4 papers
Jump Like A Squirrel: Optimized Execution Step Order for Anytime Random Forest Inference
Daniel Biebert, Christian Hakert, Kay Heider +3
Due to their efficiency and small size, decision trees and random forests are popular machine learning models used for classification on resource-constrained systems. In such syste…
Realizing Hardware-Optimized General Tree-Based Data Structures for Heterogeneous System Classes
Daniel Biebert, Christian Hakert, Jian-Jia Chen
Tree-based data structures are ubiquitous across applications. Therefore, a multitude of different tree implementations exist. However, while these implementations are diverse, the…
TREE: Tree Regularization for Efficient Execution
Lena Schmid, Daniel Biebert, Christian Hakert +4
The rise of machine learning methods on heavily resource constrained devices requires not only the choice of a suitable model architecture for the target platform, but also the opt…
Register Your Forests: Decision Tree Ensemble Optimization by Explicit CPU Register Allocation
Daniel Biebert, Christian Hakert, Kuan-Hsun Chen +1
Bringing high-level machine learning models to efficient and well-suited machine implementations often invokes a bunch of tools, e.g.~code generators, compilers, and optimizers. Al…