Noun
graduate student descent (uncountable)
- (machine learning, humorous) The process of choosing hyperparameters manually and in an ad-hoc manner, typical of work assigned to a graduate student.
[2011 April 6, Kat Scott, Twitter, archived from the original on 2022-07-04:Phrase of the day, "Graduate Student Descent." Optimization through graduate student tweaking.]
2019, Chip Huyen, “Design a machine learning system”, in Chip Huyen [personal website], retrieved 2021-09-27:[…] people without real-world experience often ignore systematic approaches to hyperparameter tuning in favor of manual, gut-feeling approach. The most popular method is arguably 'Graduate Student Descent (GSD) […]
2019 April 17, Oguzhan Gencoglu with Mark van Gils, Esin Guldogan, Chamin Morikawa, Mehmet Süzen, Mathias Gruber, Jussi Leinonen, and Heikki Huttunen, “HARK Side of Deep Learning - From Grad Student Descent to Automated Machine Learning”, in arXiv, page 2:Instead of hypothesis-forming based on theory, extensive research on previous studies and/or reflection against the existing domain knowledge, grad student descent […] is applied.
References
Nicolas Pinto (2011 December 16) “High-Performance Computing Needs Machine Learning... And Vice Versa”, in SlideShare: “"This is graduate student descent" - David McAllester”
Tim Vieira (2015 April 29) Twitter, retrieved 2021-09-27: “@bmorphism @ryan_p_adams I got "Graduate Descent" from David McAllester in 2011.”