Shashank Agnihotri
Research Assistant at Universität Siegen
Mannheim, Baden-Württemberg, Germany
Summary
👤
Senior🎓
Top SchoolShashank Agnihotri is a research-focused machine learning engineer and PhD candidate with nine years of experience across computer vision, NLP, IoT and robust ML. Based in Mannheim, he contributes to academic and open-source ecosystems—authoring multiple conference and journal papers (including an ICML workshop paper) and implementing the GSparsity optimizer in the widely used NASLib repository. His work spans hands-on optimizer and architecture search integration, applied research roles at University of Freiburg and Siegen, and recent research assistance at the Data and Web Science Group. Notably, he blends practical engineering changes in neural architecture search with theoretical robustness investigations for compressed CNNs, demonstrating a rare mix of reproducible code contributions and peer-reviewed scholarship.
9 years of coding experience
1 year of employment as a software developer
Masters of Science, Informatics, 2.0, Masters of Science, Informatics, 2.0 at The University of FreiburgDoctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at University of SiegenBachelor of Engineering - BE, Computer Science, 7.84, Bachelor of Engineering - BE, Computer Science, 7.84 at Vivekanand Education Society's Institute of Technology
English, Hindi, Marathi, Marathi, German
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (8)
algorithm10
pytorch10
machine-learning10
automl10
python10
optimizers10
optimisation10
optimization10
Programming languages (4)
Github contributions (5)
automl/NASLib
Feb 2022 - Dec 2022
NASLib is a Neural Architecture Search (NAS) library for facilitating NAS research for the community by providing interfaces to several state-of-the-art NAS search spaces and optimizers.
Role in this project:
ML Engineer
ML EngineerContributions:44 commits, 33 PRs, 27 pushes in 10 months
Contributions summary:Shashank primarily focused on implementing and refining the GSparsity optimizer, a core component of the Neural Architecture Search (NAS) library. They modified the optimizer class, updated its integration with the search space, and adjusted the discretization process for architecture selection. The contributions also include changes to the underlying mixed operation and the addition of utility functions related to the optimizer. These changes suggest a deep involvement in integrating the GSparsity method.
artnasneural-architecture-searchstate-of-the-artmachine-learning
BE-PROJECTS2018/Group-No.-10---Stylometry-Based-Authorship-Identitifcation
Apr 2018 - Dec 2020
Contributions:2 PRs, 9 pushes, 2 branches in 2 years 8 months
placementsparticularhandwritingsentencesto-do
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.