AI Paper Atlas

Research map / Learning theory and algorithms / Kernels and regression theory

Generalization in multitask deep neural classifiers: a statistical physics approach

Anthony Ndirango, Tyler Lee

NeurIPS 2019 · Learning theory and algorithms › Kernels and regression theory · approach: Empirical generalization measures · 12 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Jointly train with a related, clean auxiliary taskMultitask softmax classifier · Main task Ageneralization lossImproved
Jointly train with an unrelated, high-SNR auxiliary taskMultitask softmax classifier · Main task Ageneralization lossHurt
Jointly train with an unrelated, noisy auxiliary taskMultitask softmax classifier · Main task Ageneralization lossNo clear effect
Increase auxiliary-task data while holding main-task data fixedMultitask student network · Main task A with 100 main-task data pointsmultitask benefitMixed
Increase task relatednessMultitask student network · Main task Amultitask benefitImproved
Increase auxiliary-task SNRMultitask student network · Main task Amultitask benefitMixed
Provide abundant labeled training dataMultitask softmax classifier · Main task Amultitask benefitNo clear effect
Use deeper student networks with ReLU nonlinearitiesMultitask student network · Multitask generalizationmultitask benefitHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy