Bayesian Learning
Characteristic Circuits
In many real-world scenarios, it is crucial to be able to reliably and efficiently reason under uncertainty while capturing complex relationships in data.
Probabilistic Inference in Reinforcement Learning Done Right Jean T arbouriech Google DeepMind
A popular perspective in Reinforcement learning (RL) casts the problem as probabilistic inference on a graphical model of the Markov decision process (MDP). The core object of study is the probability of each state-action pair being visited under the optimal policy.
Mitigating Source Bias for Fairer Weak Supervision
Theoretically, we show that it is possible for our approach to simultaneously improve both accuracy and fairness--in contrast to standard fairness approaches that suffer from tradeoffs. Empirically, we show that our technique improves accuracy on weak supervision baselines by as much as 32% while reducing demographic parity gap by 82.5%.
Uncovering Meanings of Embeddings via Partial Orthogonality
Machine learning tools often rely on embedding text as vectors of real numbers. In this paper, we study how the semantic structure of language is encoded in the algebraic structure of such embeddings.
Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network Anonymous Author(s) Affiliation Address email
We show that our "Joint Structure and
Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network Tristan Deleu
In addition to being a challenging problem due to the super-exponentially large search space, learning a single DAG structure from data may also lead to confident but incorrect predictions (Madigan et al.,
Variational Gaussian Processes For Linear Inverse Problems
By now Bayesian methods are routinely used in practice for solving inverse problems.