Weekly summary 2017-07-22

Current projects

• Langevin (Mon)
• EGNN
• NLP: (Mon)
  • BoNGs: make recovery work for \(n\)-grams, \(n\ge 2\).
  • Treegrams
    • cf. Sida Wang
    • hyperdim vectors
  • document embedding (axioms?)
  • GANs for BoNGs
• Long-term memory (COLT open problem) (Tue)
  • For convex optimization
  • Tue: this seems difficult because of “bottleneck” of probability \(\ll \rc{\poly(n)}\). Next step: familiarize with lower-bound techniques and try to prove lower bound.
• Reinforcement learning (experiments - what to do?)

Reading

• Do GANs learn?
• Representation learning
• BONGs
• Hyperparameter tuning

Explorations

• Further on temperature varying and Langevin
  • AIS/RAISE estimator - similar criterion?
    • See [BGS14] Accurate and Conservative Estimates of MRF Log-likelihood using Reverse Annealing
    • “Multiplicative” weights
  • Other settings where annealing helps. Analogue on Boolean cube.
  • Tensor decomposition.
    • Beyond the homotopy method.
    • [MR16]
• Co-training - predict one part from other. Relating to/extending CCA.
• RL - kernel?