Likelihood-free MCMC with Amortized Approximate Ratio Estimators
About
Posterior inference with an intractable likelihood is becoming an increasingly common task in scientific domains which rely on sophisticated computer simulations. Typically, these forward models do not admit tractable densities forcing practitioners to make use of approximations. This work introduces a novel approach to address the intractability of the likelihood and the marginal model. We achieve this by learning a flexible amortized estimator which approximates the likelihood-to-evidence ratio. We demonstrate that the learned ratio estimator can be embedded in MCMC samplers to approximate likelihood-ratios between consecutive states in the Markov chain, allowing us to draw samples from the intractable posterior. Techniques are presented to improve the numerical stability and to measure the quality of an approximation. The accuracy of our approach is demonstrated on a variety of benchmarks against well-established techniques. Scientific applications in physics show its applicability.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Posterior Estimation | SBIBM SLCP | Joint C2ST95 | 10 | |
| Posterior Estimation | SBIBM Two Moons | Joint C2ST76 | 9 | |
| Posterior Estimation | SBIBM Gaussian Mixture | Joint C2ST75 | 9 | |
| Posterior Estimation | SBIBM SIR | Joint C2ST77 | 9 | |
| Posterior Estimation | SBIBM Lotka–Volterra | Joint C2ST1 | 9 | |
| Posterior Estimation | SBIBM Gaussian Linear | Joint C2ST0.56 | 8 | |
| Posterior Estimation | SBIBM Bernoulli GLM | Joint C2ST81 | 6 | |
| Simulation-Based Inference | SBIBM | Two Moons Performance63 | 6 |