I read this paper obout simCLR and I didn't understand a few things:
- What is the goal of the temperature parameter τ? How does it affect the loss?
- What will be the value of the loss for a batch with 2N identical samples? Is there a mathematical formulation?
- In that case (question 2), will different temperature values change the loss?
- How does the batch size affect the contrastive loss? Is large batch size better than small batch size when training a model with contrastive loss?
Thanks!