Meta-learning PINN loss functions
نویسندگان
چکیده
We propose a meta-learning technique for offline discovery of physics-informed neural network (PINN) loss functions. extend earlier works on meta-learning, and develop gradient-based algorithm addressing diverse task distributions based parametrized partial differential equations (PDEs) that are solved with PINNs. Furthermore, new theory we identify two desirable properties meta-learned losses in PINN problems, which enforce by proposing regularization method or using specific parametrization the function. In computational examples, employed at test time regression PDE distributions. Our results indicate significant performance improvement can be achieved shared-among-tasks offline-learned function even out-of-distribution meta-testing. this case, solve tasks do not belong to distribution used meta-training, also employ architectures different from architecture meta-training. To better understand capabilities limitations proposed method, consider various parametrizations describe design options how they may affect performance.
منابع مشابه
Neurofibroma of the Pinn
Neurofibromas are relatively common lesions of the nervous system, but only a few cases involving the pinna have been reported. Isolated neurofibroma of pinna without neurofibromatosis has not been reported in the literature so far. Neurofibromas may develop anywhere in the body, including cranial and peripheral nerves. The type of impairment associated with neurofibromas depends largely on the...
متن کاملOnline Learning with Pairwise Loss Functions
Efficient online learning with pairwise loss functions is a crucial component in building largescale learning system that maximizes the area under the Receiver Operator Characteristic (ROC) curve. In this paper we investigate the generalization performance of online learning algorithms with pairwise loss functions. We show that the existing proof techniques for generalization bounds of online a...
متن کاملOnline Learning with Composite Loss Functions
We study a new class of online learning problems where each of the online algorithm’s actions is assigned an adversarial value, and the loss of the algorithm at each step is a known and deterministic function of the values assigned to its recent actions. This class includes problems where the algorithm’s loss is the minimum over the recent adversarial values, the maximum over the recent values,...
متن کاملLow-Rank Spectral Learning with Weighted Loss Functions
Kulesza et al. [2014] recently observed that low-rank spectral learning algorithms, which discard the smallest singular values of a moment matrix during training, can behave in unexpected ways, producing large errors even when the discarded singular values are arbitrarily small. In this paper we prove that when learning predictive state representations those problematic cases disappear if we in...
متن کاملRelative Deviation Learning Bounds and Generalization with Unbounded Loss Functions
We present an extensive analysis of relative deviation bounds, including detailed proofs of twosided inequalities and their implications. We also give detailed proofs of two-sided generalization bounds that hold in the general case of unbounded loss functions, under the assumption that a moment of the loss is bounded. These bounds are useful in the analysis of importance weighting and other lea...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Computational Physics
سال: 2022
ISSN: ['1090-2716', '0021-9991']
DOI: https://doi.org/10.1016/j.jcp.2022.111121