Skip to main content
10 questions · 120s each

Run a focused checkpoint.

Answer what you know, skip what you do not, and let the run turn weak signals into a short review path.

Scope

Run at a glance

10 question run

Starts with lower-friction anchors, then checks the concentration-to-learning-theory bridge.

120 seconds per question
Optional self-check before start
Misses become review targets
Projects explain ready versus blocked

Focused checkpoint

Ready for the checkpoint run?

Answer what you know and skip what you do not. Misses adjust the remaining order, and the result becomes a short review path for this checkpoint.

10 question checkpoint

Optimization foundations

A curated 10-question diagnostic spine for gradients, convexity, SGD, batch-size noise, step-size failure, Hessian checks, Newton updates, and Adam.

Learner can explain descent direction, convexity, mini-batch SGD, batch-size variance, step-size caveats, Hessian convexity, Newton updates, Robbins-Monro schedules, and Adam errors.

How this run adapts

1Answer or skipSkipping is better than guessing.
2Order adjustsMisses pull related checks forward.
3Review followsThe result becomes the next study block.

Review focus

  • gradient direction
  • convexity assumptions
  • stochastic-gradient noise
  • optimizer update mechanics

Could unlock

  • Optimizer Debug Checklist
  • Learning Rate Failure Diagnoser
Watch demo loop
Optional self-check

Leave blank if you want the neutral ramp. Pick only the areas where you have a strong signal.

Linear algebra & calculus

Vectors, matrices, derivatives, notation.

Probability & statistics

Distributions, estimators, likelihood, concentration.

Optimization

Gradients, convexity, SGD, Adam, proximal ideas.

Learning theory

ERM, VC, PAC, Rademacher, generalization.

Modern ML / RL

Deep nets, attention, transformers, value functions.

Proof and transfer

Moving ideas across topics and checking assumptions.

This focused run uses the gold questions attached to the checkpoint. Sign in to attach it to your profile.

Browser-only run

This diagnostic will save for this browser, but it will not create account-level learning events. Sign in first if you want the run to count toward your profile.