Fig. 4: The categorization criterion of delta-tuning.
From: Parameter-efficient fine-tuning of large-scale pre-trained language models

Here Θ denotes the pre-trained parameters and Θ′ represents the well-tuned parameters.
From: Parameter-efficient fine-tuning of large-scale pre-trained language models

Here Θ denotes the pre-trained parameters and Θ′ represents the well-tuned parameters.