Combining dependent p-values with an empirical adaptation of Browns' method (presentation, write-up)
Bayes factors: Evaluating evidence for models (presentation, write-up)
NoiseOut: A Simple Way to Prune Neural Networks (presentation, write-up)
Optimal design, Robustness, and Risk Aversion (presentation, write-up)
The L-curve and its use in the numerical treatment of inverse problems - treasure chest (presentation, write-up)
Selecting the Number of States in Hidden Markov Models - Pitfalls, Practical Challenges and Pragmatic Solutions (presentation, write-up)
Power-Law Distributions in Empirical Data (presentation, write-up) There was some interesting discussion about the applicability of some of the results from the paper; notably the lack of underfluctations in \alpha reproduced in slide 11, as well as the criteria that the x_{min} should be placed when the distribution is a power-law seems like a self-fulfilling prophecy. If we set the x_{min} where the distribution exhibits power-law behavior, then it will exhibit power-law behavior. Maybe everything is okay, but it's still good to be critical and ask questions :-)
Sum of Weighted Poisson Events ( presentation, write-up)
Gaussian Process ( presentation, write-up)
Bayesian Blocks ( presentation, write-up)
Ensemble Samplers with Affine Invariance [EMCEE walkers] ( presentation (PDF, powerpoint), write-up)
Frequentism and Bayesianism: A Python-driven Primer ( presentation, write-up)