REVIEW 4 cited by
PopulAtion Parameter Averaging (PAPA)
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Ensemble methods combine the predictions of multiple models to improve performance, but they require significantly higher computation costs at inference time. To avoid these costs, multiple neural networks can be combined into one by averaging their weights. However, this usually performs significantly worse than ensembling. Weight averaging is only beneficial when different enough to benefit from combining them, but similar enough to average well. Based on this idea, we propose PopulAtion Parameter Averaging (PAPA): a method that combines the generality of ensembling with the efficiency of weight averaging. PAPA leverages a population of diverse models (trained on different data orders, augmentations, and regularizations) while slowly pushing the weights of the networks toward the population average of the weights. We also propose PAPA variants (PAPA-all, and PAPA-2) that average weights rarely rather than continuously; all methods increase generalization, but PAPA tends to perform best. PAPA reduces the performance gap between averaging and ensembling, increasing the average accuracy of a population of models by up to 0.8% on CIFAR-10, 1.9% on CIFAR-100, and 1.6% on ImageNet when compared to training independent (non-averaged) models.
Forward citations
Cited by 4 Pith papers
-
Model Parallelism With Subnetwork Data Parallelism
Training each GPU on a fixed overlapping subnetwork and averaging shared parameters cuts per-device memory by up to 60 percent without exchanging activations, matching DDP accuracy under FLOP-matched budgets.
-
Forget the Data and Fine-Tuning! Just Fold the Network to Compress
Model folding compresses a network by k-means clustering similar neurons across adjacent layers and repairing activation statistics without data (Fold-AR, Fold-DIR), surpassing prior data-free methods at high sparsity.
-
Intrinsic Strain-Driven Topological Evolution in SrRuO3 via Flexural Strain Engineering
The abstract reports a 21% anomalous Hall conductivity increase in flexurally strained SrRuO3, but the submitted full text belongs to a different machine learning paper.
-
FCOS: A Two-Stage Recoverable Model Pruning Framework for Automatic Modulation Recognition
FCOS combines channel clustering and layer collapse diagnosis to prune AMR models by over 95% with minimal accuracy loss.
Discussion (0). Continue with ORCID to comment.