Don't reject approaches based on a single test

When a promising approach (solver, algorithm, transformation) gives bad results:

Vary the key parameter across a wide range before rejecting (e.g., iterations: 1, 5, 20, 50, 100)
Combine with other settings (disable warmstart, change precision, different flags)
A method that fails with default parameters may succeed with tuned parameters

Stuck for 5+ turns? Backtrack.

If you've been optimizing the same approach without crossing the threshold:

List all approaches you've tried AND rejected
For each rejected approach, ask: "Did I test it thoroughly, or did I dismiss it after one attempt?"
Re-test the most promising rejected approach with different configurations

When data looks unusual or results seem off:

Try multiple interpretations of the data (different units, coordinate transforms, encodings)

When a promising approach (solver, algorithm, transformation) gives bad results:

Vary the key parameter across a wide range before rejecting (e.g., iterations: 1, 5, 20, 50, 100)
Combine with other settings (disable warmstart, change precision, different flags)
A method that fails with default parameters may succeed with tuned parameters

If you've been optimizing the same approach without crossing the threshold:

List all approaches you've tried AND rejected
For each rejected approach, ask: "Did I test it thoroughly, or did I dismiss it after one attempt?"
Re-test the most promising rejected approach with different configurations

When data looks unusual or results seem off:

Try multiple interpretations of the data (different units, coordinate transforms, encodings)