Train a VAE for Synthetic Tabular Data at a Healthtech Startup
Overview
What this challenge is about.
You train a VAE on a clinical-trial table with 50,000 patients, then evaluate utility and privacy to recommend a release setting. You get a verifiable certificate.
The scenario
The healthtech (around 100 staff, FDA Breakthrough designation for one device) has a multi-year academic collaboration on the line and a six-month-blown legal review of the real-data sharing path.
The Brief
What you'll do, and what you'll demonstrate.
Train a VAE-based synthetic data generator that meets utility and privacy thresholds acceptable for academic data-sharing.
Earning criteria — what you'll demonstrate
- Adapt VAE training to mixed-type tabular data
- Evaluate synthetic data utility via downstream-model fidelity
- Implement and interpret a membership-inference attack
- Reason about the privacy/utility trade-off for real data-sharing decisions
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Deep Generative Models
Master · Generative Ai
Strong alignment
This challenge maps to Deep Generative Models at the Master level. It sharpens the same practical skills your coursework expects — but in a real industry context with actual constraints and deliverables.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
- Vae
Apply vae to solve real industry problems and demonstrate production-level capability.
- Tabular Generation
Apply tabular generation to solve real industry problems and demonstrate production-level capability.
- Synthetic Data
Apply synthetic data to solve real industry problems and demonstrate production-level capability.
- Privacy Evaluation
Apply privacy evaluation to solve real industry problems and demonstrate production-level capability.
- Pytorch
Apply pytorch to solve real industry problems and demonstrate production-level capability.
- Utility Evaluation
Apply utility evaluation to solve real industry problems and demonstrate production-level capability.
Careers
Career paths this challenge builds toward
Completing this challenge demonstrates skills that transfer directly to these roles:
Research Scientist
Synthetic-data work with formal utility and privacy evaluation is a strong portfolio piece for any privacy-ML or generative research role.
This challenge sharpens
- vae
- synthetic-data
- privacy-evaluation
ML Researcher
Tabular VAEs and their utility/privacy trade-offs are an active research area; this challenge produces a credible first publication-ready artifact.
This challenge sharpens
- vae
- tabular-generation
- utility-evaluation
AI Safety Researcher
Privacy evaluation and membership-inference attacks are core AI safety research methods.
This challenge sharpens
- privacy-evaluation
- synthetic-data
- vae