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
Augmentations vs Algorithms: What Works in Self-Supervised Learning
Warren Morningstar, Alex Bijamov, Chris Duvarney, Luke Friedman, Neha Kalibhat, Luyang Liu, Philip Mansfield, Renan Rojas-Gomez, Karan Singhal, Bradley Green, Sushant Prakash
Evidence, Definitions and Algorithms regarding the Existence of Cohesive-Convergence Groups in Neural Network Optimization
Thien An L. Nguyen
Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition
Long-Fei Li, Peng Zhao, Zhi-Hua Zhou
Presenting Terrorizer: an algorithm for consolidating company names in patent assignees
Grazia Sveva Ascione, Valerio Sterzi
A challenge in A(G)I, cybernetics revived in the Ouroboros Model as one algorithm for all thinking
Knud Thomsen
Demonstrating a Robust Walking Algorithm for Underactuated Bipedal Robots in Non-flat, Non-stationary Environments
Oluwami Dosunmu-Ogunbi, Aayushi Shrivastava, Jessy W Grizzle
Active Learning of Mealy Machines with Timers
Véronique Bruyère, Bharat Garhewal, Guillermo A. Pérez, Gaëtan Staquet, Frits W. Vaandrager