@davidrohde
Machine Learning for Interactive Systems
Researcher in Machine Learning, Causality and Recommender Systems. On a career break to write a book on Reward Optimizing Recommender Systems. Previously led a team of researchers and engineers at Criteo.
Nothing here yet.
Nov 28, 2025 · 3 min read · A contextual bandit is a game played by seeing a context, selection an action relevant to the context and then observing reward. It is often used as a simple model of a (short term reward) recommender system. The user’s interest is revealed in the co...
Join discussion
Nov 5, 2025 · 3 min read · In 2009 an important debate exploded on the pages of 'Statistics and Medicine’ principally involving Donald Rubin and Judea Pearl, but initially sparked by a letter to the editor (Shrier 2009), which was a response to Rubin’s earlier piece. The main ...
Join discussion
Oct 21, 2025 · 3 min read · What Do We Talk About When We Talk About Causal Inference? I think it’s clear that it’s more than one thing. If an epidemiologist has run a randomized control trial, causal inference is mostly about “being careful” in the implementation of the trial....
Join discussion
Oct 21, 2025 · 5 min read · I really like Ben Recht, he thinks for himself, he is a serious scholar that knows the history of ideas and is well read on a variety of topics including medicine, the foundations of statistics and machine learning as well as philosophy. His blog is ...
Join discussion
Oct 18, 2025 · 2 min read · The “All models are wrong, some models are useful” quote attributed to George Box is a favorite in statistical presentations, but is it true, and what does it really mean? Let me make a probabilistic statement that I don’t think is wrong. If I throw...
Join discussion
