Representation Learning via Invariant Causal Mechanisms

Authors: Jovana Mitrovic, Brian McWilliams, Jacob C Walker, Lars Holger Buesing, Charles Blundell

ICLR 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirically, RELIC significantly outperforms competing methods in terms of robustness and out-of-distribution generalization on Image Net, while also significantly outperforming these methods on Atari achieving above human-level performance on 51 out of 57 games.
Researcher Affiliation Industry Jovana Mitrovic Brian Mc Williams Jacob Walker Lars Buesing Charles Blundell Deep Mind London, UK {mitrovic, bmcw, jcwalker, lbuesing, cblundell}@google.com
Pseudocode No The paper does not contain any pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets Yes For the prediction tasks, we test RELIC after pretraining the representation in a self-supervised way on the training set of the Image Net ILSVRC-2012 dataset (Russakovsky et al., 2015). ... Specifically, we test RELIC on the suite of Atari games (Bellemare et al., 2013) which consists of 57 diverse games of varying difficulty.
Dataset Splits No The paper mentions using the 'Image Net validation set' but does not provide specific details on its split (e.g., percentages, sample counts, or explicit splitting methodology) within the main text.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup No The paper refers to external procedures and appendices (e.g., 'following the procedure in (Kolesnikov et al., 2019; Chen et al., 2020a) and Appendix E.4.') but does not explicitly state concrete hyperparameter values or detailed training configurations within the main text.