Generator Based Inference (GBI)

• URL: http://arxiv.org/abs/2506.00119v1
• Date: Fri, 30 May 2025 18:00:08 GMT
• Title: Generator Based Inference (GBI)
• Authors: Chi Lung Cheng, Ranit Das, Runze Li, Radha Mastandrea, Vinicius Mikuni, Benjamin Nachman, David Shih, Gup Singh,
• Abstract summary: We propose a general framework for describing the integration of machine learning with generators called Generator Based Inference (GBI)<n>In particular, we focus on resonant anomaly detection, where the generator describing the background is learned from sidebands.<n>This transforms the statistical outputs of anomaly detection to be directly interpretable and the performance on the LHCO community benchmark dataset establishes a new state-of-the-art for anomaly detection sensitivity.
• Score: 5.2994966713734915
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Statistical inference in physics is often based on samples from a generator (sometimes referred to as a ``forward model") that emulate experimental data and depend on parameters of the underlying theory. Modern machine learning has supercharged this workflow to enable high-dimensional and unbinned analyses to utilize much more information than ever before. We propose a general framework for describing the integration of machine learning with generators called Generator Based Inference (GBI). A well-studied special case of this setup is Simulation Based Inference (SBI) where the generator is a physics-based simulator. In this work, we examine other methods within the GBI toolkit that use data-driven methods to build the generator. In particular, we focus on resonant anomaly detection, where the generator describing the background is learned from sidebands. We show how to perform machine learning-based parameter estimation in this context with data-derived generators. This transforms the statistical outputs of anomaly detection to be directly interpretable and the performance on the LHCO community benchmark dataset establishes a new state-of-the-art for anomaly detection sensitivity.

Related papers

• Breaking Latent Prior Bias in Detectors for Generalizable AIGC Image Detection [11.907536189598577]
  Current AIGC detectors often achieve near-perfect accuracy on images produced by the same generator used for training but struggle to generalize to outputs from unseen generators.<n>We trace this failure in part to latent prior bias: detectors learn shortcuts tied to patterns stemming from the initial noise vector rather than learning robust generative artifacts.<n>We propose On-Manifold Adversarial Training (OMAT), which generates adversarial examples that remain on the generator's output manifold.
  arXiv  Detail & Related papers  (2025-06-01T07:20:45Z)
• Diffusion posterior sampling for simulation-based inference in tall data settings [53.17563688225137]
  Simulation-based inference ( SBI) is capable of approximating the posterior distribution that relates input parameters to a given observation. In this work, we consider a tall data extension in which multiple observations are available to better infer the parameters of the model. We compare our method to recently proposed competing approaches on various numerical experiments and demonstrate its superiority in terms of numerical stability and computational cost.
  arXiv  Detail & Related papers  (2024-04-11T09:23:36Z)
• Improving Out-of-Distribution Robustness of Classifiers via Generative Interpolation [56.620403243640396]
  Deep neural networks achieve superior performance for learning from independent and identically distributed (i.i.d.) data. However, their performance deteriorates significantly when handling out-of-distribution (OoD) data. We develop a simple yet effective method called Generative Interpolation to fuse generative models trained from multiple domains for synthesizing diverse OoD samples.
  arXiv  Detail & Related papers  (2023-07-23T03:53:53Z)
• Evaluating generative models in high energy physics [7.545095780512178]
  We present the first systematic review and investigation into evaluation metrics and their sensitivity to failure modes of generative models. We propose two new metrics, the Fr'echet and kernel physics distances (FPD and KPD, respectively), and perform a variety of experiments measuring their performance. We demonstrate the efficacy of these proposed metrics in evaluating and comparing a novel attention-based generative adversarial particle transformer to the state-of-the-art message-passing generative adversarial network jet simulation model.
  arXiv  Detail & Related papers  (2022-11-18T15:36:28Z)
• Learning Probabilistic Models from Generator Latent Spaces with Hat EBM [81.35199221254763]
  This work proposes a method for using any generator network as the foundation of an Energy-Based Model (EBM) Experiments show strong performance of the proposed method on (1) unconditional ImageNet synthesis at 128x128 resolution, (2) refining the output of existing generators, and (3) learning EBMs that incorporate non-probabilistic generators.
  arXiv  Detail & Related papers  (2022-10-29T03:55:34Z)
• Momentum Adversarial Distillation: Handling Large Distribution Shifts in Data-Free Knowledge Distillation [65.28708064066764]
  We propose a simple yet effective method called Momentum Adversarial Distillation (MAD) MAD maintains an exponential moving average (EMA) copy of the generator and uses synthetic samples from both the generator and the EMA generator to train the student. Our experiments on six benchmark datasets including big datasets like ImageNet and Places365 demonstrate the superior performance of MAD over competing methods.
  arXiv  Detail & Related papers  (2022-09-21T13:53:56Z)
• An Energy-Based Prior for Generative Saliency [62.79775297611203]
  We propose a novel generative saliency prediction framework that adopts an informative energy-based model as a prior distribution. With the generative saliency model, we can obtain a pixel-wise uncertainty map from an image, indicating model confidence in the saliency prediction. Experimental results show that our generative saliency model with an energy-based prior can achieve not only accurate saliency predictions but also reliable uncertainty maps consistent with human perception.
  arXiv  Detail & Related papers  (2022-04-19T10:51:00Z)
• Leveraging Global Parameters for Flow-based Neural Posterior Estimation [90.21090932619695]
  Inferring the parameters of a model based on experimental observations is central to the scientific method. A particularly challenging setting is when the model is strongly indeterminate, i.e., when distinct sets of parameters yield identical observations. We present a method for cracking such indeterminacy by exploiting additional information conveyed by an auxiliary set of observations sharing global parameters.
  arXiv  Detail & Related papers  (2021-02-12T12:23:13Z)
• Simulating the Time Projection Chamber responses at the MPD detector using Generative Adversarial Networks [0.0]
  In this work, we demonstrate a novel approach to speed up the simulation of the Time Projection Chamber tracker of the MPD experiment at the NICA accelerator complex. Our method is based on a Generative Adrial Network - a deep learning technique allowing for implicit non-parametric estimation of the population distribution for a given set of objects. To evaluate the quality of the proposed model, we integrate it into the MPD software stack and demonstrate that it produces high-quality events similar to the detailed simulator.
  arXiv  Detail & Related papers  (2020-12-08T17:57:37Z)
• Self-awareness in intelligent vehicles: Feature based dynamic Bayesian models for abnormality detection [4.251384905163326]
  This paper aims to introduce a novel method to develop self-awareness in autonomous vehicles. Time-series data from the vehicles are used to develop the data-driven Dynamic Bayesian Network (DBN) models. An initial level collective awareness model that can perform joint anomaly detection in co-operative tasks is proposed.
  arXiv  Detail & Related papers  (2020-10-29T09:29:47Z)
• Parameter Estimation using Neural Networks in the Presence of Detector Effects [4.230838081898361]
  Histogram-based template fits are the main technique used for estimating parameters of high energy physics Monte Carlo generators. Parametrized neural network reweighting can be used to extend this fitting procedure to many dimensions and does not require binning. We introduce a new two-level fitting approach that only requires one dataset with detector simulation and then a set of additional generation-level datasets without detector effects included.
  arXiv  Detail & Related papers  (2020-10-07T18:00:01Z)

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.