Skip to yearly menu bar Skip to main content

Workshop: Adaptive Experimental Design and Active Learning in the Real World

Ever Evolving Evaluator (EV3): Towards Flexible and Reliable Meta-Optimization for Knowledge Distillation

Li Ding · Masrour Zoghi · Guy Tennenholtz · Maryam Karimzadehgan


We introduce EV3, a novel meta-optimization framework designed to efficiently train scalable machine learning models through an intuitive explore-assess-adapt protocol. In each iteration of EV3, we explore various model parameter updates, assess them using pertinent evaluation methods, and adapt the model based on the optimal updates and previous progress history. EV3 offers substantial flexibility without imposing stringent constraints like differentiability on the key objectives relevant to the tasks of interest. Moreover, this protocol welcomes updates with biased gradients and allows for the use of a diversity of losses and optimizers. Additionally, in scenarios with multiple objectives, it can be used to dynamically prioritize tasks. With inspiration drawn from evolutionary algorithms, meta-learning, and neural architecture search, we investigate an application of EV3 to knowledge distillation. Our experimental results illustrate EV3's capability to safely explore model spaces, while hinting at its potential applicability across numerous domains due to its inherent flexibility and adaptability.

Chat is not available.