Learning Graphical Models
On Dynamic Programming Decompositions of Static Risk Measures in Markov Decision Processes
Risk-averse reinforcement learning (RL) seeks to provide a risk-averse policy for high-stakes real-world decision problems. These high-stake domains include autonomous driving (Jin et al., 2019; Sharma et al., 2020), robot collision avoidance (Ahmadi et al., 2021; Hakobyan and Y ang, 2021),
Trust Y our: Gradient-based Intervention Targeting for Causal Discovery
Often, observational data alone is not enough to uniquely identify a system's causal structure.
9dc5accb1e4f4a9798eae145f2e4869b-Supplemental-Conference.pdf
Both challenges involve modeling long-term dependencies.
Kernel Stein Discrepancy thinning: a theoretical perspective of pathologies and a practical fix with regularization Clément Bénard 1 Brian Staber 1 Sébastien Da Veiga 2 1
Stein thinning is a promising algorithm proposed by Riabiz et al. [2022] for post-processing outputs of Markov chain Monte Carlo (MCMC). The main principle is to greedily minimize the kernelized Stein discrepancy (KSD), which only requires the gradient of the log-target distribution, and is thus well-suited for Bayesian inference.
Nonparametric Identifiability of Causal Representations from Unknown Interventions Julius von Kügelgen
We study causal representation learning, the task of inferring latent causal variables and their causal relations from high-dimensional functions ("mixtures") of the variables.
Credal Marginal MAP
Marginal MAP is a widely applicable mixed inference task that identifies the most likely assignment for a subset of variables (called MAP variables).