paper-with-me

홈 › Papers

Reference-free logged energy-oracle recovery for neural approximations of symmetric coercive variational problems: conforming Riesz reconstruction and archive-level selection

2026-08-17 · Karim Bounja, Lahcen Laayouni, Boujemaa Achchab, Abdeljalil Sakat arxiv

Neural PDE training yields a finite checkpoint archive, yet its logged energy errors are inaccessible without the exact solution, while loss-based selection does not necessarily recover the logged energy oracle. For admissible neural approximations of symmetric coercive variational problems, we introduce a reference-free selection rule based on minimizing a computable conforming Riesz monitor. The exact residual-energy identity and conforming projection make the monitor an unconditional lower bound converging monotonically to each logged energy error under nested conforming refinement; under saturation, hierarchical enrichment yields a computable upper estimate and hence a lower-upper bracket. A key finding is that archive selection is order-sensitive: unresolved checkpoint-dependent components can reverse the oracle-non-oracle ranking at finite resolution, so checkpointwise recovery alone is insufficient. For finite archives, we prove uniform recovery, yielding convergence to the logged-oracle error and, without saturation, logged-oracle selection at sufficiently fine auxiliary resolution. Under saturation, the bracket gives a computable near-oracle bound and certifies unique logged-oracle selection upon interval separation. We also bound logging-resolution loss and certify oracle inclusion over prescribed comparison trajectories. The resulting criterion replaces inaccessible exact-error minimization by computable, training-independent post-training selection on the intrinsic energy-error scale, requiring only the computed candidates and the variational problem. Experiments on diffusion and elasticity, including a non-manufactured perforated plate, demonstrate energy-scale calibration, oracle-level selection, and modest post-processing cost.

📄 PDF Abstract BibTeX arXiv:2608.16473

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Diagnosing Evidence Utilization in Long-Context and Retrieval-Augmented Language Models under Matched Evidence Conditions

2026-06-04 · Haizhou Xia arxiv

Final-answer accuracy, retrieval recall, and citation overlap do not reveal how much answer advantage a long-context or retrieval-augmented language model actually recovers from supplied evidence. A model may answer from…

Self-Evidencing Through Hierarchical Gradient Decomposition: A Dissipative System That Maintains Non-Equilibrium Steady-State by Minimizing Variational Free Energy

2025-10-20 · Michael James McCulloch arxiv

The Free Energy Principle (FEP) states that self-organizing systems must minimize variational free energy to persist, but the path from principle to implementable algorithm has remained unclear. We present a constructive…

Reinforcement LearningContinuous Control

Pessimism-Free Offline Learning in General-Sum Games via KL Regularization

2026-04-30 · Claire Chen, Yuheng Zhang arxiv

Offline multi-agent reinforcement learning in general-sum settings is challenged by the distribution shift between logged datasets and target equilibrium policies. While standard methods rely on manual pessimistic penalt…

Multi-agent Reinforcement Learning

MF-LAL: Drug Compound Generation Using Multi-Fidelity Latent Space Active Learning

2024-10-15 · Peter Eckmann, Dongxia Wu, Germano Heinzelmann, Michael K. Gilson 외

Current generative models for drug discovery primarily use molecular docking as an oracle to guide the generation of active compounds. However, such models are often not useful in practice because even compounds with hig…

Active LearningActivity PredictionDrug DiscoveryMolecular Docking

Learning and Free Energies for Vector Approximate Message Passing

2016-02-26 · Alyson K. Fletcher, Philip Schniter

Vector approximate message passing (VAMP) is a computationally simple approach to the recovery of a signal $\mathbf{x}$ from noisy linear measurements $\mathbf{y}=\mathbf{Ax}+\mathbf{w}$. Like the AMP proposed by Donoho,…