7 papers
Variance Driven Exploration: A Provable and Efficient Methodology for Pure Exploration in Highly Stochastic Environments
Khang Luong, Nam Nguyen, Hoang Ta +2
We propose Variance Driven Exploration (VarDE), a principled approach for pure exploration in highly stochastic environments, where the exploration process is dominated by stochast…
Nearly Optimal Bounds for Computing Decision Tree Splits in Data Streams
Hoang Ta, Hoa T. Vu
We establish nearly optimal upper and lower bounds for approximating decision tree splits in data streams. For regression with labels in the range , we give a one…
Near-Optimal Covering Sequences
Hoang Ta, Van Khu Vu
An -covering sequence over a finite alphabet is a cyclic sequence whose consecutive length- windows form a covering code of radius . Equiva…
A Mixture of Experts Vision Transformer for High-Fidelity Surface Code Decoding
Hoang Viet Nguyen, Manh Hung Nguyen, Hoang Ta +2
Quantum error correction is a key ingredient for large scale quantum computation, protecting logical information from physical noise by encoding it into many physical qubits. Topol…
Constructions of Covering Sequences and Arrays
Yeow Meng Chee, Tuvi Etzion, Hoang Ta +1
An -covering sequence is a cyclic sequence whose consecutive -tuples form a code of length and covering radius . Using several construction methods improvements of…
Optimizing Polynomial Graph Filters: A Novel Adaptive Krylov Subspace Approach
Keke Huang, Wencai Cao, Hoang Ta +2
Graph Neural Networks (GNNs), known as spectral graph filters, find a wide range of applications in web networks. To bypass eigendecomposition, polynomial graph filters are propose…