NBER paper argues deep learning is a projection method, merging them yields better solvers

SchoeneggerPhil · x · 2026-10-04

Kenneth L. Judd and Karl Schmedders published an NBER paper arguing that deep learning methods are essentially projection methods in the numerical-solution family.

• They place neural-network methods within the broader projection-method framework to analyze when NNs may or may not beat traditional approaches
• The paper argues merging key features of deep learning and classical projection methods will produce better solution methods
• The retweeter says the framing perspective was especially insightful even outside their usual area

Original post →

More from Research

• Paper Finds Personal Agents Get Worse as Memory Notes Pile Up — rohanpaul_ai · 2026-10-05
• Micro entities and individual inventors are far likelier to use AI in patent applications, new paper finds — robseamans · 2026-10-05
• Elephant rumble choruses encode social context through acoustic convergence, study finds — abenitezburraco · 2026-10-05
• Swarm added just +0.05: splitting context into blocks did the real work for tiny local models — deadatreides1 · 2026-10-05
• Sinclair's Harvard lab publicly demos resetting colon cancer cells via 3 reprogramming genes — tomchapin · 2026-10-04
• Diverse Approach Sampling Beats IID Self-Training on Hard Problems — PMinervini · 2026-10-04

Research channel →