Search Results for author:
Found 26 papers, 12 papers with code
Extended Flow Matching: a Method of Conditional Generation with Generalized Continuity Equation
In this paper, we develop the theory of conditional generation based on Flow Matching, a current strong contender of diffusion methods.
Neural Fourier Transform: A General Approach to Equivariant Representation Learning
Symmetry learning has proven to be an effective approach for extracting the hidden structure of data, with the concept of equivariance relation playing the central role.
Invariance-adapted decomposition and Lasso-type contrastive learning
Recent years have witnessed the effectiveness of contrastive learning in obtaining the representation of dataset that is useful in interpretation and downstream tasks.
Unsupervised Learning of Equivariant Structure from Sequences
In this study, we present meta-sequential prediction (MSP), an unsupervised framework to learn the symmetry from the time sequence of length at least three.
Contrastive Representation Learning with Trainable Augmentation Channel
In contrastive representation learning, data representation is trained so that it can classify the image instances even when the images are altered by augmentations.
Bayesian Meta-Learning for Few-Shot 3D Shape Completion
Estimating the 3D shape of real-world objects is a key perceptual challenge.
RECONNAISSANCE FOR REINFORCEMENT LEARNING WITH SAFETY CONSTRAINTS
In this study, we consider a situation in which the agent has access to the generative model which provides us with a next state sample for any given state-action pair, and propose a model to solve a CMDP problem by decomposing the CMDP into a pair of MDPs; \textit{reconnaissance} MDP (R-MDP) and \textit{planning} MDP (P-MDP).
When is invariance useful in an Out-of-Distribution Generalization problem ?
Popular approaches in this field use the hypothesis that such a predictor shall be an \textit{invariant predictor} that captures the mechanism that remains constant across environments.
Learning Structured Latent Factors from Dependent Data:A Generative Model Framework from Information-Theoretic Perspective
Learning controllable and generalizable representation of multivariate data with desired structural properties remains a fundamental problem in machine learning.
Meta Learning as Bayes Risk Minimization
However, the posterior distribution in Neural Process violates the way the posterior distribution changes with the contextual dataset.
Reconnaissance and Planning algorithm for constrained MDP
Practical reinforcement learning problems are often formulated as constrained Markov decision process (CMDP) problems, in which the agent has to maximize the expected return while satisfying a set of prescribed safety constraints.
Optuna: A Next-generation Hyperparameter Optimization Framework
We will present the design-techniques that became necessary in the development of the software that meets the above criteria, and demonstrate the power of our new design through experimental results and real world applications.
A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation
Recomputation algorithms collectively refer to a family of methods that aims to reduce the memory consumption of the backpropagation by selectively discarding the intermediate results of the forward propagation and recomputing the discarded results as needed.
Robustness to Adversarial Perturbations in Learning from Incomplete Data
What is the role of unlabeled data in an inference problem, when the presumed underlying distribution is adversarially perturbed?
Adaptive Sample-space & Adaptive Probability coding: a neural-network based approach for compression
We propose Adaptive Sample-space & Adaptive Probability (ASAP) coding, an efficient neural-network based method for lossy data compression.
DISTRIBUTIONAL CONCAVITY REGULARIZATION FOR GANS
We propose Distributional Concavity (DC) regularization for Generative Adversarial Networks (GANs), a functional gradient-based method that promotes the entropy of the generator distribution and works against mode collapse.
A Wrapped Normal Distribution on Hyperbolic Space for Gradient-Based Learning
Hyperbolic space is a geometry that is known to be well-suited for representation learning of data with an underlying hierarchical structure.
Graph Warp Module: an Auxiliary Module for Boosting the Power of Graph Neural Networks in Molecular Graph Analysis
Graph Neural Network (GNN) is a popular architecture for the analysis of chemical molecules, and it has numerous applications in material and medicinal science.
Spatially Controllable Image Synthesis with Internal Representation Collaging
We present a novel CNN-based image editing strategy that allows the user to change the semantic information of an image over an arbitrary region by manipulating the feature-space representation of the image in a trained GAN model.
Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN
Training of Generative Adversarial Network (GAN) on a video dataset is a challenge because of the sheer size of the dataset and the complexity of each observation.
Spectral Normalization for Generative Adversarial Networks
One of the challenges in the study of generative adversarial networks is the instability of its training.
Ranked #20 on
Image Generation
on STL-10
cGANs with Projection Discriminator
We propose a novel, projection based way to incorporate the conditional information into the discriminator of GANs that respects the role of the conditional information in the underlining probabilistic model.
Ranked #14 on
Conditional Image Generation
on CIFAR-10
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning
In our experiments, we applied VAT to supervised and semi-supervised learning tasks on multiple benchmark datasets.
Distributional Smoothing with Virtual Adversarial Training
We propose local distributional smoothness (LDS), a new notion of smoothness for statistical model that can be used as a regularization term to promote the smoothness of the model distribution.
Deep learning of fMRI big data: a novel approach to subject-transfer decoding
Our PSA successfully visualized the subject-independent features contributing to the subject-transferability of the trained decoder.
Principal Sensitivity Analysis
We then visualize the PSMs to demonstrate the PSA's ability to decompose the knowledge acquired by the trained classifiers.
