How do ML practitioners select hyperparameters, architectures, etc for self-supervised representation learning when the loss is non-monotonic? [D]
비모니토닉 손실에서 자기지도 표현 학습을 위한 하이퍼파라미터 선택 방법에 관한 논의.
Discussion on selecting hyperparameters for self-supervised learning with non-monotonic loss.