Tin Sum Cheng

activity

20232026

most citedA Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regression

1 citations · 1 across the 7 of their papers we have counts for

collaborators

Showing 2025 · stat.MLShow all

2 papers · 2 filters

stat.ML2025

When is Fine-Tuning Scalable? Certified Recovery from Noisy Data and Linear-Cost Fine-Tuning on Structured Task Shifts

Anastasis Kratsios, Tin Sum Cheng, Daniel Roy +1

Transformers often transfer across related tasks with little fine-tuning; we study this question in noisy nonparametric regression for continuous maps $f, g : [0, 1]^{d} \to R^{D}$ ,…

stat.ML2025

Sharp Generalization Bounds for Foundation Models with Asymmetric Randomized Low-Rank Adapters

Anastasis Kratsios, Tin Sum Cheng, Aurelien Lucchi +1

Low-Rank Adaptation (LoRA) has emerged as a widely adopted parameter-efficient fine-tuning (PEFT) technique for foundation models. Recent work has highlighted an inherent asymmetry…