Scholar
Behrooz Tahmasebi
Google Scholar ID: ZXCO3DMAAAAJ
PhD student in EECS at MIT
Citations & Impact
Citations
161
H-index
6
i10-index
5
Publications
17
Co-authors
10
list available
Contact
Resume (English only)
Academic Achievements
- ICML 2025 Spotlight paper (top 2.6%): 'Learning with Exact Invariances in Polynomial Time'
- ICLR 2025: 'Generalization Bounds for Canonicalization: A Comparative Study with Group Averaging'
- AISTATS 2025: Two papers, including 'A Robust Kernel Statistical Test of Invariance' (Oral, top 2%)
- NeurIPS 2024: 'Coded Computing for Resilient Distributed Computing: A Learning-Theoretic Framework'
- ICML 2024: 'A Universal Class of Sharpness-Aware Minimization Algorithms' – Best Paper Award at HiLD workshop
- ICML 2024: 'Sample Complexity Bounds for Estimating Probability Divergences under Invariances'
- NeurIPS 2023 Spotlight (top 3.6%): 'The Exact Sample Complexity Gain from Invariances for Kernel Regression'
- AISTATS 2023 Oral (top 1.9%): 'The Power of Recursion in Graph Neural Networks for Counting Substructures'
- Multiple publications in IEEE Transactions on Information Theory, ISIT, ITW, JSAC, etc., on information theory and function computation
