arXiv research

Introduces Cauchy-Schwarz divergence for domain adaptation.

New framework using Jensen-Shannon divergence improves domain adaptation theory.

Proposes ATM method to improve domain adaptation.

New metric and method for sEMG-based gesture recognition under domain shifts.

Paper tackles continuous transfer learning with evolving target domains.

Improved UDA framework using $f$-divergence measures.

Method generates intermediate domains to align source and target domains.

New proof of Willmore inequality using geometric divergence inequality.

The paper improves model robustness by regularizing posterior differences.

This work improves transferability by considering conditional distributions in feature representations.

Rank-statistic method approximates $f$-divergences without density-ratio estimation.

New framework for domain adaptation using hierarchical optimal transport.

Proposes a new divergence measure for probability distributions.

Study proves symmetry of bounded domains in Riemannian manifolds.

In this paper, we study eigenvalue of linear fourth order elliptic operators in divergence form with Dirichlet boundary condition on a bounded domain in a compact Riemannian manifolds with boundary (possibly empty) and find a general inequality for them. As an application, by using this inequality, we study eigenvalues…

Our main result is that if a generic convex domain in $\R^n$ collapses to a domain in $\R^{n-1}$, then the difference between the first two Dirichlet eigenvalues of the Euclidean Laplacian, known as the fundamental gap, diverges. The boundary of the domain need not be smooth, merely Lipschitz continuous. To motivate th…

TMDA aligns subdomain data distribution discrepancies across domains using manifold representations.

We tackle class imbalance in unsupervised domain adaptation using latent codes.

Study improves density estimation for compact domains using $h$-lifted KL divergence.

Paper analyzes kNN estimator for KL divergence, proving its optimality.

We aim to analyze the relation between two random vectors that may potentially have both different number of attributes as well as realizations, and which may even not have a joint distribution. This problem arises in many practical domains, including biology and architecture. Existing techniques assume the vectors to …

Paper shows robust generative learning with minimal assumptions on target distributions.

The paper estimates eigenvalues for specific differential operators on curved spaces.

New samplers minimize KL divergence for constrained and non-Euclidean geometries.

Many text classification tasks are known to be highly domain-dependent. Unfortunately, the availability of training data can vary drastically across domains. Worse still, for some domains there may not be any annotated data at all. In this work, we propose a multinomial adversarial network (MAN) to tackle the text clas…

Domain adaptation (DA) is an important and emerging field of machine learning that tackles the problem occurring when the distributions of training (source domain) and test (target domain) data are similar but different. Current theoretical results show that the efficiency of DA algorithms depends on their capacity of …

Diverging Flows detects extrapolations in flow models, ensuring reliable predictions.

This work extends alpha-beta divergences to complex data and finds closed-form solutions.

We compute estimates for eigenvalues of a class of linear second-order elliptic differential operators in divergence form (with Dirichlet boundary condition) on a bounded domain in a complete Riemannian manifold. Our estimates are based upon the Weyl's asymptotic formula. As an application, we find a lower bound for th…

Estimates KL divergence with fairness considerations for sub-populations.

Paper explores how generative models can be made more creative.

The paper provides estimates for eigenvalues of elliptic differential problems.

Unified framework for distribution shift estimation, explanation, and improvement.

Paper connects rejection learning to Bhattacharyya divergence.

New risk decompositions clarify domain adaptation issues.

Reduced sample complexity for group-invariant distributions.

Efficiently visualizes uncertainty in local divergence of 2D vector fields.

The paper finds inequalities for eigenvalues of operators on immersed manifolds.

Proposes a method to improve treatment policies in data-scarce clinical settings.

This paper is devoted to the study of convergence of sequences of solutions to the constant mean curvature H equation. The convergence domain is defined. The main Theorem characterizes the complement of this convergence domain: it shows that circle arcs of curvature 2H compose this complement. We then give results whic…

This paper studies the problem of cross-network node classification to overcome the insufficiency of labeled data in a single network. It aims to leverage the label information in a partially labeled source network to assist node classification in a completely unlabeled or partially labeled target network. Existing met…

Can neural networks learn to compare graphs without feature engineering? In this paper, we show that it is possible to learn representations for graph similarity with neither domain knowledge nor supervision (i.e.\ feature engineering or labeled graphs). We propose Deep Divergence Graph Kernels, an unsupervised method …

New perspective on Sinkhorn algorithm using stochastic mirror descent.

Generative adversarial networks improve using discrepancy measure.

Paper tackles backwards-compatible data adaptation for confounded covariate and label shifts.

Proposes Infomax and Domain-Independent Representations for robust causal inference.

Selective removal of data subsets can efficiently unlearn unwanted distributions.

Paper proposes a new ML framework to enhance creativity in music generation.