The greatest challenge to any thinker is stating the problem in a way that will allow a solution.
Bertrand Russell [England, 1902].
- Welcome
- My name is Carlos Riquelme. This is my personal website.
- About Me
- I currently work at Google Brain.
Previously, I completed my PhD in statistical machine learning at Stanford.
- Interests
- Reinforcement Learning, Machine Learning, Artificial Intelligence.
- Theory
- Algorithms, Probability, Statistics, Optimization.
- Mentors
- My advisor at Stanford was Ramesh Johari. I learnt from him every day.
At Oxford, I did work on Probabilistic Combinatorics supervised by Oliver Riordan.
I really enjoyed long discussions with Dragan Vukotic about Functional Analysis.
Thanks! Thanks! Thanks!
- Experience
- Machine Learning / Data Science @ Facebook, Twitter, PYNK, Quora, Adobe.
- Collaborators
-
Sven Schmit,
Mohammad Ghavamzadeh,
Alessandro Lazaric,
Baosen Zhang,
Sid Banerjee,
Austin Benson,
David Walsh.
If you can dream it, you can do it.
Walt Disney.
please, feel free to contact me at rikel AT google DOT com.
Publications.
- Exploration for Bayesian (Deep) Reinforcement Learning.
Work in progress.
- Deep Bayesian Bandits Showdown.
Work in progress; with George Tucker and Jasper Snoek.
NIPS 2017, Bayesian Deep Learning Workshop.
- The Beta-VAE's Implicit Prior.
Work in progress; with Matthew Hoffman and Matthew Johnson.
NIPS 2017, Bayesian Deep Learning Workshop.
- Active Learning for Accurate Estimation of Linear Models.
Riquelme, Ghavamzadeh, Lazaric | ICML 2017.
https://arxiv.org/abs/1703.00579
- Sequential Learning for Sparse Models in High Dimensions.
Work in progress.
- Experimentation under Non-Stationarity by Multitask Bayesian Optimization.
Work in progress; with Eytan Bakshy and Ben Letham.
- Human Interaction with Recommendation Systems: On Bias and Exploration.
Work in progress; with Sven Schmit.
https://arxiv.org/abs/1703.00535
- Online Active Linear Regression via Thresholding.
Riquelme, Johari, Zhang | AAAI 2017.
http://arxiv.org/abs/1602.02845
- Pricing Ride-Share Platforms: A Queueing-Theoretic Approach.
Banerjee, Johari, Riquelme | EC 2015.
http://papers.ssrn.com/sol3/papers.cfm?abstract_id=2568258
- Learning Multifractal Structure in Large Networks.
Benson, Riquelme, Schmit | KDD 2014.
http://arxiv.org/abs/1402.6787
- On the Chromatic Number of Random Graphs.
Riquelme | Masters Thesis at the University of Oxford, 2012.
What I like most about Madrid is that it always smiles at you, and smiling is contagious.