MT
Mads Toftrup
cs.LGcs.CLcs.AIcs.DSmath.OCstat.ML
On Valency
published · living versionsW_r72x54u6·v1 · currentpublished
A Unified Hessian-Guided Framework for Post-Training Quantization
with Marco Federici, Boris van Breugel, Paul Whatmough, Markus Nagel
1 version
Preprints & journals
6 papers in the corpus · 2021–2026SS-ESOAP: Self-Scaled Adaptive Preconditioning for Physics-Informed Learning2608.29448v1 · Guangyuan Wang, Mads Toftrup, Sebastian Loeschcke et al.2026 · 0 citationsarXiv
M+Adam: Low-Precision Training via Additive-Multiplicative Optimization2607.10611v2 · Xiaoyuan Liang, Sebastian Loeschcke, Mads Toftrup et al.2026 · 0 citationsarXiv
LoQT: Low-Rank Adapters for Quantized Pretraining2405.16528v4 · Sebastian Loeschcke, Mads Toftrup, Michael J. Kastoryano et al.2024 · 1 citationarXiv
On Generalization Bounds for Projective Clustering2310.09127v1 · Maria Sofia Bucarelli, Matilde FjeldsøLarsen, Chris Schwiegelshohn et al.2023 · 0 citationsarXiv
The Power of Uniform Sampling for Coresets2209.01901v2 · Vladimir Braverman, Vincent Cohen-Addad, Shaofeng H.-C. Jiang et al.2022 · 20 citationsarXiv
A reproduction of Apple's bi-directional LSTM models for language identification in short strings2102.06282v1 · Mads Toftrup, S\oren Asger S\orensen, Manuel R. Ciosici et al.2021 · 18 citationsarXiv
Career total: 6 works. 6 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.