Flows for Flows: Morphing one Dataset into another with Maximum Likelihood Estimation

• URL: http://arxiv.org/abs/2309.06472v1
• Date: Tue, 12 Sep 2023 18:00:01 GMT
• Title: Flows for Flows: Morphing one Dataset into another with Maximum Likelihood Estimation
• Authors: Tobias Golling, Samuel Klein, Radha Mastandrea, Benjamin Nachman, John Andrew Raine
• Abstract summary: We propose a protocol called flows for flows for training normalizing flows to morph one dataset into another. This enables a morphing strategy trained with maximum likelihood estimation. We show how to condition the learned flows on particular features in order to create a morphing function for every value of the conditioning feature.
• Score: 2.240286607818126
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many components of data analysis in high energy physics and beyond require morphing one dataset into another. This is commonly solved via reweighting, but there are many advantages of preserving weights and shifting the data points instead. Normalizing flows are machine learning models with impressive precision on a variety of particle physics tasks. Naively, normalizing flows cannot be used for morphing because they require knowledge of the probability density of the starting dataset. In most cases in particle physics, we can generate more examples, but we do not know densities explicitly. We propose a protocol called flows for flows for training normalizing flows to morph one dataset into another even if the underlying probability density of neither dataset is known explicitly. This enables a morphing strategy trained with maximum likelihood estimation, a setup that has been shown to be highly effective in related tasks. We study variations on this protocol to explore how far the data points are moved to statistically match the two datasets. Furthermore, we show how to condition the learned flows on particular features in order to create a morphing function for every value of the conditioning feature. For illustration, we demonstrate flows for flows for toy examples as well as a collider physics example involving dijet events

Related papers

• How Does Data Diversity Shape the Weight Landscape of Neural Networks? [2.89287673224661]
  We investigate the impact of dropout, weight decay, and noise augmentation on the parameter space of neural networks. We observe that diverse data influences the weight landscape in a similar fashion as dropout. We conclude that synthetic data can bring more diversity into real input data, resulting in a better performance on out-of-distribution test instances.
  arXiv  Detail & Related papers  (2024-10-18T16:57:05Z)
• One flow to correct them all: improving simulations in high-energy physics with a single normalising flow and a switch [0.06597195879147556]
  imperfections in the simulation can lead to sizeable differences between the observed data and simulated events. We introduce a correction method that transforms one multidimensional distribution (simulation) into another one (data) using a simple architecture. We demonstrate the effectiveness of the method on a physics-inspired toy dataset with non-trivial mismodelling of several observables and their correlations.
  arXiv  Detail & Related papers  (2024-03-27T14:03:41Z)
• Binary Quantification and Dataset Shift: An Experimental Investigation [54.14283123210872]
  Quantification is the supervised learning task that consists of training predictors of the class prevalence values of sets of unlabelled data. The relationship between quantification and other types of dataset shift remains, by and large, unexplored. We propose a fine-grained taxonomy of types of dataset shift, by establishing protocols for the generation of datasets affected by these types of shift.
  arXiv  Detail & Related papers  (2023-10-06T20:11:27Z)
• Machine Learning Force Fields with Data Cost Aware Training [94.78998399180519]
  Machine learning force fields (MLFF) have been proposed to accelerate molecular dynamics (MD) simulation. Even for the most data-efficient MLFFs, reaching chemical accuracy can require hundreds of frames of force and energy labels. We propose a multi-stage computational framework -- ASTEROID, which lowers the data cost of MLFFs by leveraging a combination of cheap inaccurate data and expensive accurate data.
  arXiv  Detail & Related papers  (2023-06-05T04:34:54Z)
• Stubborn Lexical Bias in Data and Models [50.79738900885665]
  We use a new statistical method to examine whether spurious patterns in data appear in models trained on the data. We apply an optimization approach to *reweight* the training data, reducing thousands of spurious correlations. Surprisingly, though this method can successfully reduce lexical biases in the training data, we still find strong evidence of corresponding bias in the trained models.
  arXiv  Detail & Related papers  (2023-06-03T20:12:27Z)
• X-model: Improving Data Efficiency in Deep Learning with A Minimax Model [78.55482897452417]
  We aim at improving data efficiency for both classification and regression setups in deep learning. To take the power of both worlds, we propose a novel X-model. X-model plays a minimax game between the feature extractor and task-specific heads.
  arXiv  Detail & Related papers  (2021-10-09T13:56:48Z)
• FastIF: Scalable Influence Functions for Efficient Model Interpretation and Debugging [112.19994766375231]
  Influence functions approximate the 'influences' of training data-points for test predictions. We present FastIF, a set of simple modifications to influence functions that significantly improves their run-time. Our experiments demonstrate the potential of influence functions in model interpretation and correcting model errors.
  arXiv  Detail & Related papers  (2020-12-31T18:02:34Z)
• Can we learn where people come from? Retracing of origins in merging situations [0.0]
  We use density heatmaps that can be derived from sensor data as input for a random forest regressor to predict the origin distributions. We study three different datasets: A simulated dataset, experimental data, and a hybrid approach with both experimental and simulated data.
  arXiv  Detail & Related papers  (2020-12-21T17:42:14Z)
• ACRONYM: A Large-Scale Grasp Dataset Based on Simulation [64.37675024289857]
  ACRONYM is a dataset for robot grasp planning based on physics simulation. The dataset contains 17.7M parallel-jaw grasps, spanning 8872 objects from 262 different categories. We show the value of this large and diverse dataset by using it to train two state-of-the-art learning-based grasp planning algorithms.
  arXiv  Detail & Related papers  (2020-11-18T23:24:00Z)
• Dataset Dynamics via Gradient Flows in Probability Space [15.153110906331733]
  We propose a novel framework for dataset transformation, which we cast as optimization over data-generating joint probability distributions. We show that this framework can be used to impose constraints on classification datasets, adapt them for transfer learning, or to re-purpose fixed or black-box models to classify -- with high accuracy -- previously unseen datasets.
  arXiv  Detail & Related papers  (2020-10-24T03:29:22Z)
• Deep transformation models: Tackling complex regression problems with neural network based transformation models [0.0]
  We present a deep transformation model for probabilistic regression. It estimates the whole conditional probability distribution, which is the most thorough way to capture uncertainty about the outcome. Our method works for complex input data, which we demonstrate by employing a CNN architecture on image data.
  arXiv  Detail & Related papers  (2020-04-01T14:23:12Z)

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.