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

25.0%50.0%75.0%100.0% · Sep 199219922001200920172026
48 results for structural models

GraphSTONE uses topic models to capture graph structures, improving GCN performance.

problem GCNs focus too much on node features and not enough on graph structures.
method GraphSTONE employs topic models of graphs to capture structural topics, which guide the aggregation of node features.
result GraphSTONE outperforms GCNs in performance, efficiency, and interpretability.

A general model for geometric structures on differentiable manifolds is obtained by deforming infinitesimal symmetries. Specifically, this model consists of a Lie algebroid, equipped with an affine connection compatible with the Lie algebroid structure. The curvature of this connection vanishes precisely when the struc…

2004-04-17abs ↗pdf ↗

Deep generative models have shown promising results in generating realistic images, but it is still non-trivial to generate images with complicated structures. The main reason is that most of the current generative models fail to explore the structures in the images including spatial layout and semantic relations betwe…

2018-07-10abs ↗pdf ↗

Paper reviews deep structural causal models for answering counterfactual queries.

problem Answering counterfactual queries using observational data with known causal structures.
method Deep generative models integrated with structural causal models.
result Provides insights into the capabilities and limitations of DSCMs.

In many learning tasks, structural models usually lead to better interpretability and higher generalization performance. In recent years, however, the simple structural models such as lasso are frequently proved to be insufficient. Accordingly, there has been a lot of work on "superposition-structured" models where mul…

2015-09-08abs ↗pdf ↗

Paper presents a framework for learning generative models with structured latent factors.

problem Learning controllable and generalizable representations of multivariate data with desired structural properties.
method The paper introduces a novel generative model framework that uses mask variables to model dependency structure and extends the multivariate information bottleneck theory.
result The framework learns semantically meaningful latent factors that reflect various desired structures and can automatically estimate dependency structure from data.

In this article we give an equivariant version for the construction of generic models on presheaves of structures. We deal with first order structures endowed with a suitable action of some fixed group, say GG; we call them GG-structures. We show that every exact presheaf of GG-structures M\mathcal{M} has a generic…

2013-04-09abs ↗pdf ↗

This paper presents a novel method for structural data recognition using a large number of graph models. In general, prevalent methods for structural data recognition have two shortcomings: 1) Only a single model is used to capture structural variation. 2) Naive recognition methods are used, such as the nearest neighbo…

2017-03-08abs ↗pdf ↗

Bayesian method for semi-structured models accounts for both types of uncertainty.

problem Lack of work on epistemic uncertainty in semi-structured regression models.
method Bayesian approximation with subspace inference for joint posterior sampling.
result Validated approach recovers structured effect posteriors and approaches full-space posterior.

Proposes SPCA to incorporate structural constraints in model identification.

problem Model identification with partial structural knowledge.
method Structural Principal Component Analysis (SPCA) that leverages structural information.
result Demonstrates improved model estimates using synthetic and industrial data.

New neural network predicts accurate protein complex structures.

problem Predicting accurate protein complex structures from atomic coordinates.
method Rotation-equivariant neural network combining point-based representation, equivariance, local convolutions, and hierarchical subsampling.
result Significant improvement in identifying accurate structural models.

This paper describes a simple framework for structured sparse recovery based on convex optimization. We show that many structured sparsity models can be naturally represented by linear matrix inequalities on the support of the unknown parameters, where the constraint matrix has a totally unimodular (TU) structure. For …

2014-11-07abs ↗pdf ↗

Language models exhibit low-rank structure, which can be used for generation.

problem Understanding the low-dimensional structure of large language models.
method Empirical demonstration and theoretical analysis of the approximate rank of language models' logits.
result Language models can generate responses using linear combinations of unrelated prompts.

The development of fair machine learning models that effectively avert bias and discrimination is an important problem that has garnered attention in recent years. The necessity of encoding complex relational dependencies among the features and variables for competent predictions require the development of fair, yet ex…

2020-02-21abs ↗pdf ↗

Paper learns latent and hierarchical structures in CDMs from data.

problem Jointly learning latent and hierarchical structures in CDMs from observed data.
method Penalized likelihood approach for selecting attributes and estimating structures; EM and latent structure recovery algorithms.
result Good performance demonstrated by simulation and real data applications.

FOCUS improves offline RL by incorporating causal structure into world-models.

problem Learning effective policies from historical data without interaction.
method FOCUS proposes a practical algorithm that learns and leverages causal structure in offline RL.
result FOCUS outperforms plain model-based offline RL algorithms and other causal model-based RL algorithms.

Multitask learning algorithms are typically designed assuming some fixed, a priori known latent structure shared by all the tasks. However, it is usually unclear what type of latent task structure is the most appropriate for a given multitask learning problem. Ideally, the "right" latent task structure should be learne…

2012-06-27abs ↗pdf ↗

Paper introduces a core-periphery model for identifying informative network structures.

problem Noise and bias in non-informative periphery structures obscure the informative core in complex networks.
method Spectral algorithms for core identification as a preprocessing step for network analysis.
result The proposed method outperforms traditional core-periphery methods in various downstream tasks.

Paper formalizes a reinforcement learning model for complex information structures.

problem Complex interdependence in sequential decision-making problems.
method Formalizes a novel reinforcement learning model with explicit information structure representation.
result Upper bound on sample complexity of learning general sequential decision-making problems.

A new method learns causal structure from data using amortized inference.

problem Causal structure learning is a combinatorial search problem that is costly and difficult to design suitable scores or tests.
method Train a variational inference model to predict causal structure from data.
result Our inference model generalizes well to larger problem instances and outperforms existing algorithms, especially in genomics.

Proposes a new model for testing causal structural priors and synthesizing data.

problem Testing and synthesizing causal structural priors using nonparametric knowledge and neural networks.
method Causal Structural Hypothesis Testing (C-SHT) and Causal Structural Variational Hypothesis Testing (C-SVHT) using deep neural networks.
result Demonstrates out-of-distribution generalization error as a proxy for causal structural prior hypothesis testing.

A structured understanding of our world in terms of objects, relations, and hierarchies is an important component of human cognition. Learning such a structured world model from raw sensory data remains a challenge. As a step towards this goal, we introduce Contrastively-trained Structured World Models (C-SWMs). C-SWMs…

2019-11-27abs ↗pdf ↗

Smooth structures on diffeological spaces and sheaves, resolving conjectures.

problem Model structures on diffeological spaces and sheaves of sets.
method Embedding diffeological spaces into sheaves of sets, studying combinatorial model structures, and proving equivalence to simplicial sets.
result Established a model structure on sheaves of sets that is Quillen equivalent to simplicial sets and has properties like cartesian and cofibrant smooth manifolds.

A novel federated learning framework resolves structural misalignment in model fusion.

problem Structural misalignment in model fusion due to chaotic information distribution.
method Feature-oriented regulation method (ΨΨ-Net) to ensure feature information allocation and dedicated collaboration schemes.
result Effective enhancement of federated learning applicability to heterogeneous settings with improved convergence speed, accuracy, and efficiency.

We consider the problem of learning the structure of a pairwise graphical model over continuous and discrete variables. We present a new pairwise model for graphical models with both continuous and discrete variables that is amenable to structure learning. In previous work, authors have considered structure learning of…

2012-05-22abs ↗pdf ↗

We propose a dynamic model of dependence structure between financial institutions within a financial system and we construct measures for dependence and financial instability. Employing Markov structures of joint credit migrations, our model allows for contagious simultaneous jumps in credit ratings and provides flexib…

2018-09-10abs ↗pdf ↗

Generative model predicts remaining life of damaged structures.

problem Prognosis of damage and remaining useful life of structures.
method Generative adversarial networks (GANs) in a population-based SHM framework.
result Algorithm provides confident predictions about structures' remaining useful life.

Study analyzes correlation structure in two-factor Hull-White model for XVA calculations.

problem Capturing the correlation structure in two-factor Hull-White model for accurate XVA calculations.
method Combination of approximation formula and Monte-Carlo simulation to investigate correlation structure.
result Hull-White model effectively captures de-correlation of the yield curve under specific parameter conditions.

New benchmarks for RNA 3D structure-function modeling.

problem Lack of standardized benchmarks for RNA deep learning.
method Developed seven benchmark datasets, provided tools for data handling, and offered a user-friendly environment for model comparison.
result Demonstrated utility with baseline results using a relational graph neural network.

Log-linear models are a family of probability distributions which capture relationships between variables. They have been proven useful in a wide variety of fields such as epidemiology, economics and sociology. The interest in using these models is that they are able to capture context-specific independencies, relation…

2019-07-21abs ↗pdf ↗