4 papers
Geometry-Aware Bayesian Parameter-Efficient Fine-Tuning on the Stiefel Manifold via Stein Variational Gradient Descent
Quang-Duy Tran, Trung Le, Bao Duong +2
Several geometry-aware approaches to low-rank adaptation have emerged for parameter-efficient fine-tuning of large pre-trained models. These methods aim to take full advantage of t…
Identifying Causal Direction via Variational Bayesian Compression
Quang-Duy Tran, Bao Duong, Phuoc Nguyen +1
Telling apart the cause and effect between two random variables with purely observational data is a challenging problem that finds applications in various scientific disciplines. A…
Robust Estimation of Causal Heteroscedastic Noise Models
Quang-Duy Tran, Bao Duong, Phuoc Nguyen +1
Distinguishing the cause and effect from bivariate observational data is the foundational problem that finds applications in many scientific disciplines. One solution to this probl…
Differentiable Bayesian Structure Learning with Acyclicity Assurance
Quang-Duy Tran, Phuoc Nguyen, Bao Duong +1
Score-based approaches in the structure learning task are thriving because of their scalability. Continuous relaxation has been the key reason for this advancement. Despite achievi…