Tin Sum Cheng

According to our database, Tin Sum Cheng authored at least 6 papers between 2023 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

Beyond Universal Approximation Theorems: Algorithmic Uniform Approximation by Neural Networks Trained with Noisy Data.

Anastasis Kratsios, Tin Sum Cheng, Daniel Roy

CoRR, September, 2025

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

Anastasis Kratsios, Tin Sum Cheng, Aurélien Lucchi, Haitz Sáez de Ocáriz Borde

CoRR, June, 2025

Unpacking Softmax: How Temperature Drives Representation Collapse, Compression, and Generalization.

Wojciech Masarczyk, Mateusz Ostaszewski, Tin Sum Cheng, Tomasz Trzcinski, Aurélien Lucchi, Razvan Pascanu

CoRR, June, 2025

2024

A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression.

Tin Sum Cheng, Aurélien Lucchi, Anastasis Kratsios, David Belius

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Characterizing Overfitting in Kernel Ridgeless Regression Through the Eigenspectrum.

Tin Sum Cheng, Aurélien Lucchi, Anastasis Kratsios, David Belius

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

A Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regression.

Tin Sum Cheng, Aurélien Lucchi, Anastasis Kratsios, Ivan Dokmanic, David Belius

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023