Interactive Training: Feedback-Driven Neural Network Optimization
This addresses the need for more adaptive training processes in machine learning, though it is incremental as it builds on existing optimization methods with a new interactive approach.
The paper tackles the problem of inflexible neural network training by introducing Interactive Training, a framework for real-time feedback-driven intervention, and demonstrates it achieves superior training stability and reduced hyperparameter sensitivity through case studies.
Traditional neural network training typically follows fixed, predefined optimization recipes, lacking the flexibility to dynamically respond to instabilities or emerging training issues. In this paper, we introduce Interactive Training, an open-source framework that enables real-time, feedback-driven intervention during neural network training by human experts or automated AI agents. At its core, Interactive Training uses a control server to mediate communication between users or agents and the ongoing training process, allowing users to dynamically adjust optimizer hyperparameters, training data, and model checkpoints. Through three case studies, we demonstrate that Interactive Training achieves superior training stability, reduced sensitivity to initial hyperparameters, and improved adaptability to evolving user needs, paving the way toward a future training paradigm where AI agents autonomously monitor training logs, proactively resolve instabilities, and optimize training dynamics.