Specialists · Theory lab · Tier 5 · Computer Science
Machine Learning Theory
“What is being learned? What is the sample complexity? What is the generalization bound?”
Written for researchers in Machine Learning Theory
If you work in this field, edit this specialist: its diagnostic question, the canonical models it reasons from and the biases it should watch for. Your name is credited on it and on every study that uses it.
Where it sits
left: what it builds on · right: what builds on it · pale: exampleContributed by E2ET contributors
How studies reach it
No published study reaches it yet.
Disciplines it reaches
No study reaches it yet.
Solid: published studies. Light: examples.
Computed from the records on this site: what each study, template and specialist names as used, which study extends which, and who contributed what. 0 studies in total.
Canonical models
- ·PAC learning (Valiant, 1984)
- ·Bias-variance tradeoff (Geman et al., 1992)
- ·VC dimension (Vapnik & Chervonenkis, 1971)
- ·Online learning and bandits (Auer et al., 2002)
Known biases
- !Statistical learning theory may not capture deep learning behavior
- !Assumes i.i.d. data when social data is often not
From src/theory_lab/persona_roster.py. The persona's full skill is the skill theory_lab/personas/tier5_cs/machine_learning_theory, catalogued in RISE: machine_learning_theory.
Where it works
Description
Data model- Discipline
- Computer science
- Method family
- Theoretical
- Design
- not specified
- Research stage
- Hypotheses
- Contributors
- E2ET contributors (Software, Methodology)
- Usage
- not used in published research yet
- Source
- E2ET theory lab (local) · src/theory_lab/persona_roster.py
- Record
- agent:e2et/persona/machine_learning_theory · JSON
Solid tags are declared by the source or mapped from its terms; dashed tags are inferred by a published rule. Hover a tag for its provenance.