Superposition of many models into one
This addresses the problem of efficient model storage and training for AI practitioners, offering a novel approach to utilize network capacity during training.
The paper tackles the problem of storing multiple models within a single set of parameters, showing that a surprisingly large number of models can coexist in superposition and be retrieved individually, with each model undergoing thousands of training steps without significant interference.
We present a method for storing multiple models within a single set of parameters. Models can coexist in superposition and still be retrieved individually. In experiments with neural networks, we show that a surprisingly large number of models can be effectively stored within a single parameter instance. Furthermore, each of these models can undergo thousands of training steps without significantly interfering with other models within the superposition. This approach may be viewed as the online complement of compression: rather than reducing the size of a network after training, we make use of the unrealized capacity of a network during training.