Unifying Orthogonal Monte Carlo Methods

Authors: Krzysztof Choromanski, Mark Rowland, Wenyu Chen, Adrian Weller

ICML 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We provide extensive empirical evaluations with guidance for practitioners. and We evaluate empirically AOMC approaches, noting relative strengths and weaknesses; see Section 6.
Researcher Affiliation Collaboration 1Google Brain 2University of Cambridge 3Massachusetts Institute of Technology 4Alan Turing Institute.
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks clearly labeled as 'Algorithm' or 'Pseudocode'.
Open Source Code No The paper does not include an explicit statement about the release of source code for the methodology described, nor does it provide a direct link to a code repository.
Open Datasets Yes We present experiments on four datasets: boston, cpu, wine, parkinson (more datasets studied in the Appendix). and We compare different MC estimators on the task of learning a RL policy for the Swimmer task from Open AI Gym.
Dataset Splits No The paper mentions conducting experiments on various datasets and tasks, but it does not provide specific dataset split information (e.g., exact percentages, sample counts, or detailed splitting methodology) for training, validation, and testing.
Hardware Specification No The paper does not provide specific hardware details such as exact GPU/CPU models, processor types, or memory amounts used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details, such as library or solver names with version numbers, needed to replicate the experiment.
Experiment Setup Yes In all experiments, we used Cd log(d) rotations with C = 2 for the KAC mechanism. and The policy is encoded by a neural network with two hidden layers of size 41 each and using Toeplitz matrices. The gradient vector is 253-dimensional and we use k = 253 samples for each experiment. and We learn linear policies of 96 parameters.