Unfair comparison, your method has 100x higher lr

[grypesc]

if args.loss == 'Proxy_Anchor':
param_groups.append({'params': criterion.parameters(), 'lr':float(args.lr) * 100})
elif args.loss == 'Proxy_NCA':
param_groups.append({'params': criterion.parameters(), 'lr':float(args.lr)})

Why do you multiply yours lr by 100, but not the other method? In the teaser you claim your method trains faster, but it seems it is due to 100x higher lr.