Distributed GLM

---

Event Information

Event: Atlanta Big Data Science

Date: January 27, 2015

Place: Atlanta, GA @ Polygon

Speakers: Tom Kraljevic

---

Content

• Slides PDF
• Slides PPT

---

Q & A

There will be time for questions at the event.

After the event concludes, please send questions to h2ostream@googlegroups.com.

---

References

Books

• Introduction to Statistical Learning (PDF)
• Elements of Statistical Learning (PDF)

Journal articles

• Zou, H and Hastie, T. (2005) Regularization and variable selection via the elastic net

• Friedman, J., Hastie, T. and Tibshirani, R. (2008) Regularization Paths for Generalized Linear Models via Coordinate Descent

• Stephen Boyd, Neal Parikh, Eric Chu, Borja Peleato and Jonathan Eckstein. (2011) Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers

• Tibshirani, Robert., Bien, J., Friedman, J.,Hastie, T.,Simon, N.,Taylor, J. and Tibshirani, Ryan. (2012) Strong Rules for Discarding Predictors in Lasso-type Problems, JRSSB, vol 74

Software Documentation

• H2O Mirzakhani Release Documentation
• H2O Software Architecture
• H2O GLM Documentation (Contains many references)
• H2O GLM Vignette (Contains many references)

Software Downloads

(H2O latest version at the date of the talk. All demos from this talk will use this version of H2O.)

• H2O Mirzakhani Release
• H2O package for R (Mirzakhani Release)

(H2O older versions)

• H2O package for R (Markov Release in CRAN, which is a release behind on the date of the talk)

(Other)

• glmnet package for R (Contains many references)

Talks

• Nykodym, T. (2013) Distributed GLM Implementation
• Kraljevic, T. (2014) H2O World 2014: H2O in Big Data Environments
• Nykodym, T. and Maj, P. (2014) GOTO Berlin: Fast Analytics on Big Data

Web

• Trevor Hastie's Stanford Page
• Rob Tibshirani's Stanford Page
• Stephen Boyd's Stanford Page and details about ADMM
• Wikipedia GLM