3 papers
cs.LG2026
OLion: Approaching the Hadamard Ideal by Intersecting Spectral and Implicit Biases
Zixiao Wang, Yifei Shen, Huishuai Zhang
Many optimizers can be interpreted as steepest-descent methods under norm-induced geometries, and thus inherit corresponding implicit biases. We introduce \nameA{} (\fullname{}), w…
cs.CL2025
Synthetic Data RL: Task Definition Is All You Need
Yiduo Guo, Zhen Guo, Chuanwei Huang +5
Reinforcement learning (RL) is a powerful way to adapt foundation models to specialized tasks, but its reliance on large-scale human-labeled data limits broad adoption. We introduc…
cs.LG2025
Understanding Nonlinear Implicit Bias via Region Counts in Input Space
Jingwei Li, Jing Xu, Zifan Wang +2
One explanation for the strong generalization ability of neural networks is implicit bias. Yet, the definition and mechanism of implicit bias in non-linear contexts remains little…