Event

ECE Special Seminar - Professor Or Ordentlich, Hebrew University of Jerusalem

Wednesday, November 18, 2026
2:00 a.m.
2168 A. V. Williams
Darcy Long
301 405 3114
dlong123@umd.edu

Speaker: Professor Or Ordentlich, Hebrew University of Jerusalem

Title: Quantized Matrix Multiplication -Theory and Practice

Abstract: Matrix multiplication is the main computational building block of large language models, and is often bottlenecked by moving data from memory. Quantization reduces this cost by representing matrices with fewer bits, but introduces errors that can degrade model accuracy. This talk explores how information theory can guide the design of accurate and efficient quantization schemes. We begin with the rate-distortion function for Gaussian matrix multiplication and a nested-lattice construction that asymptotically achieves this limit. We then discuss NestQuant, which brings these ideas to LLM quantization, and hierarchical lattice schemes that enable matrix multiplication using small lookup tables. Finally, we turn to activation statistics and hardware constraints: WaterSIC combines rate allocation with successive interference cancellation to approach information-theoretic limits for weight quantization, while OSFP4 jointly optimizes diagonal smoothing and block scales for the NVFP4 format. These results connect fundamental limits with practical methods for preserving LLM accuracy at low precision.

Bio: Or Ordentlich received the B.Sc. (cum laude), M.Sc. (summa cum laude), and Ph.D. degrees in electrical engineering from Tel Aviv University, Tel Aviv, Israel, in 2010, 2011, and 2016, respectively. He is an Associate Professor with the School of Computer Science and Engineering, Hebrew University of Jerusalem, Jerusalem, Israel. From 2015 to 2017, he was a Post-doctoral Fellow with the Laboratory for Information and Decision Systems, Massachusetts Institute of Technology (MIT), Cambridge, MA, USA, and the Department of Electrical and Computer Engineering, Boston University, Boston, MA. His research interests include information theory, and its application to modern problems in communication, compression, and data science.

Dr. Ordentlich was the recipient of the 2026 IEEE Information Theory Society James Massey Award and was the recipient of the Frontier of the Science Award in 2025 for his work on lattice covering. He has been an Associate Editor for Signal Processing and Source Coding in IEEE Transactions on Information Theory since 2021.