Pruning Techniques Revisited
Jonathan questions the validity of pruning techniques in machine learning, highlighting cherry-picking of results and lack of scientific rigor in the field. Kanjun agrees, emphasizing the need for more openness to imperfections in research papers.In this clip
From this podcast
Generally Intelligent
Episode 13: Jonathan Frankle, MIT, on the lottery ticket hypothesis and the science of deep learning
Related Questions
What is the main topic of the clip Neural Network Pruning from the episode The Lottery Ticket Hypothesis with Jonathan Frankle?
How rigorous is scientific publishing as discussed in the episode #040 - Adversarial Examples (Dr. Nicholas Carlini, Dr. Wieland Brendel, Florian Tramèr) and the clip Incentives for Rigorous Analysis?
How rigorous is scientific publishing?