Learning Graphical Models
Laplace Redux - Effortless Bayesian Deep Learning
Despite their successes, modern neural networks (NNs) still suffer from several shortcomings that limit their applicability in some settings.
Uncertainty Quantification and Deep Ensembles
Although the calibration of probabilistic models is well studied, calibrating extremely over-parametrized models in the low-data regime presents unique challenges.
Masked Prediction: A Parameter Identifiability View
The vast majority of work in self-supervised learning have focused on assessing recovered features by a chosen set of downstream tasks.
Masked Prediction: A Parameter Identifiability View
The vast majority of work in self-supervised learning have focused on assessing recovered features by a chosen set of downstream tasks.
Reinforcement Learning in Factored MDPs: Oracle-Efficient Algorithms and Tighter Regret Bounds for the Non-Episodic Setting
We study reinforcement learning in non-episodic factored Markov decision processes (FMDPs).
Optimality of variational inference for stochastic block model with missing links
V ariational methods are extremely popular in the analysis of network data.
Bounds all around: training energy-based models with bidirectional bounds
Recent work has established links to generative adversarial networks, where the EBM is trained through a minimax game with a variational value function.