5 papers
RAPTOR: Role-Aware Private Training for Mixture-of-Experts
Duc Dm, Khai Le-Duc, Nguyen Do +18
Differentially private (DP) fine-tuning methods treat sparse Mixture-of-Experts (MoE) models as a single dense block, ignoring that shared layers see all data while experts only se…
Efficient Algorithms for Influence Maximization in General Models and Observed Cascades
Fabian Spaeh, Themistoklis Haris, Alina Ene +1
We study influence maximization in general stochastic models, the observed cascades model, and the independent cascade (IC) model. For general stochastic models with only black-box…
Solving Positive Linear Programs with Differential Privacy
Alina Ene, Huy Le Nguyen, Ta Duy Nguyen +1
We study differentially private approximation algorithms for positive linear programs (LPs with nonnegative coefficients and variables), focusing on the fundamental families of pac…
Testable and Actionable Calibration for Full Swap Regret
Konstantina Bairaktari, Lunjia Hu, Huy L. Nguyen +1
AI generated predictions increasingly inform decision making in critical tasks, and therefore must be trustworthy. One widely used measure of trustworthiness is calibration, which…
Lean and Mean Adaptive Optimization via Subset-Norm and Subspace-Momentum with Convergence Guarantees
Thien Hang Nguyen, Huy Le Nguyen
We introduce two complementary techniques for efficient optimization that reduce memory requirements while accelerating training of large-scale neural networks. The first technique…