Showing stat.MLShow all
2 papers · 1 filter
stat.ML2025
Optimal Condition for Initialization Variance in Deep Neural Networks: An SGD Dynamics Perspective
Hiroshi Horii, Sothea Has
Stochastic gradient descent (SGD), one of the most fundamental optimization algorithms in machine learning (ML), can be recast through a continuous-time approximation as a Fokker-P…
stat.ML2022
Consensual Aggregation on Random Projected High-dimensional Features for Regression
Sothea Has
In this paper, we present a study of a kernel-based consensual aggregation on randomly projected high-dimensional features of predictions for regression. The aggregation scheme is…