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.

168,657 papers · 148 categories

Trend · papers per month

150301451601 · Jun 202019922001200920172026
48 results for source space

New method disentangles sources of different timescales in planetary seismic data.

problem Unsupervised source separation of multi-scale seismic data from planetary missions.
method Wavelet scattering spectra for multi-scale clustering and variational autoencoder for source separation.
result Disentangles sources with different timescales in InSight mission seismic data.

Optimizes black-box functions with varying costs across multiple sources.

problem Optimizing black-box functions with varying costs across multiple sources.
method Uses Augmented Gaussian Process and Gaussian Process to model fidelity and location-dependent costs, respectively. Uses Confidence Bound acquisition function to select sources and locations.
result The approach significantly outperforms existing methods on Hyperparameters Optimization tasks.

Proposes a framework to fuse heterogeneous data sources for better modeling.

problem Heterogeneous data sources with different input parameter spaces.
method Input mapping calibration (IMC) and latent variable Gaussian process (LVGP).
result Improved predictive accuracy over single source models.

ESS-Flow guides flow models without retraining, using Bayesian inference in source space.

problem Training flow models on paired data for conditional generation or sample production.
method Gradient-free Bayesian inference in source space using Elliptical Slice Sampling.
result Effective in diverse tasks including material design and protein structure prediction.

The paper establishes new Casorati inequalities for various Riemannian maps and submersions.

problem Developing new inequalities for Riemannian maps and submersions.
method Using general forms of Casorati inequalities, the paper derives inequalities for specific Riemannian spaces.
result The paper provides new Casorati inequalities for Riemannian maps and submersions.

PLRM synthesizes labels from mismatched sources for better training sets.

problem Creating labeled training sets is a major challenge in machine learning.
method PLRM uses probabilistic modeling to synthesize labels from indirect supervision sources with different output spaces.
result PLRM outperforms baselines by 2%-9% on various tasks.

Study characterizes harmful low-fidelity data sources for surrogate models.

problem Identifying which low-fidelity data sources to use in constructing surrogate models.
method Employed benchmark filtering techniques to assess harmful sources using limited data.
result Provided guidelines for using low-fidelity sources in an industrial setting.

Integrates multiple datasets to solve open set crowdsourcing problems.

problem Crowdsourcing with unknown label space and unfamiliar tasks.
method Integrates multiple crowdsourced datasets, weights them based on category correlation, and uses open set transfer learning.
result Proves OSCrowd solves open set crowdsourcing problems and outperforms related solutions.

Deep neural networks suffer from performance decay when there is domain shift between the labeled source domain and unlabeled target domain, which motivates the research on domain adaptation (DA). Conventional DA methods usually assume that the labeled data is sampled from a single source distribution. However, in prac…

2019-11-22abs ↗pdf ↗

StrTransformer recovers sources without labels by optimizing latent matrices and enforcing structural constraints.

problem Unsupervised blind source recovery in signal processing.
method Source-wise structured Transformer framework with latent source matrix optimization, structural regularization, and branch-specific weights.
result StrTransformer learns distinct temporal-scale structures and recovers source-aligned latent trajectories.

Combines foundation models with weak supervision to improve NLP and video tasks.

problem Leveraging weak supervision with foundation models without labeled data.
method Liger, a combination of foundation model embeddings and weak supervision techniques.
result Liger outperforms existing weak supervision methods by 14.1 points on benchmark NLP and video tasks.

This paper proposes a multichannel source separation technique called the multichannel variational autoencoder (MVAE) method, which uses a conditional VAE (CVAE) to model and estimate the power spectrograms of the sources in a mixture. By training the CVAE using the spectrograms of training examples with source-class l…

2018-08-02abs ↗pdf ↗

LEARNER improves low-rank matrix estimation using source population data.

problem Improving low-rank matrix estimation in target populations with diverse data sources.
method LEARNER uses similarity in latent spaces between source and target populations to enhance estimation.
result LEARNER often outperforms benchmark methods, especially with higher signal-to-noise ratios in the source population.

Researchers can retrieve Yang-Mills-Higgs fields from Minkowski space measurements.

problem Retrieving Yang-Mills-Higgs fields from active local measurements in Minkowski space.
method Exploiting non-linear wave interactions and Lie algebra structure.
result Yang-Mills-Higgs fields can be retrieved from source-to-solution data.

StrADiff separates sources from mixtures without labels, using structured priors.

problem Blind source separation of linear and nonlinear mixtures without labeled data.
method Structured Source-Wise Adaptive Diffusion Framework with Gaussian process priors.
result StrADiff can recover latent source trajectories in an unsupervised manner, especially stable in linear mixtures.

This paper studies the problem of Generalized Zero-shot Learning (G-ZSL), whose goal is to classify instances belonging to both seen and unseen classes at the test time. We propose a novel space decomposition method to solve G-ZSL. Some previous models with space decomposition operations only calibrate the confident pr…

2018-10-17abs ↗pdf ↗

The study identifies two sources of invariants in 2--nondegenerate CR geometries.

problem Characterizing fundamental invariants of 2--nondegenerate CR geometries.
method Analyzes the harmonic curvature and the difference in complex structures.
result Nontrivial examples of CR geometries can be obtained as deformations of models.

A new method for separating mixed signals in space and time.

problem Nonlinear and nonstationary spatio-temporal data challenges.
method Identifiable autoregressive variational autoencoder.
result The method outperforms existing techniques in blind source separation and spatio-temporal prediction.

Isolating individual instruments in a musical mixture has a myriad of potential applications, and seems imminently achievable given the levels of performance reached by recent deep learning methods. While most musical source separation techniques learn an independent model for each instrument, we propose using a common…

2018-11-07abs ↗pdf ↗

Prototype extraction framework for domain adaptation.

problem Statistical distance minimization issues in unsupervised domain adaptation.
method Memory and computation-efficient probabilistic framework for class prototype extraction and feature alignment.
result Competitive performance with state-of-the-art methods, no additional model parameters required.

Method transfers knowledge without label overlap, source data, or target architecture consistency.

problem Difficulties in transfer learning due to label mismatch, restricted source data, and specialized target architectures.
method Uses deep generative models in two stages: pseudo pre-training and pseudo semi-supervised learning.
result Outperforms scratch training and knowledge distillation methods.

Study homotopy groups of spaces of long links and knots, finding new generators.

problem Understanding homotopy groups of spaces of long links and knots.
method Graphing map increases dimensions, split injections from homotopy groups of spheres, and analyzing knotting effects.
result Generators for homotopy groups in a new degree for spaces of equidimensional long links.

The paper tackles domain generalization using functional regression.

problem Learning a model that generalizes well across different source distributions.
method Functional regression approach to learn a linear operator between marginal and conditional distributions.
result The proposed algorithm achieves finite sample error bounds for the idealized risk.

Compared with shallow domain adaptation, recent progress in deep domain adaptation has shown that it can achieve higher predictive performance and stronger capacity to tackle structural data (e.g., image and sequential data). The underlying idea of deep domain adaptation is to bridge the gap between source and target d…

2018-11-15abs ↗pdf ↗

Paper tackles entity matching over multi-source data, optimizing alignment and mitigating negative transfer.

problem Learning effective entity matching models over multi-source large-scale data with relaxed assumptions.
method Proposes a Relaxed Multi-source Large-scale Entity-matching (RMLE) problem and Incentive Compatible Pareto Alignment (ICPA) method.
result Optimized cross-source alignments and mitigated negative transfer, improving entity matching accuracy.

A new machine learning method for Bayesian inverse problems in function spaces.

problem Bayesian inverse problems in function spaces with incompatibility of white noise sources.
method One-step generative transport with amortized neural operator and prior-aligned Gaussian random field.
result Generative operator trained on prior samples and noisy observations generates posterior samples efficiently.

Paper tackles open set domain adaptation by detecting unknown classes.

problem Adapting to target domains with unknown classes when label spaces partially overlap.
method Instance-level reweighting strategy combined with Extreme Value Theory for unknown class detection.
result Proposed method outperforms state-of-the-art models on conventional datasets.

Study on reliability of latent reuse in diffusion models under distribution shift.

problem When can latent spaces from a source dataset be reused for a target dataset with different distributions?
method Considered a source-target setting with approximately low-dimensional datasets near different subspaces. Analyzed the target-domain score error due to principal-angle misalignment and target ambient noise.
result Latent reuse is reliable only if the source and target subspaces are close and the target ambient noise is not too amplified.

Unified CLIP space manipulations improve GAN adaptation with a single target image.

problem Overfitting or underfitting in fine-tuning a pre-trained generator with a single target image.
method Two-step training strategy: latent optimization in CLIP space followed by generator fine-tuning with CLIP space consistency loss.
result Our model generates diverse outputs with the target texture and outperforms baseline models.

The paper tackles MSDA by learning dictionary atoms in Wasserstein space.

problem Mitigating data distribution shifts across multiple source domains to target domain.
method Dictionary learning and optimal transport in Wasserstein space; DaDiL algorithm for learning.
result Improved classification performance by 3.15%, 2.29%, and 7.71% in benchmarks.

The paper recasts Penrose-Sparling's non-Hausdorff twistor space using noncommutative geometry.

problem Reinterpreting Penrose-Sparling's non-Hausdorff twistor space.
method Introduces noncommutative geometry techniques to reinterpret the space, using explicit etale gluing groupoid and convolution algebra.
result The source-adapted cyclic pairing recovers the Coulomb charge, demonstrating the effectiveness of the new algebraic model.