arXiv research

Paper presents a Transformer model for automatic domain adaptation.

Transformer models show robustness across domains with domain adversarial training.

Learning multiple tasks across heterogeneous domains is a challenging problem since the feature space may not be the same for different tasks. We assume the data in multiple tasks are generated from a latent common domain via sparse domain transforms and propose a latent probit model (LPM) to jointly learn the domain t…

Proves nonemptyness of domains for specific group actions.

This work improves Fourier pricing for multi-asset options using RQMC with domain transformation.

The characteristics (or numerical patterns) of a feature vector in the transform domain of a perturbation model differ significantly from those of its corresponding feature vector in the input domain. These differences - caused by the perturbation techniques used for the transformation of feature patterns - degrade the…

New method eliminates domain size restrictions for X-ray transform inversion.

Transformers adapted to spherical geometry using space-filling curves.

OLinear forecasts time series more efficiently by transforming data orthogonally.

Extends SW and GSW to compare heterogeneous joint distributions.

This work tackles OOD generalization by leveraging causal invariance without needing to recover causal features.

We introduce a general method of performing Residual Network inference and learning in the JPEG transform domain that allows the network to consume compressed images as input. Our formulation leverages the linearity of the JPEG transform to redefine convolution and batch normalization with a tune-able numerical approxi…

Stability is a key aspect of data analysis. In many applications, the natural notion of stability is geometric, as illustrated for example in computer vision. Scattering transforms construct deep convolutional representations which are certified stable to input deformations. This stability to deformations can be interp…

Transforms game optimization dynamics into frequency domain for precise hyperparameter analysis.

This research studies affine invariance in continuous-domain convolutional neural networks.

TransCORALNet uses transformer and CORAL for supply chain credit assessment with cold start.

Data augmentation is a ubiquitous technique for increasing the size of labeled training sets by leveraging task-specific data transformations that preserve class labels. While it is often easy for domain experts to specify individual transformations, constructing and tuning the more sophisticated compositions typically…

Paper proposes linear transformers for efficient in-context learning without context length limitations.

Images seen during test time are often not from the same distribution as images used for learning. This problem, known as domain shift, occurs when training classifiers from object-centric internet image databases and trying to apply them directly to scene understanding tasks. The consequence is often severe performanc…

Previous research has shown that computation of convolution in the frequency domain provides a significant speedup versus traditional convolution network implementations. However, this performance increase comes at the expense of repeatedly computing the transform and its inverse in order to apply other network operati…

Non-negative blind source separation (non-negative BSS), which is also referred to as non-negative matrix factorization (NMF), is a very active field in domains as different as astrophysics, audio processing or biomedical signal processing. In this context, the efficient retrieval of the sources requires the use of sig…

This study proposes a trainable adaptive window switching (AWS) method and apply it to a deep-neural-network (DNN) for speech enhancement in the modified discrete cosine transform domain. Time-frequency (T-F) mask processing in the short-time Fourier transform (STFT)-domain is a typical speech enhancement method. To re…

A multi-step framework tackles online unsupervised domain adaptation with novel mean-target subspace computation.

Distance metric learning (DML) plays a crucial role in diverse machine learning algorithms and applications. When the labeled information in target domain is limited, transfer metric learning (TML) helps to learn the metric by leveraging the sufficient information from other related domains. Multi-task metric learning …

Theory of packing diabolic domains in liquid crystals.

New method reduces label and data shifts between domains using optimal transport.

URT layer improves few-shot image classification across diverse domains.

The large-N limit of Segal-Bargmann transform on spheres is studied.

Paper studies Transformer learning theory for Euclidean and Riemannian domains.

Transformer-based multi-scale model outperforms traditional methods in solving PDEs on irregular domains.

SIG model identifies invariant variables for MSDA with fewer domain constraints.

Sparse Inverse Covariance Estimation (SICE) is useful in many practical data analyses. Recovering the connectivity, non-connectivity graph of covariates is classified amongst the most important data mining and learning problems. In this paper, we introduce a novel SICE approach using adaptive thresholding. Our method i…

Dataset augmentation, the practice of applying a wide array of domain-specific transformations to synthetically expand a training set, is a standard tool in supervised learning. While effective in tasks such as visual recognition, the set of transformations must be carefully designed, implemented, and tested for every …

CATS adapts multivariate time series models by addressing correlation shift.

A new iterative low complexity algorithm has been presented for computing the Walsh-Hadamard transform (WHT) of an $N$ dimensional signal with a $K$-sparse WHT, where $N$ is a power of two and $K = O(N^α)$, scales sub-linearly in $N$ for some $0 < α< 1$. Assuming a random support model for the non-zero transform domain…

Transformers can learn new tasks from diverse pretraining data but struggle with out-of-domain tasks.

Reconstructing a planar domain from its Dirichlet-to-Neumann data

Transformer architecture struggles with complex tasks due to limitations in function composition.

Scattering transforms are non-trainable deep convolutional architectures that exploit the multi-scale resolution of a wavelet filter bank to obtain an appropriate representation of data. More importantly, they are proven invariant to translations, and stable to perturbations that are close to translations. This stabili…

Proposes a measure to predict generalization in non-matching environments.

CWAN tackles multi-source heterogeneous domain adaptation with conditional weighting.

Survey explores methods to adapt deep learning models across multiple labeled domains.

GWIL uses Gromov-Wasserstein distance to align expert and imitation agent states.

EntProp increases entropy of clean samples to generate out-of-distribution data for better DNN performance.

The theory of slice regular functions of a quaternion variable is applied to the study of orthogonal complex structures on domains Ω of R^4. When Ω is a symmetric slice domain, the twistor transform of such a function is a holomorphic curve in the Klein quadric. The case in which Ω is the complement of a parabola is st…

Symmetry transformations induce invariances which are frequently described with deep latent variable models. In many complex domains, such as the chemical space, invariances can be observed, yet the corresponding symmetry transformation cannot be formulated analytically. We propose to learn the symmetry transformation …

New framework infers causal shifts in event sequences under out-of-domain interventions.

Enhances RL in target domains with limited data using augmented return.