How does differentiable NAS (DARTS) differ from RL-based methods?
Machine Learning / AI
What is secure aggregation?
What fallback methods are there in case of no internet and weak device?
When does deep learning outperform GBDT on tabular data?
What is the RBF kernel and its hyperparameters?
What tasks do KG embeddings solve (link prediction, entity typing)?
What is Feast and what are its components (offline/online store)?
What is mediation analysis?
What is Prophet and what are its strengths and weaknesses?
What are the features of training on large satellite tiles (memory, IO)?
What is semantic segmentation of satellite images and which models are used?
What simulators are used (MuJoCo, Isaac Sim, Gazebo)?
What is a clipped objective in PPO?
What is Bayesian optimization for HPO?
What is censoring and what types are there?
What are potential outcomes (potential outcomes) according to Rubin?
What are switchback experiments?
What is Dyna-Q?
What are Gaussian Processes and what kernel functions are used?
What is DiD (difference-in-differences)?