All your loss are belong to Bayes

Quantile Propagation for Wasserstein-Approximate Gaussian Processes

Variational Inference for Sparse Gaussian Process Modulated Hawkes Process

Efficient non-parametric Bayesian Hawkes processes

Monge blunts Bayes: Hardness results for adversarial training

SynthNet: Learning to Synthesize Music End-to-End.

Fast Bayesian Intensity Estimation for the Permanental Process

Neural Dynamic Programming for Musical Self Similarity

Self-Bounded Prediction Suffix Tree via Approximate String Matching

Computer Assisted Composition with Recurrent Neural Networks

In the audio playlist linked below, we take a piece by Mozart from and **1)** Fix the melody line (the first track). **2)** Fix the rhythmic (or timing) information of the remaining three tracks to that of the original midi file (last track). **3)** Select the pitches of the remaining tracks conditional on the above (second and third tracks); one example uses conditional sampling with our **particle filter**, the other using conditional probability maximisation with a **beam search**, giving two different styles.