SIFAR: A Simple Faster Accelerated Variance-Reduced Gradient Method

Authors: Zhize Li

IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, the numerical experiments show that SIFAR converges faster than the previous state-of-the-art Varag, validating our theoretical results and confirming the practical superiority of SIFAR. In Figure 1, the x-axis and y-axis represent the number of data passes (i.e., we compute n stochastic gradients for each data pass) and the training loss, respectively. The numerical results presented in Figure 1 are conducted on different datasets. Each plot corresponds to one dataset (six datasets in total).
Researcher Affiliation Academia Zhize Li Singapore Management University EMAIL
Pseudocode Yes Algorithm 1 SIFAR: SImple Faster Accelerated variance Reduced gradient
Open Source Code No The paper does not contain any explicit statements or links indicating that the source code for the methodology described is open-source or publicly available.
Open Datasets Yes All datasets used in our experiments are downloaded from LIBSVM [Chang and Lin, 2011].
Dataset Splits No The paper mentions using datasets for a logistic regression problem but does not provide specific details on training, validation, or test splits (e.g., percentages or sample counts).
Hardware Specification No The paper describes numerical experiments but does not specify any hardware details such as CPU, GPU models, or memory.
Software Dependencies No The paper mentions 'LIBSVM [Chang and Lin, 2011]' as the source for datasets but does not provide specific version numbers for LIBSVM or any other software libraries or programming languages used for implementation.
Experiment Setup No Given the parameter L, we are ready to set all other hyperparameters for GD (see Corollary 2.1.2 in [Nesterov, 2004]), for Varag (see Theorem 1 in [Lan et al., 2019]) and for SIFAR (see our Theorem 1). Note that all of these three algorithms only require L for setting their (hyper)parameters.