Speaker:	Subhadeep Sarkar (the Indian Institute of Technology Patna (IIT Patna))
Title:	Hunting Sparticles at the LHC using Machine Learning
Date (JST):	Wed, Mar 11, 2026, 13:30 - 15:00
Place:	Seminar Room A
Abstract:	Supersymmetry (SUSY) stands out as one of the most compelling frameworks for physics beyond the Standard Model. In the Minimal Supersymmetric Standard Model (MSSM) with R-parity conservation, the lightest supersymmetric particle (LSP) is stable and provides a well-motivated dark matter candidate. Alternatively, R-parity violating (RPV) scenarios offer an attractive mechanism to generate neutrino masses, thereby addressing another fundamental limitation of the Standard Model. Both the ATLAS and CMS collaborations have extensively searched for SUSY signatures at the Large Hadron Collider (LHC); however, the absence of any confirmed signal has led to stringent lower bounds on sparticle masses. While the colored sector of the RPV spectrum is tightly constrained, the electroweak sector remains comparatively less restricted. With the LHC entering its high-luminosity phase and prospects of further energy upgrades, it becomes crucial to systematically assess the discovery and exclusion potential for electroweakinos at the High Luminosity-LHC and High Energy-LHC. In this talk, we explore the search sensitivities of electroweakinos at future colliders using modern machine learning (ML) tools, which can efficiently capture complex correlations among multiple kinematic observables and significantly enhance signal–background discrimination compared to traditional cut-based methods. Furthermore, we investigate the possibility of reconstructing heavy sparticle masses directly from detector-level data in the presence of an excess over the Standard Model expectation, demonstrating how advanced ML techniques can improve both discovery prospects and parameter determination in supersymmetric scenarios.

← Back