collaborators

10 papers

cs.IT2026

Price of metric universality in vector quantization is at most 0.11 bit

Alina Harbuzova, Or Ordentlich, Yury Polyanskiy

Fast computation of a matrix product is a workhorse of modern LLMs. To make their deployment more efficient, a popular approach is that of using a low-precision approxim…

cs.LG2026

High-Rate Quantized Matrix Multiplication II

Or Ordentlich, Yury Polyanskiy

This is the second part of the work investigating quantized matrix multiplication (MatMul). In part I we considered the case of calibration-free quantization, whereas here we discu…

cs.LG2026

WaterSIC: Information-Theoretically (Near) Optimal Linear Layer Quantization

Egor Lifar, Semyon Savkin, Or Ordentlich +1

This paper considers the problem of converting a given dense linear layer to low precision. The tradeoff between compressed length and output discrepancy is analyzed information th…

cs.IT2026

High-Rate Quantized Matrix Multiplication I

Or Ordentlich, Yury Polyanskiy

This paper investigates the problem of quantized matrix multiplication (MatMul), which has become crucial for the efficient deployment of large language models (LLMs). We consider…

cs.IT2026

The Voronoi Spherical CDF for Lattices and Linear Codes: New Bounds for Quantization and Coding

Or Ordentlich

For a lattice/linear code, we define the Voronoi spherical cumulative density function (CDF) as the CDF of the -norm/Hamming weight of a random vector uniformly distributed…

cs.IT2025

Optimal Quantization for Matrix Multiplication

Or Ordentlich, Yury Polyanskiy

Recent work in machine learning community proposed multiple methods for performing lossy compression (quantization) of large matrices. This quantization is important for accelerati…