What can be estimated? Identifiability, estimability, causal inference and ill-posed inverse problems
https://arxiv.org/abs/1904.02826
https://arxiv.org/abs/1904.02826
Forwarded from Recent AI News
inFERENCe: Notes on Causally Correct Partial Models https://www.inference.vc/notes-on-causally-correct-partial-models-2/
inFERENCe
Notes on Causally Correct Partial Models
I recently encountered this cool paper in a reading group presentation:
* Rezende et al (2020) Rezende Causally Correct Partial Models for
Reinforcement Learning [https://arxiv.org/abs/2002.02836v1]
It's frankly taken me a long time to understand what…
* Rezende et al (2020) Rezende Causally Correct Partial Models for
Reinforcement Learning [https://arxiv.org/abs/2002.02836v1]
It's frankly taken me a long time to understand what…
On Causal and Anticausal Learning
https://arxiv.org/abs/1206.6471
https://arxiv.org/abs/1206.6471
arXiv.org
On Causal and Anticausal Learning
We consider the problem of function estimation in the case where an underlying causal model can be inferred. This has implications for popular scenarios such as covariate shift, concept drift,...
Underspecification Presents Challenges for Credibility in Modern Machine Learning
https://arxiv.org/abs/2011.03395
https://arxiv.org/abs/2011.03395
Counterfactual Data Augmentation using Locally Factored Dynamics
https://arxiv.org/abs/2007.02863
https://arxiv.org/abs/2007.02863
arXiv.org
Counterfactual Data Augmentation using Locally Factored Dynamics
Many dynamic processes, including common scenarios in robotic control and reinforcement learning (RL), involve a set of interacting subprocesses. Though the subprocesses are not independent, their...
Proactive Pseudo-Intervention: Causally Informed Contrastive Learning For Interpretable Vision Models
https://arxiv.org/abs/2012.03369v1
https://arxiv.org/abs/2012.03369v1
Actual causation: a stone soup essay
https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.225.1178&rep=rep1&type=pdf
https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.225.1178&rep=rep1&type=pdf
Feedback in Imitation Learning: Confusion on Causality and Covariate Shift
https://arxiv.org/abs/2102.02872
https://arxiv.org/abs/2102.02872
Selecting Treatment Effects Models for Domain Adaptation Using Causal Knowledge
http://arxiv.org/abs/2102.06271
http://arxiv.org/abs/2102.06271
Efficient Learning with Arbitrary Covariate Shift
http://arxiv.org/abs/2102.07802
http://arxiv.org/abs/2102.07802
Forwarded from Data Science by ODS.ai 🦜
Towards Causal Representation Learning
Work on how neural networks derive casual variables from low-level observations.
Link: https://arxiv.org/abs/2102.11107
#casuallearning #bengio #nn #DL
Work on how neural networks derive casual variables from low-level observations.
Link: https://arxiv.org/abs/2102.11107
#casuallearning #bengio #nn #DL
The Deconfounded Recommender: A Causal Inference Approach to Recommendation
https://arxiv.org/abs/1808.06581
https://arxiv.org/abs/1808.06581
arXiv.org
The Deconfounded Recommender: A Causal Inference Approach to Recommendation
The goal of recommendation is to show users items that they will like. Though usually framed as a prediction, the spirit of recommendation is to answer an interventional question---for each user...
#study_materials
Introduction to Causal Inference by Brady Neal
(PhD student from MILA)
[videos, slides, a list of literature]
https://www.bradyneal.com/causal-inference-course
Introduction to Causal Inference by Brady Neal
(PhD student from MILA)
[videos, slides, a list of literature]
https://www.bradyneal.com/causal-inference-course
Bradyneal
Introduction to Causal Inference
Introduction to Causal Inference. A free online course on causal inference from a machine learning perspective.
Forwarded from Just links
Counterfactual VQA: A Cause-Effect Look at Language Bias https://arxiv.org/abs/2006.04315
Forwarded from Arxiv
- Probing Causal Common Sense in Dialogue Response Generation. (arXiv:2104.09574v1 [cs.CL])
http://arxiv.org/abs/2104.09574
http://arxiv.org/abs/2104.09574
#offtopic
Bayesian Optimization is Superior to Random Search for Machine Learning Hyperparameter Tuning: Analysis of the Black-Box Optimization Challenge 2020
https://arxiv.org/abs/2104.10201
Bayesian Optimization is Superior to Random Search for Machine Learning Hyperparameter Tuning: Analysis of the Black-Box Optimization Challenge 2020
https://arxiv.org/abs/2104.10201
Forwarded from Just links
Causal Inference Q-Network: Toward Resilient Reinforcement Learning https://arxiv.org/abs/2102.09677