
  Flow Matching Corrected Posterior Estimation is a framework that refines simulation-trained posterior estimators using a small set of real calibration samples.<n>We show that our proposal consistently mitigates the effects of misspecification, delivering improved inference accuracy and uncertainty calibration compared to standard SBI baselines.
  arXiv  Detail & Related papers  (2025-09-27T16:10:53Z)
• Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation [67.80294336559574]
  Continual Test Time Adaptation (CTTA) is a task that requires a source pre-trained model to continually adapt to new scenarios.<n>We propose a novel pipeline, Orthogonal Projection Subspace to aggregate online Prior-knowledge, dubbed OoPk.
  arXiv  Detail & Related papers  (2025-06-23T18:17:39Z)
• Taming Polysemanticity in LLMs: Provable Feature Recovery via Sparse Autoencoders [50.52694757593443]
  Existing SAE training algorithms often lack rigorous mathematical guarantees and suffer from practical limitations.<n>We first propose a novel statistical framework for the feature recovery problem, which includes a new notion of feature identifiability.<n>We introduce a new SAE training algorithm based on bias adaptation'', a technique that adaptively adjusts neural network bias parameters to ensure appropriate activation sparsity.
  arXiv  Detail & Related papers  (2025-06-16T20:58:05Z)
• Model Predictive Task Sampling for Efficient and Robust Adaptation [57.414812940406996]
  We introduce Model Predictive Task Sampling (MPTS), a framework that bridges the task space and adaptation risk distributions.<n>MPTS employs a generative model to characterize the episodic optimization process and predicts task-specific adaptation risk via posterior inference.<n>MPTS seamlessly integrates into zero-shot, few-shot, and supervised finetuning settings.
  arXiv  Detail & Related papers  (2025-01-19T13:14:53Z)
• Active Sequential Posterior Estimation for Sample-Efficient Simulation-Based Inference [12.019504660711231]
  We introduce sequential neural posterior estimation (ASNPE)<n>ASNPE brings an active learning scheme into the inference loop to estimate the utility of simulation parameter candidates to the underlying probabilistic model.<n>Our method outperforms well-tuned benchmarks and state-of-the-art posterior estimation methods on a large-scale real-world traffic network.
  arXiv  Detail & Related papers  (2024-12-07T08:57:26Z)
• Surrogate Neural Networks for Efficient Simulation-based Trajectory Planning Optimization [28.292234483886947]
  This paper presents a novel methodology that uses surrogate models in the form of neural networks to reduce the computation time of simulation-based optimization of a reference trajectory. We find a 74% better-performing reference trajectory compared to nominal, and the numerical results clearly show a substantial reduction in computation time for designing future trajectories.
  arXiv  Detail & Related papers  (2023-03-30T15:44:30Z)

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.