WaterKron and FlipFlop Hessian: Information-Theoretically Grounded Quantization with Kronecker-factored Hessians

arXiv:2609.14706 · cs.LG, cs.AI · Submitted 2026-09-13 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-09-13

Updated: 2026-09-27

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Quantization — 38× in this paper · explained in 12 episodes
• Calibration — 7× in this paper · explained in 7 episodes
• Core — 5× in this paper · explained in 2 episodes
• Perplexity — 3× in this paper · explained in 3 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Decode — 1× in this paper · explained in 2 episodes
• Elias — 1× in this paper · explained in 2 episodes
• Fisher Information — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• FastKron: Efficient Quantization with Kronecker-Factored Hessians
• SoftWater: Class-Aware Rate Allocation for Softmax Quantization
• GPTQ-2D: Cubic-Time Two-Sided Adaptive Rounding
• The Pile: An 800GB Dataset of Diverse Text for Language Modeling
• The Llama 3 Herd of Models
• Pointer Sentinel Mixture Models
• High-Rate Quantized Matrix Multiplication II
• Qwen3 Technical Report
• Provable Post-Training Quantization: Theoretical Analysis of OPTQ and Qronos

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks