Hessian-based toolbox for reliable and interpretable machine learning in physics

• URL: http://arxiv.org/abs/2108.02154v1
• Date: Wed, 4 Aug 2021 16:32:59 GMT
• Title: Hessian-based toolbox for reliable and interpretable machine learning in physics
• Authors: Anna Dawid, Patrick Huembeli, Micha{\l} Tomza, Maciej Lewenstein, Alexandre Dauphin
• Abstract summary: We present a toolbox for interpretability and reliability, extrapolation of the model architecture. It provides a notion of the influence of the input data on the prediction at a given test point, an estimation of the uncertainty of the model predictions, and an agnostic score for the model predictions. Our work opens the road to the systematic use of interpretability and reliability methods in ML applied to physics and, more generally, science.
• Score: 58.720142291102135
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine learning (ML) techniques applied to quantum many-body physics have emerged as a new research field. While the numerical power of this approach is undeniable, the most expressive ML algorithms, such as neural networks, are black boxes: The user does neither know the logic behind the model predictions nor the uncertainty of the model predictions. In this work, we present a toolbox for interpretability and reliability, agnostic of the model architecture. In particular, it provides a notion of the influence of the input data on the prediction at a given test point, an estimation of the uncertainty of the model predictions, and an extrapolation score for the model predictions. Such a toolbox only requires a single computation of the Hessian of the training loss function. Our work opens the road to the systematic use of interpretability and reliability methods in ML applied to physics and, more generally, science.

Related papers

• Hypothesis Testing and Machine Learning: Interpreting Variable Effects in Deep Artificial Neural Networks using Cohen's f2 [0.0]
  Deep artificial neural networks show high predictive performance in many fields. But they do not afford statistical inferences and their black-box operations are too complicated for humans to comprehend. This article extends current XAI methods and develops a model agnostic hypothesis testing framework for machine learning.
  arXiv  Detail & Related papers  (2023-02-02T20:43:37Z)
• Prediction-Powered Inference [68.97619568620709]
  Prediction-powered inference is a framework for performing valid statistical inference when an experimental dataset is supplemented with predictions from a machine-learning system. The framework yields simple algorithms for computing provably valid confidence intervals for quantities such as means, quantiles, and linear and logistic regression coefficients. Prediction-powered inference could enable researchers to draw valid and more data-efficient conclusions using machine learning.
  arXiv  Detail & Related papers  (2023-01-23T18:59:28Z)
• Interpretable models for extrapolation in scientific machine learning [0.0]
  Complex machine learning algorithms often outperform simple regressions in interpolative settings. We examine the trade-off between model performance and interpretability across a broad range of science and engineering problems.
  arXiv  Detail & Related papers  (2022-12-16T19:33:28Z)
• Interpretable Self-Aware Neural Networks for Robust Trajectory Prediction [50.79827516897913]
  We introduce an interpretable paradigm for trajectory prediction that distributes the uncertainty among semantic concepts. We validate our approach on real-world autonomous driving data, demonstrating superior performance over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2022-11-16T06:28:20Z)
• An Explainable Regression Framework for Predicting Remaining Useful Life of Machines [6.374451442486538]
  This paper proposes an explainable regression framework for the prediction of machines' Remaining Useful Life (RUL) We also evaluate several Machine Learning (ML) algorithms including classical and Neural Networks (NNs) based solutions for the task.
  arXiv  Detail & Related papers  (2022-04-28T15:44:12Z)
• Learning continuous models for continuous physics [94.42705784823997]
  We develop a test based on numerical analysis theory to validate machine learning models for science and engineering applications. Our results illustrate how principled numerical analysis methods can be coupled with existing ML training/testing methodologies to validate models for science and engineering applications.
  arXiv  Detail & Related papers  (2022-02-17T07:56:46Z)
• Conformal prediction for the design problem [72.14982816083297]
  In many real-world deployments of machine learning, we use a prediction algorithm to choose what data to test next. In such settings, there is a distinct type of distribution shift between the training and test data. We introduce a method to quantify predictive uncertainty in such settings.
  arXiv  Detail & Related papers  (2022-02-08T02:59:12Z)
• NUQ: Nonparametric Uncertainty Quantification for Deterministic Neural Networks [151.03112356092575]
  We show the principled way to measure the uncertainty of predictions for a classifier based on Nadaraya-Watson's nonparametric estimate of the conditional label distribution. We demonstrate the strong performance of the method in uncertainty estimation tasks on a variety of real-world image datasets.
  arXiv  Detail & Related papers  (2022-02-07T12:30:45Z)
• Enhancing predictive skills in physically-consistent way: Physics Informed Machine Learning for Hydrological Processes [1.0635248457021496]
  We develop a Physics Informed Machine Learning (PIML) model that combines the process understanding of conceptual hydrological model with predictive abilities of state-of-the-art ML models. We apply the proposed model to predict the monthly time series of the target (streamflow) and intermediate variables (actual evapotranspiration) in the Narmada river basin in India.
  arXiv  Detail & Related papers  (2021-04-22T12:13:42Z)
• A Causal Lens for Peeking into Black Box Predictive Models: Predictive Model Interpretation via Causal Attribution [3.3758186776249928]
  We aim to address this problem in settings where the predictive model is a black box. We reduce the problem of interpreting a black box predictive model to that of estimating the causal effects of each of the model inputs on the model output. We show how the resulting causal attribution of responsibility for model output to the different model inputs can be used to interpret the predictive model and to explain its predictions.
  arXiv  Detail & Related papers  (2020-08-01T23:20:57Z)

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.