Search Results for author:
Found 16 papers, 6 papers with code
Diversity-Aware Agnostic Ensemble of Sharpness Minimizers
There has long been plenty of theoretical and empirical evidence supporting the success of ensemble learning.
Robust Diffusion GAN using Semi-Unbalanced Optimal Transport
Diffusion models, a type of generative model, have demonstrated great potential for synthesizing highly detailed images.
Ranked #5 on
Image Generation
on STL-10
Robust Contrastive Learning With Theory Guarantee
Contrastive learning (CL) is a self-supervised training paradigm that allows us to extract meaningful features without any label information.
Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks
Recent works have shown that deep neural networks are vulnerable to adversarial examples that find samples close to the original image but can make the model misclassify.
RSAM: Learning on manifolds with Riemannian Sharpness-aware Minimization
Motivated by this analysis, we introduce our algorithm, Riemannian Sharpness-Aware Minimization (RSAM).
Sharpness & Shift-Aware Self-Supervised Learning
Self-supervised learning aims to extract meaningful features from unlabeled data for further downstream tasks.
Entropic Gromov-Wasserstein between Gaussian Distributions
When the metric is the inner product, which we refer to as inner product Gromov-Wasserstein (IGW), we demonstrate that the optimal transportation plans of entropic IGW and its unbalanced variant are (unbalanced) Gaussian distributions.
Improving Mini-batch Optimal Transport via Partial Transportation
Mini-batch optimal transport (m-OT) has been widely used recently to deal with the memory issue of OT in large-scale applications.
On Multimarginal Partial Optimal Transport: Equivalent Forms and Computational Complexity
We demonstrate that the ApproxMPOT algorithm can approximate the optimal value of multimarginal POT problem with a computational complexity upper bound of the order $\tilde{\mathcal{O}}(m^3(n+1)^{m}/ \varepsilon^2)$ where $\varepsilon > 0$ stands for the desired tolerance.
On Robust Optimal Transport: Computational Complexity and Barycenter Computation
We consider robust variants of the standard optimal transport, named robust optimal transport, where marginal constraints are relaxed via Kullback-Leibler divergence.
On Transportation of Mini-batches: A Hierarchical Approach
To address these problems, we propose a novel mini-batch scheme for optimal transport, named Batch of Mini-batches Optimal Transport (BoMb-OT), that finds the optimal coupling between mini-batches and it can be seen as an approximation to a well-defined distance on the space of probability measures.
Point-set Distances for Learning Representations of 3D Point Clouds
From this study, we propose to use sliced Wasserstein distance and its variants for learning representations of 3D point clouds.
Improving Relational Regularized Autoencoders with Spherical Sliced Fused Gromov Wasserstein
To improve the discrepancy and consequently the relational regularization, we propose a new relational discrepancy, named spherical sliced fused Gromov Wasserstein (SSFG), that can find an important area of projections characterized by a von Mises-Fisher distribution.
Distributional Sliced-Wasserstein and Applications to Generative Modeling
Sliced-Wasserstein distance (SW) and its variant, Max Sliced-Wasserstein distance (Max-SW), have been used widely in the recent years due to their fast computation and scalability even when the probability measures lie in a very high dimensional space.
On Unbalanced Optimal Transport: An Analysis of Sinkhorn Algorithm
We provide a computational complexity analysis for the Sinkhorn algorithm that solves the entropic regularized Unbalanced Optimal Transport (UOT) problem between two measures of possibly different masses with at most $n$ components.
Scalable Support Vector Clustering Using Budget
In this paper, we propose applying Stochastic Gradient Descent (SGD) framework to the first phase of support-based clustering for finding the domain of novelty and a new strategy to perform the clustering assignment.
