Regularization in ResNet with Stochastic Depth

Authors: Soufiane Hayou, Fadhel Ayed

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

Reproducibility Variable Result LLM Response
Research Type Experimental We introduce a new algorithm called Sense Mode to compute the survival rates under a fixed training budget and provide a series of experiments that validates our Budget hypothesis introduced in Section 5. The objective of this section is two-fold: we empirically verify the theoretical analysis developed in sections 3 and 4 with a Vanilla Res Net model on a toy regression task; we also empirically validate the Budget Hypothesis on the benchmark datasets CIFAR-10 and CIFAR-100 [Krizhevsky et al., 2009].
Researcher Affiliation Collaboration Soufiane Hayou Department of Statistics University of Oxford United Kingdom Fadhel Ayed Huawei Technologies France
Pseudocode No The paper describes algorithmic steps for 'Sense Mode' in prose but does not provide a formally structured pseudocode or algorithm block.
Open Source Code Yes Notebooks and code to reproduce all experiments, plots and tables presented are available in the supplementary material.
Open Datasets Yes we also empirically validate the Budget Hypothesis on the benchmark datasets CIFAR-10 and CIFAR-100 [Krizhevsky et al., 2009].
Dataset Splits No The paper mentions benchmark datasets CIFAR-10 and CIFAR-100 but does not explicitly state the training, validation, and test splits (e.g., percentages, sample counts, or specific predefined splits) used for the experiments.
Hardware Specification No The paper does not provide specific details on the hardware (e.g., GPU/CPU models, memory, cloud instances) used for running the experiments.
Software Dependencies No The paper mentions building on an 'open-source implementation of standard Res Net4' (linking to a PyTorch repository) but does not list specific software dependencies with version numbers (e.g., Python, PyTorch, CUDA versions).
Experiment Setup Yes Implementation details: Vanilla Stable Res Net is composed of identical residual blocks each formed of a Linear layer followed by Re LU. Res Net110 follows [He et al., 2016, Huang et al., 2016]; it comprises three groups of residual blocks; each block consists of a sequence Convolution Batch Norm-Re LU-Convolution-Batch Norm. We use the adjective "Stable" (Stable Vanilla Res Net, Stable Res Net110) to indicate that we scale the blocks using a factor 1/ L as described in Section 3. ... We compare the three modes: Uniform, Linear, and Sense Mode on two benchmark datasets using a grid survival proportions.