Timeline for Test accuracy go down after decreasing learning rate

Current License: CC BY-SA 4.0

6 events

when toggle format	what		by	license	comment
Jan 25, 2022 at 16:07	comment	added	Edoardo Guerriero		well if your train, test and validation sets are different that's the very first thing to address. They are suppose to be representative of the same distribution, if not the test results are useless and not even to be interpret at all (otherwise it's like comparing apples and bananas and wondering why they don't look the same).
Jan 25, 2022 at 14:44	comment	added	BestR		You are right, in the grey graph the validation is basically flat because lr is low. if i dont change it varies again. But also in low lr, it improves a tiny bit. You think about early stopping? And the differences between the sets is becuase they are from different distributions.
Jan 25, 2022 at 14:14	comment	added	Edoardo Guerriero		Your still optimizing on your validation set, so that doesn't prove it's not over fitting. And as you can see by decreasing learning rate every 40 epochs you keep fine tuning on the same batches again and again, improving slightly (cause after a while the weights basically stop changing) without any benefit on the test set, which remain slightly the same (if you smooth the scores with moving average it's most likely flat, not decreasing). Plus you have a 10 to 20% difference between the 2 sets scores, which is another strong indicator for over fitting.
Jan 25, 2022 at 13:42	comment	added	BestR		As you can see these are validation and test graph not training graphs. Validation keep increases. Also, the grey in the test set is also increasing. Only the green (with mixup) is decreasing. The question is how to solve it
Jan 25, 2022 at 12:09	comment	added	Edoardo Guerriero		what dataset are you using/how large is it? Could be simply over fitting from these graphs.
Jan 25, 2022 at 12:00	history	asked	BestR	CC BY-SA 4.0