3 papers
cs.LG2025
A Proximal Operator for Inducing 2:4-Sparsity
Jonas M Kübler, Yu-Xiang Wang, Shoham Sabach +5
Recent hardware advancements in AI Accelerators and GPUs allow to efficiently compute sparse matrix multiplications, especially when 2 out of 4 consecutive weights are set to zero.…
cs.LG2024
Uncertainty separation via ensemble quantile regression
Navid Ansari, Hans-Peter Seidel, Vahid Babaei
This paper introduces a novel and scalable framework for uncertainty estimation and separation with applications in data driven modeling in science and engineering tasks where reli…
cs.LG2024
Large-Batch, Iteration-Efficient Neural Bayesian Design Optimization
Navid Ansari, Alireza Javanmardi, Eyke Hüllermeier +2
Bayesian optimization (BO) provides a powerful framework for optimizing black-box, expensive-to-evaluate functions. It is therefore an attractive tool for engineering design proble…