Author

Ke Lu

h-index 32 View on Semantic Scholar

We have 2 of 90 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Oct 2026

Adaptive parameter manifold learning for low-dimensional neural network optimization.

Deep neural networks have achieved remarkable success across diverse domains, yet their massive over-parameterization introduces significant optimization challenges, particularly susceptibility to overfitting and noise memorization. While traditional stochastic gradient descent treats all parameters equally in the nati...

Zhe-Kai Du, Wei Ao, Jie-Yan Liu et al. · Neural Networks · 0 citations

Aug 2026

Triplet Decomposition and Extensions: A General Framework for Parameter-Efficient Fine-Tuning.

This work unify these approaches under a Triplet Matrix Decomposition framework and reveals that frequency-domain methods can surpass low-rank approaches when optimal frequency components are selected, and this advantage stems from orthogonal transformation matrices and flexible basis vector combinations.

Zhekai Du, Yinjie Min, Dan Zhang et al. · IEEE Transactions on Pattern... · 0 citations