Search Results for author: Sara Magliacane

Found 12 papers, 8 papers with code

iCITRIS: Causal Representation Learning for Instantaneous Temporal Effects

1 code implementation13 Jun 2022 Phillip Lippe, Sara Magliacane, Sindy Löwe, Yuki M. Asano, Taco Cohen, Efstratios Gavves

Recent work has shown that one can reconstruct the causal variables from temporal sequences of observations under the assumption that there are no instantaneous causal relations between them.

Causal Discovery Representation Learning +1

Factored Adaptation for Non-Stationary Reinforcement Learning

no code implementations30 Mar 2022 Fan Feng, Biwei Huang, Kun Zhang, Sara Magliacane

Dealing with non-stationarity in environments (e. g., in the transition dynamics) and objectives (e. g., in the reward functions) is a challenging problem that is crucial in real-world applications of reinforcement learning (RL).

reinforcement-learning reinforcement Learning

CITRIS: Causal Identifiability from Temporal Intervened Sequences

1 code implementation7 Feb 2022 Phillip Lippe, Sara Magliacane, Sindy Löwe, Yuki M. Asano, Taco Cohen, Efstratios Gavves

Understanding the latent causal factors of a dynamical system from visual observations is considered a crucial step towards agents reasoning in complex environments.

Representation Learning Temporal Sequences

AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning

1 code implementation ICLR 2022 Biwei Huang, Fan Feng, Chaochao Lu, Sara Magliacane, Kun Zhang

We show that by explicitly leveraging this compact representation to encode changes, we can efficiently adapt the policy to the target domain, in which only a few samples are needed and further policy optimization is avoided.

Atari Games reinforcement-learning +2

Active Structure Learning of Causal DAGs via Directed Clique Trees

1 code implementation NeurIPS 2020 Chandler Squires, Sara Magliacane, Kristjan Greenewald, Dmitriy Katz, Murat Kocaoglu, Karthikeyan Shanmugam

Most existing works focus on \textit{worst-case} or \textit{average-case} lower bounds for the number of interventions required to orient a DAG.

Selection bias

Active Structure Learning of Causal DAGs via Directed Clique Tree

3 code implementations1 Nov 2020 Chandler Squires, Sara Magliacane, Kristjan Greenewald, Dmitriy Katz, Murat Kocaoglu, Karthikeyan Shanmugam

Most existing works focus on worst-case or average-case lower bounds for the number of interventions required to orient a DAG.

Selection bias

Verifiably Safe Exploration for End-to-End Reinforcement Learning

1 code implementation2 Jul 2020 Nathan Hunt, Nathan Fulton, Sara Magliacane, Nghia Hoang, Subhro Das, Armando Solar-Lezama

We also prove that our method of enforcing the safety constraints preserves all safe policies from the original environment.

object-detection Object Detection +3

An Upper Bound for Random Measurement Error in Causal Discovery

no code implementations18 Oct 2018 Tineke Blom, Anna Klimovskaia, Sara Magliacane, Joris M. Mooij

Causal discovery algorithms infer causal relations from data based on several assumptions, including notably the absence of measurement error.

Causal Discovery

Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions

1 code implementation NeurIPS 2018 Sara Magliacane, Thijs van Ommen, Tom Claassen, Stephan Bongers, Philip Versteeg, Joris M. Mooij

An important goal common to domain adaptation and causal inference is to make accurate predictions when the distributions for the source (or training) domain(s) and target (or test) domain(s) differ.

Causal Inference Domain Adaptation

Joint Causal Inference from Multiple Contexts

no code implementations30 Nov 2016 Joris M. Mooij, Sara Magliacane, Tom Claassen

We explain how several well-known causal discovery algorithms can be seen as addressing special cases of the JCI framework, and we also propose novel implementations that extend existing causal discovery methods for purely observational data to the JCI setting.

Causal Discovery Causal Inference

Ancestral Causal Inference

1 code implementation NeurIPS 2016 Sara Magliacane, Tom Claassen, Joris M. Mooij

Constraint-based causal discovery from limited data is a notoriously difficult challenge due to the many borderline independence test decisions.

Causal Discovery Causal Inference

Cannot find the paper you are looking for? You can Submit a new open access paper.