Unlock: Langevin Dynamics
The overdamped Langevin SDE: gradient descent plus calibrated Gaussian noise. The mathematical object behind SGLD, ULA, and energy-based MCMC samplers, and the simplest sampler with provable polynomial-time convergence on log-concave targets.
232 Prerequisites0 Mastered0 Working182 Gaps
Prerequisite mastery22%
Recommended probe
Natural Language Processing Foundations is your weakest prerequisite with available questions. You haven't been assessed on this topic yet.
Langevin DynamicsTARGET
Not assessed5 questions
Not assessed5 questions
Score MatchingAdvanced
Not assessed6 questions
Fokker–Planck EquationAdvanced
Not assessed1 question
Hamiltonian Monte CarloAdvanced
Not assessed5 questions
No quiz
Not assessed2 questions
Not assessed5 questions
Stochastic Calculus for MLAdvanced
Not assessed5 questions
Sign in to track your mastery and see personalized gap analysis.