AI RESEARCH
Quantizing With Randomized Hadamard Transforms: Efficient Heuristic Now Proven
arXiv CS.LG
•
ArXi:2605.06014v1 Announce Type: new Uniform random rotations (URRs) are a common preprocessing step in modern quantization approaches used for gradient compression, inference acceleration, KV-cache compression, model weight quantization, and approximate nearest-neighbor search in vector databases. In practice, URRs are often replaced by randomized Hadamard transforms (RHTs), which preserve orthogonality while admitting fast implementations. The remaining issue is the performance for worst-case inputs.