← Search

Lingyu Wu

2 accepted papers

2025

Continuous Subspace Optimization for Continual Learning

NeurIPS 2025poster

Continual learning aims to learn multiple tasks sequentially while preserving prior knowledge, but faces the challenge of catastrophic forgetting when adapting to new tasks. Recently, approaches leveraging pre-trained models have gained increasing popularity in mitigating this issue, due to the stro…

Cited by 10Source ↗Scholar ↗
2023

Learning Unnormalized Statistical Models via Compositional Optimization

ICML 2023poster

Learning unnormalized statistical models (e.g., energy-based models) is computationally challenging due to the complexity of handling the partition function. To eschew this complexity, noise-contrastive estimation (NCE) has been proposed by formulating the objective as the logistic loss of the real…

Cited by 4Source ↗PDF ↗Scholar ↗