Weekly summary 2016-10-29

Last week. (See wonderings there.)

Threads

Priority

• Come up with a class of MDPs on exponential space that is interesting and tractable. Thoughts
  • Understand provable guarantees on MDP’s first
• Alexa references (Wed-Fri)

Other

• PMI - get some results!
  • Mon. - train CIFAR.
  • Todos
    • Check MNIST model 1. What are sizes of coefficients?
    • Run experiments on CIFAR.
• SoS - chapters 2–5
• DL experiments DL generalization
• On hold
  • (*) NN learns DL. Can write up weak result, worth doing?
• Papers
  • [HM16] on unsupervised learning (finish)
  • [HMR16] on dynamical system learning

Analyze Arora and Ge’s NMF algorithm in the presence of noise. Exactly how much noise can it tolerate?

Other papers

• TODO Read this paper: [CFP16] Assessing significance in a Markov chain without mixing