Practical Algorithm
Practical algorithm research focuses on developing and improving algorithms for diverse applications, prioritizing efficiency, accuracy, and interpretability. Current research emphasizes areas like efficient model training and inference (e.g., low-bit quantization for LLMs, distributed algorithms for large datasets), robust optimization techniques (e.g., evolutionary algorithms, Q-learning variants), and methods for handling noisy data or dynamic environments. These advancements have significant implications across various fields, including machine learning, robotics, and data analysis, by enabling more efficient and reliable solutions to complex problems.
Papers
Message Propagation Through Time: An Algorithm for Sequence Dependency Retention in Time Series Modeling
Shaoming Xu, Ankush Khandelwal, Arvind Renganathan, Vipin Kumar
Nondestructive chicken egg fertility detection using CNN-transfer learning algorithms
Shoffan Saifullah, Rafal Drezewski, Anton Yudhana, Andri Pranolo, Wilis Kaswijanti, Andiko Putro Suryotomo, Seno Aji Putra, Alin Khaliduzzaman, Anton Satria Prabuwono, Nathalie Japkowicz
Provable advantages of kernel-based quantum learners and quantum preprocessing based on Grover's algorithm
Till Muser, Elias Zapusek, Vasilis Belis, Florentin Reiter
Mixed variable structural optimization using mixed variable system Monte Carlo tree search formulation
Fu-Yao Ko, Katsuyuki Suzuki, Kazuo Yonekura