Generalized No Free Lunch Theorem for Adversarial Robustness

Authors: Elvis Dohmatob

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

Reproducibility Variable Result LLM Response
Research Type Experimental Our theoretical bounds are demonstrated on both simulated and real data (MNIST). Section 4 presents experiments on both simulated and real data that confirm our theoretical results.
Researcher Affiliation Industry 1Criteo, Paris, France.
Pseudocode No The paper does not contain any structured 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 MNIST dataset (Le Cun & Cortes, 2010)
Dataset Splits No The paper mentions 'held-out data' and 'train' but does not specify exact dataset split percentages or sample counts for training, validation, and test sets.
Hardware Specification No The paper does not provide specific hardware details used for running its experiments.
Software Dependencies No The paper mentions 'PyTorch' but does not provide specific version numbers for it or any other software dependencies.
Experiment Setup Yes The classifier h is a multi-layer perceptron with architecture 1000 200 100 2 and Re LU activations. trained a deep feed-forward CNN (architecture: Conv2d Conv2d 320 10)