
Contrastive Representation Learning with Trainable Augmentation Channel
In contrastive representation learning, data representation is trained s...
read it

OutofDistribution Generalization with Maximal Invariant Predictor
OutofDistribution (OOD) generalization problem is a problem of seeking...
read it

Learning Structured Latent Factors from Dependent Data:A Generative Model Framework from InformationTheoretic Perspective
Learning controllable and generalizable representation of multivariate d...
read it

Meta Learning as Bayes Risk Minimization
MetaLearning is a family of methods that use a set of interrelated task...
read it

Reconnaissance and Planning algorithm for constrained MDP
Practical reinforcement learning problems are often formulated as constr...
read it

Optuna: A Nextgeneration Hyperparameter Optimization Framework
The purpose of this study is to introduce new designcriteria for nextg...
read it

A Graph Theoretic Framework of Recomputation Algorithms for MemoryEfficient Backpropagation
Recomputation algorithms collectively refer to a family of methods that ...
read it

Robustness to Adversarial Perturbations in Learning from Incomplete Data
What is the role of unlabeled data in an inference problem, when the pre...
read it

A Differentiable Gaussianlike Distribution on Hyperbolic Space for GradientBased Learning
Hyperbolic space is a geometry that is known to be wellsuited for repre...
read it

Graph Warp Module: an Auxiliary Module for Boosting the Power of Graph Neural Networks
Recently, Graph Neural Networks (GNNs) are trending in the machine learn...
read it

Collaging on Internal Representations: An Intuitive Approach for Semantic Transfiguration
We present a novel CNNbased image editing method that allows the user t...
read it

Spectral Normalization for Generative Adversarial Networks
One of the challenges in the study of generative adversarial networks is...
read it

cGANs with Projection Discriminator
We propose a novel, projection based way to incorporate the conditional ...
read it

Virtual Adversarial Training: a Regularization Method for Supervised and Semisupervised Learning
We propose a new regularization method based on virtual adversarial loss...
read it

Distributional Smoothing with Virtual Adversarial Training
We propose local distributional smoothness (LDS), a new notion of smooth...
read it

Deep learning of fMRI big data: a novel approach to subjecttransfer decoding
As a technology to read brain states from measurable brain activities, b...
read it

Principal Sensitivity Analysis
We present a novel algorithm (Principal Sensitivity Analysis; PSA) to an...
read it
Masanori Koyama
is this you? claim profile