Zijian Zhang
4 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper develops improved Gaussian mechanisms for Rényi Pufferfish Privacy (RPP) by incorporating Gaussian and Gaussian-mixture priors, significantly reducing the required noise and improving the privacy-utility trade-off.
This paper introduces an active traffic analysis method (NATA) and a deep learning framework (BM-Net) to demonstrate that bandwidth perturbations can be used by an adversary to correlate and de-anonymize Tor traffic flows.
The paper introduces the $\alpha$-Wasserstein mechanism to achieve Rényi Pufferfish Privacy using Laplace and Gaussian noise, demonstrating that it generalizes existing privacy frameworks and reduces noise power.
This paper studies the distribution of reinforcement learning (RL) adaptation across transformer layers in large language models and finds that training a single layer can recover most of the gains obtained during full RL training.
Papers
Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training
Zijian Zhang, Rizhen Hu, Athanasios Glentis, Dawei Li +3 more
This paper studies the distribution of reinforcement learning (RL) adaptation across transformer layers in large language models and finds that training a single layer can recover most of the gains ob…