HEW-Local SGD provides exact-weight adaptive aggregation for heterogeneous local SGD with one-step guarantees and explicit convergence results under unequal local horizons.
Mnist handwritten digit database.ATT Labs [Online]
5 Pith papers cite this work. Polarity classification is still indexing.
citation-role summary
citation-polarity summary
verdicts
UNVERDICTED 5roles
dataset 1polarities
use dataset 1representative citing papers
A new parameter reconstruction method achieves globally optimal training for spiking neural networks by convexifying parallel recurrent threshold networks that include SNNs as a special case.
Introduces a novel search direction enabling sublinear stochastic bilevel regret guarantees for first- and zeroth-order online bilevel optimization algorithms without relying on window smoothing.
AML outperforms cross-validated baselines including CNNs on 50-2000 example image datasets and is comparable to XGBoost/LightGBM on tabular data using only training data and no task-dependent hyperparameters.
Dim-R2 extends R2 to arbitrary dimensions, supplies multidimensional accuracy views, and reduces noise sensitivity for better regression evaluation.
citing papers explorer
-
Heterogeneous-Horizon Exact-Weight Local SGD
HEW-Local SGD provides exact-weight adaptive aggregation for heterogeneous local SGD with one-step guarantees and explicit convergence results under unequal local horizons.
-
Globally Optimal Training of Spiking Neural Networks via Parameter Reconstruction
A new parameter reconstruction method achieves globally optimal training for spiking neural networks by convexifying parallel recurrent threshold networks that include SNNs as a special case.
-
Stochastic Regret Guarantees for Online Zeroth- and First-Order Bilevel Optimization
Introduces a novel search direction enabling sublinear stochastic bilevel regret guarantees for first- and zeroth-order online bilevel optimization algorithms without relying on window smoothing.
-
Algebraic Machine Learning for Small-to-Medium Datasets Is Competitive against Strong Standard Baselines
AML outperforms cross-validated baselines including CNNs on 50-2000 example image datasets and is comparable to XGBoost/LightGBM on tabular data using only training data and no task-dependent hyperparameters.
-
A dimensional R2 regression metric
Dim-R2 extends R2 to arbitrary dimensions, supplies multidimensional accuracy views, and reduces noise sensitivity for better regression evaluation.