Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,932 papers · 148 categories

Trend · papers per month

89178266355 · Jun 202019922001200920172026
48 results for domain insights

Gradual domain adaptation improves model transfer between domains with intermediate training.

problem Challenges in unsupervised domain adaptation when distribution shifts are large.
method Gradual self-training using intermediate domains along the Wasserstein geodesic.
result GOAT framework generates intermediate domains for improved adaptation.

Algorithm finds significant sub-interval relationships in time series data.

problem Finding meaningful interactions in small sub-intervals of time series data.
method Fast-optimal guaranteed algorithm for sub-interval relationships (SIR).
result Algorithm identifies SIR relationships that are prominent in specific sub-intervals.

Hybrid framework injects TSLM insights into GRLM for robust time-series reasoning.

problem Lack of domain-specific knowledge in large language models for time-series reasoning.
method Hybrid knowledge-injection framework combining RLVR for efficient knowledge transfer.
result Consistently outperforms existing models by 7.9%-26.1% on multivariate time-series benchmarks.

Optimal transport aligns source and target distributions for linear regression in 2D.

problem Domain adaptation for linear regression in 2D with limited target data.
method Combining K-means and optimal transport for estimating geometric transformations.
result Optimal transport recovers geometric transformations like rotations, translations, and homotheties.

DASH simplifies neural networks for gene regulatory dynamics using domain knowledge.

problem Pruning neural networks for gene regulatory dynamics lacks biologically meaningful structure learning.
method DASH uses domain-specific structural information to guide network pruning, leading to sparser, better interpretable models.
result DASH outperforms general pruning methods in gene regulatory network inference, yielding deeper insights.

Machine learning aids scientific discoveries by explaining complex data.

problem Extracting scientific insights from complex data.
method Combining machine learning with domain knowledge for transparency, interpretability, and explainability.
result Enhanced scientific consistency through machine learning and domain knowledge integration.

The paper studies fundamental domains in H^3 and their associated polyhedra.

problem Understanding the relationship between polyhedra and groups associated with fundamental domains in H^3.
method Analyzes torsion-free groups and edge classes of abstract polyhedra, proving results about group properties and edge classes.
result Classifies fundamental domains on the cube with torsion-free groups and provides insights into polyhedra and groups.

Paper develops upper-bounds for target general loss in multiple source DA and DG settings.

problem Complexity and trade-offs in multiple source domain adaptation and domain generalization.
method Defines two types of domain-invariant representations and studies their pros, cons, and trade-offs.
result Developed upper-bounds for target general loss offer insights into domain-invariant representations.

This paper explores SSL for graph neural networks, improving performance on real-world datasets.

problem Leveraging unlabeled data for graph neural networks to improve deep learning performance.
method Empirical study of various SSL pretext tasks on graphs and proposing a new approach called SelfTask.
result Proposes SelfTask, achieving state-of-the-art performance on real-world datasets.

Deep learning has produced state-of-the-art results for a variety of tasks. While such approaches for supervised learning have performed well, they assume that training and testing data are drawn from the same distribution, which may not always be the case. As a complement to this challenge, single-source unsupervised …

2018-12-06abs ↗pdf ↗

Domain adaptation framework identifies latent variables for target distribution identifiability.

problem Unsupervised domain adaptation without identifiable joint distribution of features and labels.
method Formulated latent variable model with invariant and changing components, constrained domain shift to influence only changing components.
result Joint distribution of data and labels in target domain is identifiable under mild conditions.

Self-training improves gradual domain adaptation with unlabeled data.

problem Improving machine learning models' adaptability to gradually shifting data distributions.
method Proved upper bounds on self-training error, highlighted the importance of regularization and label sharpening, and demonstrated algorithmic insights.
result Self-training works well for gradual shifts, especially with small Wasserstein-infinity distance.

Improves domain adaptation by combining multiple source domains and target domain data.

problem Poor performance of empirical risk minimization in distributionally shifted target domains.
method Distributionally robust model optimizing adversarial reward based on explained variance across multiple source domains.
result The robust model is a weighted average of conditional outcome models from source domains.

Optimal transport aligns rotated linear regression models across domains.

problem Aligning rotated linear regression models across domains with differing statistical properties.
method Combines K-means clustering, OT, and SVD to estimate rotation angle and adapt regression model.
result Optimal transport map recovers underlying rotation in R2\mathbb{R}^2.

New insights into how data transformations affect self-supervised clustering.

problem Impact of data transformations on self-supervised clustering convergence.
method Theoretical and empirical analysis of various data transformations.
result Certain transformations help in faster convergence of self-supervised clustering.

Due to the ability of deep neural nets to learn rich representations, recent advances in unsupervised domain adaptation have focused on learning domain-invariant features that achieve a small error on the source domain. The hope is that the learnt representation, together with the hypothesis learnt from the source doma…

2019-01-27abs ↗pdf ↗

DGSAM improves domain generalization by minimizing individual sharpness.

problem Improving domain generalization models that perform well on unseen target domains.
method Shifts DG paradigm toward minimizing individual sharpness across source domains.
result DGSAM reduces performance variance across domains with less computational overhead.

CICME estimates common and domain-specific causal mechanisms from multi-sensor data.

problem Inferring causal mechanisms from heterogeneous multi-sensor data across multiple domains.
method Three-step approach using Causal Transfer Learning (CTL).
result CICME reliably detects domain-invariant causal mechanisms and guides individual domain causal mechanism estimation.

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 …

2016-10-14abs ↗pdf ↗

The paper explains how data augmentation can improve domain generalization by weakening spurious correlations.

problem Machine learning models trained with observational data fail to generalize to unseen domains due to spurious correlations.
method Developed a causal perspective to explain the success of data augmentation and derived an algorithm to select effective augmentation techniques.
result Data augmentation can be used to simulate interventional data, leading to better domain generalization.

Process mining is a research field focused on the analysis of event data with the aim of extracting insights in processes. Applying process mining techniques on data from smart home environments has the potential to provide valuable insights in (un)healthy habits and to contribute to ambient assisted living solutions. …

2016-09-12abs ↗pdf ↗

FrequentNet uses frequency domain basis vectors for image classification, making models more interpretable and efficient.

problem Image classification models are often complex and hard to interpret.
method FrequentNet selects filter vectors from frequency domain basis vectors instead of training them with back propagation.
result The method improves interpretability and efficiency of image classification models.

New algorithm enhances generative modeling for bounded domains.

problem Ad-hoc thresholding techniques for boundary enforcement in diffusion models.
method Reflected Schrödinger Bridge algorithm for entropy-regularized optimal transport.
result Generative modeling in diverse bounded domains with optimal transport properties.

Benchmark for UDA in time series classification.

problem Lack of benchmarks for unsupervised domain adaptation in time series.
method Introduces a comprehensive benchmark with new datasets and state-of-the-art neural network backbones.
result Insights into strengths and limitations of UDA methods for time series data.

Study finds neural dialog models struggle with conversational tasks.

problem Insufficient understanding of dialog by neural models.
method Analysis of internal representations and evaluation of model performance.
result Neural dialog models lack key conversational skills like answering questions and inferring contradiction.

Proposes a new approach for domain adaptation using latent representations.

problem Handling distribution shifts between source and target domains in high-dimensional data.
method Learn compact latent representations based on the label's Markov blanket, partitioning into parents, children, and spouses.
result General domain adaptation can be achieved by learning representations of the label's parents, children, and spouses.

Proposes a new method for manifold alignment using geometry-regularized twin autoencoders.

problem Traditional MA methods lack out-of-sample extension and real-world applicability.
method Guided representation learning with geometry-regularized twin autoencoders.
result Improves cross-domain generalization and robustness while maintaining alignment fidelity.

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

problem Improving classifier performance on out-of-distribution data by leveraging stable features.
method SFB learns a predictor that separates stable and unstable features, then adapts unstable predictions using stable predictions.
result SFB can learn an asymptotically-optimal predictor without test-domain labels.

Paper proposes a probabilistic alignment method for domain adaptation.

problem Latent distribution mismatch and miscalibrated uncertainty in adapting large-scale models.
method Bayesian latent transport framework with PAC-Bayesian regularization.
result Reduction in latent manifold discrepancy and improved uncertainty calibration.

Unified analysis of generalization and sample complexity for semi-supervised domain adaptation.

problem Theoretical foundations of domain adaptation remain underexplored, especially for modern approaches.
method Unified theoretical study of domain adaptation algorithms based on domain alignment, considering joint learning of feature transformations and shared classifiers in a semi-supervised setting.
result Unified theoretical analysis of domain adaptation algorithms, providing generalization bounds and sample complexity bounds for MMD and adversarial models.

DG algorithms often fail to generalize well in limited domains, highlighting necessary vs. sufficient conditions.

problem DG algorithms fail to consistently outperform ERM in limited domains.
method Examined necessary and sufficient conditions for DG, proposing a subspace alignment method.
result DG methods focus on sufficient conditions, often neglecting necessary conditions, leading to generalization failures.

Study introduces KorFinMTEB for Korean financial texts, revealing model limitations.

problem Limited evaluation benchmarks for low-resource domains, especially Korean.
method Developed KorFinMTEB, a tailored benchmark for Korean financial texts.
result Models perform better on translated benchmarks than on domain-specific ones.

System detects financial misinformation and generates clear explanations.

problem Identifying and explaining fraudulent financial content.
method Combined large language models, pre-processing, and sequential learning.
result Achieved F1-score of 0.8283 for classification and ROUGE-1 of 0.7253 for explanations.

New insights into mirror symmetry via Monge-Ampère domains and pre-Frobenius manifolds.

problem Exploring mirror symmetry using Landau-Ginzburg models and probability densities.
method Investigating Landau-Ginzburg models through Koopman-von Neumann's construction, showing existence of Monge-Ampère domains, and proving mirror pairs via Berglund-Hubsch-Krawitz construction.
result Existence of Monge-Ampère domains and their connection to pre-Frobenius manifolds.

Proposes SGShift to identify shifted features causing model performance degradation under concept shift.

problem Concept shift leading to miscalibration in ML models across domains.
method SGShift method for identifying sparse set of shifted features using feature selection and statistical tools.
result SGShift identifies shifted features more accurately than baseline methods, requires few samples in the shifted domain, and is robust to complex cases.

Proposes a new approach to MSDA by introducing latent covariate shift to handle varying label distributions.

problem Challenges of conventional MSDA approaches in real-world settings where label distributions vary across domains.
method Introduces latent covariate shift (LCS) and a causal generative model with latent noises, latent content variable, and latent style variable.
result Identifies latent content variable up to block identifiability, enabling more nuanced label distribution recovery.