Search Results for author:
Found 14 papers, 4 papers with code
From Temporal to Contemporaneous Iterative Causal Discovery in the Presence of Latent Confounders
We present a constraint-based algorithm for learning causal structures from observational time-series data, in the presence of latent confounders.
Wall Street Tree Search: Risk-Aware Planning for Offline Reinforcement Learning
However, this promise also bears the drawback of this setting as the restricted dataset induces uncertainty because the agent can encounter unfamiliar sequences of states and actions that the training data did not cover.
Learning Control by Iterative Inversion
The key challenge is a $\textit{distribution shift}$ between the desired outputs and the outputs of an initial random guess, and we prove that iterative inversion can steer the learning correctly, under rather strict conditions on the function.
CLEAR: Causal Explanations from Attention in Neural Recommenders
We present CLEAR, a method for learning session-specific causal graphs, in the possible presence of latent confounders, from attention in pre-trained attention-based recommenders.
Iterative Causal Discovery in the Possible Presence of Latent Confounders and Selection Bias
Essentially, we tie the size of the CI conditioning set to its distance on the graph from the tested nodes, and increase this value in the successive iteration.
Validate on Sim, Detect on Real -- Model Selection for Domain Randomization
We show that our score - VSDR - can significantly improve the accuracy of policy ranking without requiring additional real world data.
Improving Efficiency and Accuracy of Causal Discovery Using a Hierarchical Wrapper
In this paper, we introduce such a strategy in the form of a recursive wrapper for existing constraint-based causal discovery algorithms, which preserves soundness and completeness.
Efficient Self-Supervised Data Collection for Offline Robot Learning
In this work, we propose that data collection policies should actively explore the environment to collect diverse data.
A Single Iterative Step for Anytime Causal Discovery
We present a sound and complete algorithm for recovering causal graphs from observed, non-interventional data, in the possible presence of latent confounders and selection bias.
Neural Network Distiller: A Python Package For DNN Compression Research
This paper presents the philosophy, design and feature-set of Neural Network Distiller, an open-source Python package for DNN compression research.
Modeling Uncertainty by Learning a Hierarchy of Deep Neural Connections
This approach leads to a new deep architecture, where networks are sampled from the posterior of local causal structures, and coupled into a compact hierarchy.
Bayesian Structure Learning by Recursive Bootstrap
The proposed method deals with the main weakness of constraint-based learning---sensitivity to errors in the independence tests---by a novel way of combining bootstrap with constraint-based learning.
Constructing Deep Neural Networks by Bayesian Network Structure Learning
We prove that conditional-dependency relations among the latent variables in the generative graph are preserved in the class-conditional discriminative graph.
Unsupervised Deep Structure Learning by Recursive Dependency Analysis
Finally, a deep neural network structure is constructed based on the discriminative graph.
