About Me
About Me
I'm a research fellow in the Kempner Institute at Harvard University. Previously, I did my PhD at the School of Computer Science and Engineering in the Hebrew University of Jerusalem, advised by Prof. Shai Shalev-Shwartz.
My research focus is Machine Learning and Theoretical Foundations of Deep Learning and Language Models. I'm mainly interested in computational aspects of learning and optimization.
Contact:
Contact:
Email: eran.malach (at) gmail.com
Research Highlights
Transcendence: Generative Models Can Outperform The Experts That Train Them
Transcendence: Generative Models Can Outperform The Experts That Train Them
Repeat After Me: Transformers are Better than State Space Models at Copying
Repeat After Me: Transformers are Better than State Space Models at Copying
Auto-Regressive Next-Token Predictors are Universal Learners
Auto-Regressive Next-Token Predictors are Universal Learners