Two noise-tolerant, bound-constrained AdaGrad variants for multilevel and domain-decomposition problems are proved to find an epsilon-approximate critical point in O(epsilon^-2) iterations with high probability.
Better Training using Weight-Constrained Stochastic Dynamics
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
We employ constraints to control the parameter space of deep neural networks throughout training. The use of customized, appropriately designed constraints can reduce the vanishing/exploding gradients problem, improve smoothness of classification boundaries, control weight magnitudes and stabilize deep neural networks, and thus enhance the robustness of training algorithms and the generalization capabilities of neural networks. We provide a general approach to efficiently incorporate constraints into a stochastic gradient Langevin framework, allowing enhanced exploration of the loss landscape. We also present specific examples of constrained training methods motivated by orthogonality preservation for weight matrices and explicit weight normalizations. Discretization schemes are provided both for the overdamped formulation of Langevin dynamics and the underdamped form, in which momenta further improve sampling efficiency. These optimization schemes can be used directly, without needing to adapt neural network architecture design choices or to modify the objective with regularization terms, and see performance improvements in classification tasks.
citation-role summary
citation-polarity summary
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Recursive Bound-Constrained AdaGrad with Applications to Multilevel and Domain Decomposition Minimization
Two noise-tolerant, bound-constrained AdaGrad variants for multilevel and domain-decomposition problems are proved to find an epsilon-approximate critical point in O(epsilon^-2) iterations with high probability.