Label-Imbalanced and Group-Sensitive Classification under Overparameterization

Authors: Ganesh Ramachandra Kini, Orestis Paraskevas, Samet Oymak, Christos Thrampoulidis

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

Reproducibility Variable Result LLM Response
Research Type Experimental Importantly, our experiments on state-of-the-art datasets are fully consistent with our theoretical insights and confirm the superior performance of our algorithms.
Researcher Affiliation Academia Ganesh Ramachandra Kini University of California, Santa Barbara kini@ucsb.edu Orestis Paraskevas University of California, Santa Barbara orestis@ucsb.edu Samet Oymak University of California, Riverside oymak@ece.ucr.edu Christos Thrampoulidis University of British Columbia cthrampo@ece.ubc.ca
Pseudocode No The paper does not contain any pseudocode or explicitly labeled algorithm blocks.
Open Source Code Yes [1] Code for paper: Label-imbalanced and group-sensitive classification under overparameterization. https://github.com/orparask/VS-Loss.
Open Datasets Yes Table 1 evaluates LA/CDT/VS-losses on imbalanced instances of CIFAR-10/100... We consider the Waterbirds dataset [45].
Dataset Splits Yes For consistency with [17, 8, 32, 54] we keep a balanced test set and in addition to evaluating our models on it, we treat it as our validation set and use it to tune our hyperparameters.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper does not list specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup Yes We set an imbalance ratio Nmax/Nmin = 100... For consistency, we follow the training setting in [8]... We use a grid to pick the best τ / γ / (τ,γ)-pair for the LA / CDT / VS losses... In Fig. 4(c1,c3) we trained for 200 epochs, while in Fig. 4(c2,c4) we trained for 300 epochs... For γ = 0.15... We did not fine-tune γ as the heuristic choice already shows the benefit of Group-VS-loss.