Bin Yu
6 papers in the PaperMetrix corpus
Papers by this author
-
Fractal Ledger
2023
Scalability is often considered the "Achilles' heel" of blockchain technology. With a traditional chain-based structure, blocks cannot be generated concurrently, thus limiting the throughput and slowing transaction confirmation. Recently emerged graph-based blockchains generally excel in …
-
On the Computational Efficiency of Bayesian Additive Regression Trees: An Asymptotic Analysis
2024 · arXiv (Cornell University)
Bayesian Additive Regression Trees (BART) is a popular Bayesian non-parametric regression model that is commonly used in causal inference and beyond. Its strong predictive performance is supported by well-developed estimation theory, comprising guarantees that its …
-
VMCFDGS: Variable Multicenter Aggregation Clustering Method Based on Fuzzy Dominating (Dominated)-Granularity Structure
2024 · IEEE Transactions on Fuzzy Systems
With the continuous surge in data, the order information increases while the distinguishability of the data diminishes. To address the decreased efficiency and stability of traditional clustering methods owing to intercluster overlap and noise, this …
-
A “Ruler” to Measure the Elemental Concentration Level of Au and Its Application in the Zhongchuan Area of Western Qinling, China
2025 · Applied Sciences
The traditional methods for classifying elemental concentrations such as the cumulative frequency method, the logarithmic interval method, and the mean–standard deviation method all have the limitation of depending on a specific dataset. An objective “ruler” …
-
Predictability–Computability–Stability workflow for veridical data science in the age of artificial intelligence
2026 · Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences
Data science is a pillar of artificial intelligence (AI), which is transforming nearly every domain of human activity, from the social and physical sciences to engineering and medicine. While data-driven findings in AI offer unprecedented …
-
Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs
2018 · arXiv (Cornell University)
The driving force behind the recent success of LSTMs has been their ability to learn complex and non-linear relationships. Consequently, our inability to describe these relationships has led to LSTMs being characterized as black boxes. …