7 papers
When Does -Boosting Overfit Benignly? High-Dimensional Risk Asymptotics and the Implicit Bias
Ye Su, Jian Li, Yong Liu
Benign overfitting is well-characterized in geometries, but its behavior under the implicit bias of greedy ensembles remains challenging. The analytical barrier s…
Sparsity is Combinatorial Depth: Quantifying MoE Expressivity via Tropical Geometry
Ye Su, Huayi Tang, Zixuan Gong +1
While Mixture-of-Experts (MoE) architectures define the state-of-the-art, their theoretical success is often attributed to heuristic efficiency rather than geometric expressivity.…
Geometric Capacity of Transformers: A Tropical Geometry Perspective
Ye Su, Yong Liu
To quantify the geometric capacity of transformers, we develop a tropical-geometric framework for analyzing the spatial partitions induced by conditioned self-attention. In the zer…
Exact Finite-Sample Variance Decomposition of Subagging: A Spectral Filtering Perspective
Ye Su, Mingrui Ye, Yining Wang +2
Standard resampling ratios (e.g., ) are widely used as default baselines in ensemble learning for three decades. However, how these ratios interact with a base lea…
Cell-cell Communication Inference and Analysis: Biological Mechanisms, Computational Approaches, and Future Opportunities
Xiangzheng Cheng, Haili Huang, Ye Su +3
In multicellular organisms, cells coordinate their activities through cell-cell communication (CCC), which is crucial for development, tissue homeostasis, and disease progression.…
Effective Frontiers: A Unification of Neural Scaling Laws
Jiaxuan Zou, Zixuan Gong, Ye Su +2
Neural scaling laws govern the prediction power-law improvement of test loss with respect to model capacity (), datasize (), and compute (). However, existing theoretical…