Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Rogier Van Dalen

Rogier Van Dalen

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

ML×2Crypto×2AI×1Distributed×1

Frequent co-authors

Haaris Mehmood2×
Jie Xu2×
Karthikeyan Saravanan2×
Mete Ozay2×

Research Timeline

2026
Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation

The paper proposes PINA, a two-stage differentially private clustered federated learning framework that improves convergence and robustness by using low-rank adaptation and a normality-driven aggregation mechanism.

DP-LAC: Lightweight Adaptive Clipping for Differentially Private Federated Fine-tuning of Language Models

The paper proposes DP-LAC, a novel lightweight adaptive clipping technique for differentially private federated fine-tuning, which efficiently estimates and adapts the clipping threshold without consuming extra privacy budget or requiring manual hyperparameter tuning.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIcs.CRRecentMay 11, 2026

DP-LAC: Lightweight Adaptive Clipping for Differentially Private Federated Fine-tuning of Language Models

Haaris Mehmood, Jie Xu, Karthikeyan Saravanan, Rogier Van Dalen +1 more

The paper proposes DP-LAC, a novel lightweight adaptive clipping technique for differentially private federated fine-tuning, which efficiently estimates and adapts the clipping threshold without consu…

View →
cs.LGcs.CRRecentApr 22, 2026

Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation

Jie Xu, Haaris Mehmood, Rogier Van Dalen, Karthikeyan Saravanan +1 more

The paper proposes PINA, a two-stage differentially private clustered federated learning framework that improves convergence and robustness by using low-rank adaptation and a normality-driven aggregat…

View →