PRASS: Probabilistic Risk-averse Robust Learning with Stochastic Search

Authors: Tianle Zhang, Yanghao Zhang, Ronghui Mu, Jiaxu Liu, Jonathan Fieldsend, Wenjie Ruan

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical experiments demonstrate that PRASS outperforms existing state-of-the-art baselines.
Researcher Affiliation Academia 1Department of Computer Science, University of Liverpool, Liverpool, L69 3BX, UK 2Department of Computer Science, University of Exeter, Exeter, EX4 4QF, UK
Pseudocode Yes The full algorithm is summarised in Algorithm 1 in Appendix C.
Open Source Code No The paper does not provide an explicit statement or a link to open-source code for the described methodology.
Open Datasets Yes We conduct an extensive evaluation of the risk-averse robust learning method on three datasets: MNIST, CIFAR-10 and CIFAR-100.
Dataset Splits No The paper mentions 'Train/test set evaluations' but does not provide specific percentages or counts for training, validation, and test splits, nor does it explicitly mention a validation split.
Hardware Specification Yes All the experiments are executed on a system with a 32-Core AMD EPYC 7452 CPU and an NVIDIA A100 40GB GPU.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., PyTorch, TensorFlow, or specific library versions) used for the experiments.
Experiment Setup Yes For MNIST, we adopt a Re LU network architecture with two convolutional layers, while for CIFAR-10 and CIFAR-100, we utilise an 18-layer residual network architecture. Moreover, the uncertainty set under consideration is a perturbation set, defined as = {δ ∈ Rd : ||δ||∞ ≤ ϵ}, situated within a Gaussian distribution set p(δ) ∈ P. We set ϵ = 0.3 for MNIST and ϵ = 8/255 for CIFAR-10 and CIFAR-100. Full details are provided in Appendix C.