domains / families / research / ijoc-methods

ijoc-methods

separate

Use when the method choice, baselines, and computational-experiment design need alignment for an INFORMS Journal on Computing (IJOC) manuscript — before the experiments are run at scale. Designs a fair, reproducible experimental protocol; it does not write the algorithm proofs (see ijoc-theory-development).

When to use

• Designing experimental protocol
• Selecting baselines
• Defining fair tuning procedures
• Specifying hardware and time limits
• Choosing metrics and statistical tests
• Ensuring reproducibility for IJOC deposit
• Auditing empirical causal designs

When not to use

• Writing algorithm proofs
• Running experiments at scale

Skill page

Source