Schrödinger bridge and Trajectory Inference (Part 2)
Event details
| Date | 15.03.2023 |
| Hour | 16:00 › 17:00 |
| Speaker | Chizat Lénaic (EPFL) |
| Location |
Bernoulli Center
|
| Category | Conferences - Seminars |
| Event Language | English |
Abstract:
We consider statistical and computation methods to infer trajectories of a stochastic process from snapshots of its temporal marginals. This problem arises for instance in the analysis of single cell RNA-sequencing data. The goal of these lectures is to present and understand the estimator proposed by [Lavenant et al. 2020] which searches for the diffusion process that fits the observations with minimal entropy relative to a Wiener process. This estimator comes with consistency guarantees—for a suitable class of ground truth processes—and lends itself to computational methods with global optimality guarantees. Its analysis is the occasion to review important tools from entropic optimal transport — aka the Schrödinger bridge problem.
We consider statistical and computation methods to infer trajectories of a stochastic process from snapshots of its temporal marginals. This problem arises for instance in the analysis of single cell RNA-sequencing data. The goal of these lectures is to present and understand the estimator proposed by [Lavenant et al. 2020] which searches for the diffusion process that fits the observations with minimal entropy relative to a Wiener process. This estimator comes with consistency guarantees—for a suitable class of ground truth processes—and lends itself to computational methods with global optimality guarantees. Its analysis is the occasion to review important tools from entropic optimal transport — aka the Schrödinger bridge problem.
Practical information
- General public
- Free
Contact
- Prof. Xue-Mei Li