Bayesian Inference
Multi-task Learning of Order-Consistent Causal Graphs
Lastly, our analysis also shows the consistency of union support recovery of the structures.
ESH_Dynamics-20
In contrast to MCMC approaches like Hamiltonian Monte Carlo, no stochastic step is required. Instead, the proposed deterministic dynamics in an extended state space exactly sample the target distribution, specified by an energy function, under an assumption of ergodicity. Alternatively, the dynamics can be interpreted as a normalizing flow that samples a specified energy model without training.
Deterministic Langevin Monte Carlo with Normalizing Flows for Bayesian Inference
We take advantage of NF preconditioning and NF based Metropolis-Hastings updates for a faster convergence.
Bivariate Causal Discovery for Categorical Data via Classification with Optimal Label Permutation
By design, COLP is a parsimonious classifier, which gives rise to a provably identifiable causal model.
Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees
Inverse reinforcement learning (IRL) aims to recover the reward function and the associated optimal policy that best fits observed sequences of states and actions implemented by an expert.
Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees
Inverse reinforcement learning (IRL) aims to recover the reward function and the associated optimal policy that best fits observed sequences of states and actions implemented by an expert.