3 papers
cs.LG2026
KV Cache Compression Through the Lens of Transform Coding
Hannah Laus, Claudio Mayrink Verdun, Hao Wang +2
The key-value (KV) cache stores information from past tokens and is a major memory bottleneck in long-context inference. Existing quantization methods address this bottleneck by re…
cs.LG2024
Non-Asymptotic Uncertainty Quantification in High-Dimensional Learning
Frederik Hoppe, Claudio Mayrink Verdun, Hannah Laus +2
Uncertainty quantification (UQ) is a crucial but challenging task in many high-dimensional regression or learning problems to increase the confidence of a given predictor. We devel…
stat.ML2023
Uncertainty quantification for learned ISTA
Frederik Hoppe, Claudio Mayrink Verdun, Felix Krahmer +2
Model-based deep learning solutions to inverse problems have attracted increasing attention in recent years as they bridge state-of-the-art numerical performance with interpretabil…