arXiv:2608. 06291v1 Announce Type: cross Abstract: We accelerate a family of algorithms for neural network quantization whose geometry is informed by any Kronecker-factored approximation of the Hessian.
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 arXiv AI.
arXiv:2505. 22988v3 Announce Type: replace-cross Abstract: The goal of quantization is to produce a compressed model whose output distribution is as close to the original model's as possible.
The paper introduces WaterKron, a method that integrates two-sided GPTQ with row- and column-dependent waterfilling scales and entropy coding for post‑training quantization. It derives a high‑rate distortion measure relative to the full Hessian, introducing a Kronecker‑Hessian mismatch factor Φ that quantifies the distortion penalty of using a Kronecker approximation. Minimizing Φ leads to a Gaussian covariance‑fitting problem solved via classical flip‑flop updates, yielding a FlipFlop Hessian that empirically improves KL divergence and perplexity compared to other Hessian choices.
arXiv:2605.11222v2 Announce Type: replace Abstract: Quantization is an effective strategy to reduce the storage and computation footprint of large language models (LLMs). Post-training quantization (...
arXiv:2607. 07964v1 Announce Type: new Abstract: Post-training quantization (PTQ) is a widely adopted technique for compressing large language models (LLMs) without retraining.
arXiv:2510. 18784v3 Announce Type: replace Abstract: Despite significant work on low-bit quantization-aware training (QAT), there is still an accuracy gap between such techniques and native training.
arXiv:2607. 27042v1 Announce Type: cross Abstract: Adaptive rounding methods such as GPTQ, or equivalently Babai's nearest plane algorithm, round a real matrix to integers under a quadratic metric.