3 papers
cs.LG2026
Activation Denoising: A Robustness View on Parallel vs Sequential LLM Quantization
Yan Scholten, Rachel Lawrence, James Hensman +3
Post-training quantization is a powerful tool for compressing large language models. The most scalable methods quantize every layer in parallel, but quantization errors then compou…
math.OC2026
Bilevel learning
Riccardo Grazzi, Massimiliano Pontil, Saverio Salzo +1
Bilevel learning refers to machine learning problems that can be formulated as bilevel optimization models, where decisions are organized in a hierarchical structure. This paradigm…
cs.LG2026
OptRot: Mitigating Weight Outliers via Data-Free Rotations for Post-Training Quantization
Advait Gadhikar, Riccardo Grazzi, James Hensman
The presence of outliers in Large Language Models (LLMs) weights and activations makes them difficult to quantize. Recent work has leveraged rotations to mitigate these outliers. I…