14 citations · 46 across the 25 of their papers we have counts for
6 papers · 1 filter
Linear Mode Connectivity in Differentiable Tree Ensembles
Ryuichi Kanoh, Mahito Sugiyama
Linear Mode Connectivity (LMC) refers to the phenomenon that performance remains consistent for linearly interpolated models in the parameter space. For independently optimized mod…
StiefelGen: A Simple, Model Agnostic Approach for Time Series Data Augmentation over Riemannian Manifolds
Prasad Cheema, Mahito Sugiyama
Data augmentation is an area of research which has seen active development in many machine learning fields, such as in image-based learning models, reinforcement learning for self…
Analyzing Tree Architectures in Ensembles via Neural Tangent Kernel
Ryuichi Kanoh, Mahito Sugiyama
A soft tree is an actively studied variant of a decision tree that updates splitting rules using the gradient method. Although soft trees can take various architectures, their impa…
A Neural Tangent Kernel Perspective of Infinite Tree Ensembles
Ryuichi Kanoh, Mahito Sugiyama
In practical situations, the tree ensemble is one of the most popular models along with neural networks. A soft tree is a variant of a decision tree. Instead of using a greedy meth…
Unintended Effects on Adaptive Learning Rate for Training Neural Network with Output Scale Change
Ryuichi Kanoh, Mahito Sugiyama
A multiplicative constant scaling factor is often applied to the model output to adjust the dynamics of neural network parameters. This has been used as one of the key intervention…
Learning Graph Representation via Formal Concept Analysis
Yuka Yoneda, Mahito Sugiyama, Takashi Washio
We present a novel method that can learn a graph representation from multivariate data. In our representation, each node represents a cluster of data points and each edge represent…