Keeping Score: Efficiency Improvements in Neural Likelihood Surrogate Training via Score-Augmented Loss Functions

• URL: http://arxiv.org/abs/2605.12118v1
• Date: Tue, 12 May 2026 13:34:30 GMT
• Title: Keeping Score: Efficiency Improvements in Neural Likelihood Surrogate Training via Score-Augmented Loss Functions
• Abstract summary: parameter inference is often bottlenecked by computationally expensive likelihood functions.<n>We propose to augment the standard binary cross-entropy loss with exact score information.<n>In some cases, our approach achieves a 10x increase in training data with less than a 1.1x increase in training time.
• Score: 46.638644823334424
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: For stochastic process models, parameter inference is often severely bottlenecked by computationally expensive likelihood functions. Simulation-based inference (SBI) bypasses this restriction by constructing amortized surrogate likelihoods, but most SBI methods assume a black-box data generating process. While these surrogates are exact in the limit of infinite training data, practical scenarios force a strict tradeoff between model quality and simulation cost. In this work, we loosen the black-box assumption of SBI to improve this tradeoff for structured stochastic process models. Specifically, for neural network likelihood surrogates trained via probabilistic classification, we propose to augment the standard binary cross-entropy loss with exact score information $\nabla_θ\log p(x \mid θ)$ and adaptive weighting based on loss gradients. We evaluate our approach on case studies involving network dynamics and spatial processes, demonstrating that our method improves surrogate quality at a drastically lower computational cost than generating more training data. Notably, in some cases, our approach achieves downstream inference performance equivalent to a 10x increase in training data with less than a 1.1x increase in training time.

Related papers

• Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learning [45.78096783448304]
  In this work, seeking data efficiency, we design unsupervised pretraining for PDE operator learning.<n>We mine unlabeled PDE data without simulated solutions, and we pretrain neural operators with physics-inspired reconstruction-based proxy tasks.<n>Our method is highly data-efficient, more generalizable, and even outperforms conventional vision-pretrained models.
  arXiv  Detail & Related papers  (2024-02-24T06:27:33Z)
• Adaptive operator learning for infinite-dimensional Bayesian inverse problems [7.716833952167609]
  We develop an adaptive operator learning framework that can reduce modeling error gradually by forcing the surrogate to be accurate in local areas. We present a rigorous convergence guarantee in the linear case using the UKI framework. The numerical results show that our method can significantly reduce computational costs while maintaining inversion accuracy.
  arXiv  Detail & Related papers  (2023-10-27T01:50:33Z)
• IB-UQ: Information bottleneck based uncertainty quantification for neural function regression and neural operator learning [11.5992081385106]
  We propose a novel framework for uncertainty quantification via information bottleneck (IB-UQ) for scientific machine learning tasks. We incorporate the bottleneck by a confidence-aware encoder, which encodes inputs into latent representations according to the confidence of the input data. We also propose a data augmentation based information bottleneck objective which can enhance the quality of the extrapolation uncertainty.
  arXiv  Detail & Related papers  (2023-02-07T05:56:42Z)
• Data efficient surrogate modeling for engineering design: Ensemble-free batch mode deep active learning for regression [0.6021787236982659]
  We propose a simple and scalable approach for active learning that works in a student-teacher manner to train a surrogate model. By using this proposed approach, we are able to achieve the same level of surrogate accuracy as the other baselines like DBAL and Monte Carlo sampling.
  arXiv  Detail & Related papers  (2022-11-16T02:31:57Z)
• Scaling Laws Beyond Backpropagation [64.0476282000118]
  We study the ability of Direct Feedback Alignment to train causal decoder-only Transformers efficiently. We find that DFA fails to offer more efficient scaling than backpropagation.
  arXiv  Detail & Related papers  (2022-10-26T10:09:14Z)
• Deep Equilibrium Optical Flow Estimation [80.80992684796566]
  Recent state-of-the-art (SOTA) optical flow models use finite-step recurrent update operations to emulate traditional algorithms. These RNNs impose large computation and memory overheads, and are not directly trained to model such stable estimation. We propose deep equilibrium (DEQ) flow estimators, an approach that directly solves for the flow as the infinite-level fixed point of an implicit layer.
  arXiv  Detail & Related papers  (2022-04-18T17:53:44Z)
• Test-time Batch Statistics Calibration for Covariate Shift [66.7044675981449]
  We propose to adapt the deep models to the novel environment during inference. We present a general formulation $alpha$-BN to calibrate the batch statistics. We also present a novel loss function to form a unified test time adaptation framework Core.
  arXiv  Detail & Related papers  (2021-10-06T08:45:03Z)
• Last Layer Marginal Likelihood for Invariance Learning [12.00078928875924]
  We introduce a new lower bound to the marginal likelihood, which allows us to perform inference for a larger class of likelihood functions. We work towards bringing this approach to neural networks by using an architecture with a Gaussian process in the last layer.
  arXiv  Detail & Related papers  (2021-06-14T15:40:51Z)
• Scalable Marginal Likelihood Estimation for Model Selection in Deep Learning [78.83598532168256]
  Marginal-likelihood based model-selection is rarely used in deep learning due to estimation difficulties. Our work shows that marginal likelihoods can improve generalization and be useful when validation data is unavailable.
  arXiv  Detail & Related papers  (2021-04-11T09:50:24Z)
• Predicting Training Time Without Training [120.92623395389255]
  We tackle the problem of predicting the number of optimization steps that a pre-trained deep network needs to converge to a given value of the loss function. We leverage the fact that the training dynamics of a deep network during fine-tuning are well approximated by those of a linearized model. We are able to predict the time it takes to fine-tune a model to a given loss without having to perform any training.
  arXiv  Detail & Related papers  (2020-08-28T04:29:54Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.