Scholar
Kristian Georgiev
Google Scholar ID: t8RKSJsAAAAJ
OpenAI
Citations & Impact
Citations
590
H-index
10
i10-index
10
Publications
11
Co-authors
21
list available
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Publications: TRAK: Attributing Model Behavior at Scale (ICML 2023); Rethinking Backdoor Attacks (ICML 2023); Privacy Induces Robustness: Information-Computation Gaps and Sparse Mean Estimation (NeurIPS 2022); Implicit Bias of Linear Equivariant Networks (ICML 2022); On the Convergence Theory of Debiased Model-Agnostic Meta-Reinforcement Learning (NeurIPS 2021).
Research Experience
- Worked at QuantCo and Apple. Currently a second-year PhD student at MIT.
Education
- PhD candidate, MIT EECS, Advisor: Aleksander Mądry; S.B. MIT, Advisor: Asuman Özdağlar, as a SuperUROP scholar.
Background
- Research Interests: Science of deep learning, deep learning for science, adversarial robustness, and privacy. Personal Background: Obtained a joint degree in Math and Computer Science from MIT.
Miscellany
- Grew up in Bulgaria. Enjoys playing soccer and chess. Led the AI@MIT club at MIT.
