July 11, 2025 Doctoral Dissertation Open Access

Bal, Aritra

JSON Export

{
  "conceptrecid": "22336", 
  "created": "2025-07-28T15:42:30.474327+00:00", 
  "files": [
    {
      "bucket": "429be66d-6fd2-4635-9ff7-c4075b5eeb9a", 
      "checksum": "md5:28e501a400a159ae7a647e9590b4510b", 
      "key": "Classical_and_Quantum_Machine_Learning_for_Anomaly_Detection_at_the_CMS_Experiment_and_Beyond.pdf", 
      "links": {
        "self": "https://publish.etp.kit.edu/api/files/429be66d-6fd2-4635-9ff7-c4075b5eeb9a/Classical_and_Quantum_Machine_Learning_for_Anomaly_Detection_at_the_CMS_Experiment_and_Beyond.pdf"
      }, 
      "size": 14886938, 
      "type": "pdf"
    }
  ], 
  "id": 22337, 
  "links": {
    "bucket": "https://publish.etp.kit.edu/api/files/429be66d-6fd2-4635-9ff7-c4075b5eeb9a", 
    "html": "https://publish.etp.kit.edu/record/22337", 
    "latest": "https://publish.etp.kit.edu/api/records/22337", 
    "latest_html": "https://publish.etp.kit.edu/record/22337"
  }, 
  "metadata": {
    "access_right": "open", 
    "access_right_category": "success", 
    "communities": [
      {
        "id": "etp"
      }
    ], 
    "contributors": [], 
    "creators": [
      {
        "affiliation": "KIT/ETP", 
        "name": "Bal, Aritra"
      }
    ], 
    "description": "<p>This thesis presents two novel methodologies for anomaly detection in particle collision events, utilising both classical and quantum machine learning techniques. The first approach employs an unsupervised, data-driven variational autoencoder (VAE), trained on collision data recorded by the CMS detector at the Large Hadron Collider during Run 2.&nbsp;No significant excess above the Standard Model (SM) expectation is observed. This method is subsequently used to derive exclusion limits on a large number of exotic signal models derived from Beyond the Standard Model (BSM) physics.&nbsp;The second approach introduces a novel quantum machine learning framework, named <em>1P1Q</em>, for encoding jet kinematic features onto two-level quantum bits (qubits).&nbsp;For both the anomaly detection and supervised classification tasks, the <em>1P1Q</em> method is demonstrated to achieve signal identification and separation performance comparable to or surpassing current state-of-the-art classical machine learning algorithms.</p>", 
    "keywords": [
      "machine learning", 
      "quantum machine learning", 
      "anomaly detection", 
      "BSM physics", 
      "EXO", 
      "CMS", 
      "model-agnostic", 
      "unsupervised", 
      "ML", 
      "searches", 
      "CMS", 
      "ETP"
    ], 
    "language": "eng", 
    "publication_date": "2025-07-11", 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "22337"
          }, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "22336"
          }
        }
      ]
    }, 
    "resource_type": {
      "subtype": "phd-thesis", 
      "title": "Doctoral Dissertation", 
      "type": "thesis"
    }, 
    "thesis": {
      "report_number": "ETP-KA/2025-06", 
      "supervisors": [
        {
          "affiliation": "KIT/ETP", 
          "name": "Klute, Markus"
        }, 
        {
          "affiliation": "KIT/ETP", 
          "name": "Wolf, Roger"
        }, 
        {
          "affiliation": "Imperial College, London", 
          "name": "Maier, Benedikt"
        }
      ]
    }, 
    "title": "Classical and Quantum Machine Learning for Anomaly Detection at the CMS Experiment and Beyond"
  }, 
  "owners": [
    106
  ], 
  "revision": 3, 
  "stats": {}, 
  "updated": "2025-08-07T08:58:39.260580+00:00"
}