Deep Sets

Authors: Manzil Zaheer, Satwik Kottur, Siamak Ravanbakhsh, Barnabas Poczos, Russ R. Salakhutdinov, Alexander J. Smola

NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate the applicability of our method on population statistic estimation, point cloud classification, set expansion, and outlier detection.
Researcher Affiliation Collaboration Manzil Zaheer1,2, Satwik Kottur1, Siamak Ravanbhakhsh1, Barnabás Póczos1, Ruslan Salakhutdinov1, Alexander J Smola1,2 1 Carnegie Mellon University 2 Amazon Web Services {manzilz,skottur,mravanba,bapoczos,rsalakhu,smola}@cs.cmu.edu
Pseudocode No No structured pseudocode or algorithm blocks are present in the paper.
Open Source Code No No explicit statement or link providing concrete access to the source code for the Deep Sets methodology described in this paper.
Open Datasets Yes MNIST8m [24] contains 8 million instances of 28 28 grey-scale stamps of digits in {0, . . . , 9}.
Dataset Splits Yes Each dataset is split into TRAIN (80%), VAL (10%) and TEST (10%). We learn models using TRAIN and evaluate on TEST, while VAL is used for hyperparameter selection and early stopping.
Hardware Specification No No specific hardware details (GPU models, CPU types, memory) used for running experiments are provided in the paper.
Software Dependencies No The paper does not provide specific version numbers for software dependencies or libraries used (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup Yes We train using L2 loss with a Deep Sets architecture having 3 fully connected layers with Re LU activation for both transformations φ and ρ.