Most engineers see quantization as shrinking vectors. TurboQuant asks a harder question: can you shrink them without breaking their geometry?
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Towards Data Science.
arXiv:2608. 11240v1 Announce Type: new Abstract: Vector quantization is an old problem but has recently become central to AI infrastructure.
arXiv:2603. 11021v2 Announce Type: replace Abstract: Scalar quantization of large language models (LLMs) is fundamentally limited by information-theoretic bounds.
arXiv:2601. 21626v2 Announce Type: replace-cross Abstract: Post Training Quantization (PTQ), a mainstream model compression technique, often leads to the paradoxical 'low error, high loss' phenomenon because it focuses solely on minimizing quantization error.
arXiv:2608. 05127v1 Announce Type: cross Abstract: Achieving local differential privacy in distributed optimization while maintaining low communication cost remains challenging.
ShamAN-Q is a sub‑1‑bit post‑training quantization technique that builds on NanoQuant by replacing its diagonal reconstruction geometry with a dense curvature metric inspired by the Shampoo optimizer. For each linear weight, it fits a Kronecker product to the empirical Fisher information matrix of a small calibration set via Kullback–Leibler minimization, yielding a Mahalanobis reconstruction loss. The method updates continuous ADMM steps to Sylvester equations while keeping the discrete projection and deployment format unchanged, and it redistributes uniform rank across layers, achieving lower perplexity on Qwen3‑Base at roughly 1 bpw and matching or improving zero‑shot accuracy on the Eleuther LM Evaluation Harness.