Hi Everyone! Is Anybody Using Log-Scale Parameter Ranges For Hyper-Parameter Optimization? It Seems That There Is A Bug In The Hpbandster Module. I'M Getting Negative Learning Rates..

Unanswered

Moreover, the LogUniformParameterRange is not implemented for hpbanster optimizer and results in a range from values [-3, 1] since LogUniformParameterRange inherits from UniformParameterRange. See https://github.com/allegroai/clearml/blob/master/clearml/automation/hpbandster/bandster.py#L355

  				
Posted 
	one year ago

					More
				  		
  Report
		
					GreasyLeopard35
				
					0
					 × 1

84 Views

0 Answers

one year ago