arXiv research

TCRI improves domain generalization by enforcing conditional independence constraints.

DI-SVM improves brain condition decoding performance via domain independence.

A statistical test of independence may be constructed using the Hilbert-Schmidt Independence Criterion (HSIC) as a test statistic. The HSIC is defined as the distance between the embedding of the joint distribution, and the embedding of the product of the marginals, in a Reproducing Kernel Hilbert Space (RKHS). It has …

Typical spoken language understanding systems provide narrow semantic parses using a domain-specific ontology. The parses contain intents and slots that are directly consumed by downstream domain applications. In this work we discuss expanding such systems to handle compound entities and intents by introducing a domain…

In this paper, we present a novel framework incorporating a combination of sparse models in different domains. We posit the observed data as generated from a linear combination of a sparse Gaussian Markov model (with a sparse precision matrix) and a sparse Gaussian independence model (with a sparse covariance matrix). …

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

In this paper, we consider eigenvalues of the Dirichlet biharmonic operator on a bounded domain in a hyperbolic space. We obtain universal bounds on the $(k+1)$th eigenvalue in terms of the first $k$th eigenvalue independent of the domains.

Two impossibility theorems show formal alignment certification is impossible for AI systems.

HSIC loss improves robust regression and classification models.

In this paper, we study the problem of transfer learning with the attribute data. In the transfer learning problem, we want to leverage the data of the auxiliary and the target domains to build an effective model for the classification problem in the target domain. Meanwhile, the attributes are naturally stable cross d…

Self-training avoids spurious features in domain adaptation.

Automated dialogue quality evaluation using user satisfaction estimates across multiple domains.

We investigate the eigenvalues of the buckling problem of arbitrary order on compact domains in Euclidean spaces and spheres. We obtain universal bounds for the $k$th eigenvalue in terms of the lower eigenvalues independently of the particular geometry of the domain.

Through deep learning and computer vision techniques, driving manoeuvres can be predicted accurately a few seconds in advance. Even though adapting a learned model to new drivers and different vehicles is key for robust driver-assistance systems, this problem has received little attention so far. This work proposes to …

SFB uses stable features to adapt unstable ones for better performance.

Estimates the mass gap for domains with integral Ricci curvature bounds.

New metric estimates user satisfaction for dialogue quality evaluation.

In this paper we study the area of ideals triangles in a convex domain with its Hilbert geometry. We obtain a characterization of the hyperbolic geometry among all the Hilbert geometry in terms of area of ideals triangles. We also obtain a sharp lower bound on the hilbert area of ideal triangles, independant of the con…

In this paper we analyze the problem of the geodesic connectedness of subsets of Riemannian manifolds. By using variational methods, the geodesic connectedness of open domains (whose boundaries can be not differentiable and not convex) of a smooth Riemannian manifold is proved. In some cases also the convexity of the d…

Improved visual speech synthesis using adapted ASR acoustic models.

We study the volume distribution of nodal domains of random band-limited functions on generic manifolds, and find that in the high energy limit a typical instance obeys a deterministic universal law, independent of the manifold. Some of the basic qualitative properties of this law, such as its support, monotonicity and…

We show that the error probability of reconstructing kernel matrices from Random Fourier Features for the Gaussian kernel function is at most $\mathcal{O}(R^{2/3} \exp(-D))$, where $D$ is the number of random features and $R$ is the diameter of the data domain. We also provide an information-theoretic method-independen…

A method identifies domain-general features using causal graph constraints and regularization.

Domain adaptation in person re-identification (re-ID) has always been a challenging task. In this work, we explore how to harness the natural similar characteristics existing in the samples from the target domain for learning to conduct person re-ID in an unsupervised manner. Concretely, we propose a Self-similarity Gr…

Optimal Farey sequence for $Γ_0(2^n)$ with upper bound $2^{n-1}$.

SIGMA prior enables federated learning for non-factorizable models.

Sparse graph learning for dependent time series using ADMM.

This paper studies eigenvalues of the buckling problem of arbitrary order on bounded domains in Euclidean spaces and spheres. We prove universal bounds for the k-th eigenvalue in terms of the lower ones independent of the domains. Our results strengthen the recent work in [28] and generalize Cheng-Yang's recent estimat…

Optimizes synthetic image augmentation for sim2real policy transfer in robotics.

Unified analysis for graph learning from multi-attribute Gaussian time series.

Method constructs finance LLMs without instruction data using pretraining and model merging.

Neural planners for RDDL MDPs produce deep reactive policies in an offline fashion. These scale well with large domains, but are sample inefficient and time-consuming to train from scratch for each new problem. To mitigate this, recent work has studied neural transfer learning, so that a generic planner trained on othe…

Maximum mean discrepancy (MMD), also called energy distance or N-distance in statistics and Hilbert-Schmidt independence criterion (HSIC), specifically distance covariance in statistics, are among the most popular and successful approaches to quantify the difference and independence of random variables, respectively. T…

We present a novel method for learning a set of disentangled reward functions that sum to the original environment reward and are constrained to be independently obtainable. We define independent obtainability in terms of value functions with respect to obtaining one learned reward while pursuing another learned reward…

DIVA learns domain-invariant latent subspaces for domain generalization.

DSRGAN learns independent structure and rendering without tuple supervision.

Dual U-net models improve multi-channel MRI image reconstruction.

The Blaschke rolling disk theorem is extended to non-convex domains.

SCTL scales causal domain adaptation without prior knowledge.

Fitting high-dimensional data involves a delicate tradeoff between faithful representation and the use of sparse models. Too often, sparsity assumptions on the fitted model are too restrictive to provide a faithful representation of the observed data. In this paper, we present a novel framework incorporating sparsity i…

We present a method for translating music across musical instruments, genres, and styles. This method is based on a multi-domain wavenet autoencoder, with a shared encoder and a disentangled latent space that is trained end-to-end on waveforms. Employing a diverse training dataset and large net capacity, the domain-ind…

Proposes a new method for handling domain shift in samples with biases in both covariates and labels.

Aims to eliminate domain bias in authentication without domain labels.

CoNN uses cooperative neural networks to leverage prior independence structure for improved text classification.

New dataset for industrial machine malfunction detection with domain shifts.

New graph embedding method uses domain-specific knowledge.

The paper proposes a method to create domain-invariant representations using Wasserstein distance.

We prove regularity results up to the boundary for time independent generalized Maxwell equations on Riemannian manifolds with boundary using the calculus of alternating differential forms. We discuss homogeneous and inhomogeneous boundary data and show 'polynomially weighted' regularity in exterior domains as well.