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

2815638441,125 · Jun 202019922001200920172026
48 results for Incomplete Data

New method clusters strong and weak views effectively, improving performance by up to 40%.

problem Clustering incomplete multi-view data with unbalanced incompleteness.
method View evolution scheme and weighted multi-view subspace clustering.
result Improves clustering performance by up to 40% on three metrics.

Develops GNNs for incomplete graphs, improving learning from missing node attributes.

problem Learning from incomplete graphs with missing node attributes.
method Introduces PaGNNs with novel partial aggregation functions for incomplete graph data.
result Demonstrates effectiveness and efficiency of PaGNNs on various datasets.

Variational autoencoders (VAEs), as well as other generative models, have been shown to be efficient and accurate for capturing the latent structure of vast amounts of complex high-dimensional data. However, existing VAEs can still not directly handle data that are heterogenous (mixed continuous and discrete) or incomp…

2018-07-10abs ↗pdf ↗

Beyond existing multi-view clustering, this paper studies a more realistic clustering scenario, referred to as incomplete multi-view clustering, where a number of data instances are missing in certain views. To tackle this problem, we explore spectral perturbation theory. In this work, we show a strong link between per…

2019-05-31abs ↗pdf ↗

A new criterion HBIC improves model selection for factor analysis with missing data.

problem Model selection for factor analysis with incomplete data.
method Proposes a novel criterion HBIC that uses actual observed information in the penalty term.
result HBIC is more accurate than BIC when missing data rates are high.

In 2002, Isenberg-Mazzeo-Pollack (IMP) constructed a series of vacuum initial data sets via a gluing construction. In this paper, we investigate some local geometry of these initial data sets as well as implications regarding their spacetime developments. In particular, we state conditions for the existence of outer tr…

2019-06-29abs ↗pdf ↗

This paper improves learning uncertain Bayesian networks from incomplete data.

problem Learning conditional probabilities in Bayesian networks with limited data.
method Develops methods to estimate and quantify uncertainty in conditional probabilities with incomplete data.
result Improves state-of-the-art approaches for handling uncertain Bayesian networks with incomplete data.

This paper extends the recently proposed and theoretically justified iterative thresholding and KK residual means algorithm ITKrM to learning dicionaries from incomplete/masked training data (ITKrMM). It further adapts the algorithm to the presence of a low rank component in the data and provides a strategy for recove…

2017-01-13abs ↗pdf ↗

MUSIC learns coupled systems with sparse data and incomplete physics.

problem Learning coupled systems with incomplete physical constraints and missing data.
method Sparsity induced multitask neural network framework integrating partial physical constraints with data-driven learning.
result MUSIC accurately learns solutions to complex coupled systems under data-scarce and noisy conditions.

Bayesian approach for handling incomplete clinical data.

problem Challenges in machine learning with multimodal, incomplete clinical data.
method Generative and discriminative learning, semi-supervised strategy, imputation of missing views.
result Automatic imputation of missing views and robust inference across different data sources.

Relational data are usually highly incomplete in practice, which inspires us to leverage side information to improve the performance of community detection and link prediction. This paper presents a Bayesian probabilistic approach that incorporates various kinds of node attributes encoded in binary form in relational m…

2017-06-14abs ↗pdf ↗

MGMC method handles missing data in medical datasets for accurate disease classification.

problem Handling missing data in incomplete medical datasets for accurate disease classification.
method Multigraph Geometric Matrix Completion (MGMC) using multiple graph convolutional networks.
result MGMC achieves superior classification and imputation performance compared to state-of-the-art approaches.

We construct genRBF\bf genRBF kernel, which generalizes the classical Gaussian RBF kernel to the case of incomplete data. We model the uncertainty contained in missing attributes making use of data distribution and associate every point with a conditional probability density function. This allows to embed incomplete data i…

2016-12-05abs ↗pdf ↗

Paper improves ML estimation from incomplete data with robust M-estimator.

problem Estimating parameters from incomplete data with improved accuracy.
method Developed a robust M-estimator and a sandwich estimator for standard errors.
result Improved estimation accuracy with smaller standard errors than ML estimates.

A new method for state estimation in state-space models using incomplete data.

problem State estimation in nonlinear state-space models with incomplete observations.
method Statistical analysis of incomplete observations, score function, observed information matrices, EM-gradient-particle filtering.
result Maximum likelihood estimation of state-vector with explicit form of observed information matrix.

Paper presents a method for estimating long-term PDs with incomplete data.

problem Estimating long-term PDs with limited and incomplete historical data.
method Single risk factor approach for simultaneous calibration of PDs across sub-portfolios.
result Method yields long-term PDs without requiring complete historical data.

Most existing algorithms for dictionary learning assume that all entries of the (high-dimensional) input data are fully observed. However, in several practical applications (such as hyper-spectral imaging or blood glucose monitoring), only an incomplete fraction of the data entries may be available. For incomplete sett…

2018-04-24abs ↗pdf ↗

Paper addresses unsupervised learning from incomplete measurements in inverse problems.

problem Learning from incomplete measurements is challenging in inverse problems.
method Use multiple measurement operators to overcome nullspace issues; propose a novel unsupervised learning loss.
result Presented necessary and sufficient conditions for successful unsupervised learning.

MissNODAG learns cyclic causal graphs from incomplete data.

problem Causal discovery in systems with feedback loops and missing data.
method Differentiable framework integrating additive noise model and expectation-maximization.
result MissNODAG uncovers cyclic structures and missingness mechanisms from partially observed data.

The paper analyzes how wealth affects investment strategies in incomplete markets.

problem Investment strategies in markets with incomplete information.
method Developed a five-component decomposition for optimal portfolio choice, solved explicitly for HARA utility and nonrandom interest rate, and used a stochastic volatility model for US equity data.
result Demonstrated the impacts of wealth-dependent utilities on optimal portfolio allocation, including cycle-dependence and hysteresis effect.

Framework for generating multiple clusterings from multi-view data.

problem Challenges in finding optimal clustering criteria and handling incomplete multi-view data.
method DiMVMC framework that optimizes multiple decoder deep networks to complete data views and generate shared representations.
result DiMVMC outperforms state-of-the-art competitors in generating multiple clusterings with high diversity and quality.

GFA model uncovers brain-behavior associations in incomplete data sets.

problem Incomplete data sets and lack of robust statistical inferences.
method Hierarchical Bayesian model that handles missing data and models modality-specific associations.
result GFA identified four relevant shared factors and predicted non-imaging measures from brain connectivity.