Learning Graphical Models
PAC-Bayes under potentially heavy tails
WederivePAC-Bayesian learning guarantees forheavy-tailed losses, andobtain a novel optimal Gibbs posterior which enjoys finite-sample excess risk bounds atlogarithmic confidence. Ourcoretechnique itselfmakesuseofPAC-Bayesian inequalities in order to derive a robust risk estimator, which by design is easy to compute.
Posterior Sampling for Competitive RL: Function Approximation and Partial Observation
This paper investigates posterior sampling algorithms for competitive reinforcement learning (RL) in the context of general function approximations.
Implicit Generation and Modeling with Energy Based Models
Neural Information Processing Systems http://nips.cc/
Learning Discrete Concepts in Latent Hierarchical Models
Learning concepts from natural high-dimensional data (e.g., images) holds potential
Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstruction Manuel Brenner
Dynamical systems (DS) theory is fundamental for many areas of science and engineering. It can provide deep insights into the behavior of systems evolving in time, as typically described by differential or recursive equations.