1 code implementation • 1 Jun 2023 • Raanan Y. Rohekar, Shami Nisimov, Yaniv Gurwicz, Gal Novik
We present a constraint-based algorithm for learning causal structures from observational time-series data, in the presence of latent confounders.
no code implementations • 6 Nov 2022 • Dan Elbaz, Gal Novik, Oren Salzman
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.
no code implementations • 3 Nov 2022 • Gal Leibovich, Guy Jacob, Or Avner, Gal Novik, Aviv Tamar
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.
no code implementations • 7 Oct 2022 • Shami Nisimov, Raanan Y. Rohekar, Yaniv Gurwicz, Guy Koren, Gal Novik
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.
1 code implementation • NeurIPS 2021 • Raanan Y. Rohekar, Shami Nisimov, Yaniv Gurwicz, Gal Novik
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.
no code implementations • 1 Nov 2021 • Gal Leibovich, Guy Jacob, Shadi Endrawis, Gal Novik, Aviv Tamar
We show that our score - VSDR - can significantly improve the accuracy of policy ranking without requiring additional real world data.
no code implementations • 11 Jul 2021 • Shami Nisimov, Yaniv Gurwicz, Raanan Y. Rohekar, Gal Novik
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.
no code implementations • 10 May 2021 • Shadi Endrawis, Gal Leibovich, Guy Jacob, Gal Novik, Aviv Tamar
In this work, we propose that data collection policies should actively explore the environment to collect diverse data.
no code implementations • 14 Dec 2020 • Raanan Y. Rohekar, Yaniv Gurwicz, Shami Nisimov, Gal Novik
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.
4 code implementations • 27 Oct 2019 • Neta Zmora, Guy Jacob, Lev Zlotnik, Bar Elharar, Gal Novik
This paper presents the philosophy, design and feature-set of Neural Network Distiller, an open-source Python package for DNN compression research.
no code implementations • NeurIPS 2019 • Raanan Y. Rohekar, Yaniv Gurwicz, Shami Nisimov, Gal Novik
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.
1 code implementation • NeurIPS 2018 • Raanan Y. Rohekar, Yaniv Gurwicz, Shami Nisimov, Guy Koren, Gal Novik
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.
no code implementations • NeurIPS 2018 • Raanan Y. Rohekar, Shami Nisimov, Yaniv Gurwicz, Guy Koren, Gal Novik
We prove that conditional-dependency relations among the latent variables in the generative graph are preserved in the class-conditional discriminative graph.
no code implementations • ICLR 2018 • Raanan Y. Yehezkel Rohekar, Guy Koren, Shami Nisimov, Gal Novik
Finally, a deep neural network structure is constructed based on the discriminative graph.