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.

168,695 papers · 148 categories

Trend · papers per month

3166319471,262 · Jun 202019922001200920172026
48 results for Neural Factorization Machine

Machine learning factors outperform traditional portfolio optimization methods.

problem Comparing machine learning and traditional portfolio optimization methods.
method Examined machine learning and factor-based portfolio optimization using autoencoder neural networks and dimensionality reduction techniques.
result Minimum-variance portfolios using latent factors derived from autoencoders and sparse methods outperform simpler benchmarks in risk minimization.

Paper explores subdifferential chain rules for matrix factorization and related machine learning models.

problem Clarke subdifferential chain rules for matrix factorization and factorization machines.
method Analyzes conditions for subdifferential chain rules to hold, especially for overparameterized models.
result Subdifferential chain rules hold for matrix factorization and factorization machines under certain conditions.

The study compares different models for predicting factor premiums and finds neural networks perform better but have unstable weights.

problem Predicting and timing the CMA factor premium using machine learning models.
method Compared regression models (OLS, Ridge, Random Forest, Neural Network) and tested factor timing strategies.
result Neural networks outperform linear models in explaining factor premium variance, but weights are unstable.

Deep weight factorization improves neural network training through smooth optimization of sparse penalties.

problem Challenges in applying sparse regularization in neural networks due to non-differentiability of penalties.
method Introduces deep weight factorization, decomposing weights into multiple factors for smooth optimization of L1L_1-penalized networks.
result Deep weight factorization outperforms shallow factorization and pruning methods consistently across various architectures and datasets.

Study proposes a new method for deep portfolio optimization using residual factors.

problem Non-stationary financial market makes traditional machine learning methods ineffective.
method Predict distribution of residual factors using a novel neural network architecture with financial inductive biases.
result Demonstrated improved performance on U.S. and Japanese stock market data.

The paper studies how neural policies can be interpreted using decision trees.

problem Understanding how machine learning controllers make decisions in complex environments.
method The approach involves disentangled representation using decision trees to interpret neural policies.
result The paper shows that disentanglement of learned neural dynamics improves interpretability.

NeuralFactors uses deep learning to improve factor analysis in equity modeling.

problem Enhancing classical factor models for better risk forecasting and portfolio construction.
method Introduces a novel machine-learning approach (NeuralFactors) that outputs factor exposures and returns, trained using variational autoencoders.
result NeuralFactors outperforms prior approaches in log-likelihood performance and computational efficiency.

Neural networks outperform single-hour models in day-ahead electricity price forecasting.

problem Improving accuracy in day-ahead electricity price forecasting.
method Compared two neural network structures: one-hour models and daily auction models.
result Daily auction models outperform one-hour models in forecasting accuracy.

Proposes FEFM and DeepFEFM for CTR prediction, outperforming state-of-the-art models.

problem Click-through rate prediction in online applications.
method Field-Embedded Factorization Machine (FEFM) and its deep counterpart DeepFEFM, combining feature embeddings and deep neural networks.
result FEFM and DeepFEFM outperform existing models in CTR prediction tasks.

Neural network implementation of Brenier's polar factorization for vector fields.

problem Implementing Brenier's polar factorization theorem for vector fields using neural networks.
method Parameterizing the convex function uu as an input convex neural network and estimating the measure-preserving map MM.
result Practical neural implementation of Brenier's polar factorization theorem.

This paper investigates the impact of normalization on deep neural networks for click-through rate prediction.

problem The effect of normalization on deep neural network models for CTR estimation.
method Systematic study of various normalization approaches applied to feature embedding and MLP part of DNN models.
result Correct normalization significantly enhances model performance, as demonstrated by extensive experiments on real-world datasets.

Hardware-accelerated RBM solves large combinatorial problems and integer factorization.

problem Solving large combinatorial optimization and integer factorization problems.
method Logically synthesized RBM architecture, hardware acceleration, and efficient training methods.
result Hardware-accelerated RBM factorizes 16-bit numbers with 10000x speed and 32x power improvements.

FedSplit improves federated learning for heterogeneous data.

problem Data heterogeneity in federated learning degrades convergence and performance.
method FedSplit splits data into shared and personalized groups, optimizing a novel objective function.
result FedSplit converges faster and performs better than standard federated learning.

p3^3VAE combines physics and machine learning for robust data representations.

problem Improving machine learning models' robustness to environmental factors of variation.
method Physics-informed variational autoencoder integrating physical knowledge with neural networks.
result p3^3VAE outperforms competing models in extrapolation and interpretability.

Study evaluates machine learning methods for uncertainty quantification in complex systems.

problem Accurately quantify epistemic and aleatoric uncertainties in complex dynamical systems.
method Examined Gaussian processes, UQ-augmented neural networks (ENN, BNN, D-NN, G-NN) on two model data sets.
result Concluded on model architecture and hyperparameter tuning for improved UQ accuracy.

A neural network method determines the latent dimensionality of NMF.

problem Determining the correct number of hidden features (latent dimensionality) in NMF.
method Combining NMFk with an MLP classifier trained on a dataset of matrices with known latent features.
result The MLP classifier in conjunction with NMFk achieves a greater than 95% success rate in determining the correct number of latent features.

GEM improves recommendation by capturing complex feature interactions.

problem Capturing complex high-order interaction signals in feature-based recommendation models.
method Integrates graph convolution networks to generate high-order embeddings and combines with FM-based models.
result Significant improvement in recommendation performance over baselines.

New neural network solves Nirenberg problem for curvature on sphere.

problem Prescribing Gaussian curvature on S2S^2 for metrics conformal to the round metric.
method Mesh-free physics-informed neural network (PINN) that directly parametrises the conformal factor.
result Neural network achieves very low losses for realisable curvatures, distinguishing them from non-realisable ones.

Factor analysis or sometimes referred to as variable analysis has been extensively used in classification problems for identifying specific factors that are significant to particular classes. This type of analysis has been widely used in application such as customer segmentation, medical research, network traffic, imag…

2019-04-30abs ↗pdf ↗

Matrix factorization is at the heart of many machine learning algorithms, for example, dimensionality reduction (e.g. kernel PCA) or recommender systems relying on collaborative filtering. Understanding a singular value decomposition (SVD) of a matrix as a neural network optimization problem enables us to decompose lar…

2017-02-06abs ↗pdf ↗

New method improves sales forecasting accuracy using tensor factorization.

problem Improving sales forecasting accuracy in retail businesses.
method Advanced Temporal Latent-factor Approach to Sales forecasting (ATLAS) using tensor factorization.
result Accurate and individualized prediction for sales across multiple stores and products.

Graph neural networks speed up nonnegative matrix factorization.

problem Efficiently factorize nonnegative matrices for various applications.
method Developed a graph neural network that combines bipartite self-attention with ADMM updates.
result Significant acceleration achieved in nonnegative matrix factorization.

The paper explores indeterminacy in latent factor projections and its implications for data representation.

problem Indeterminacy in latent factor projections and its implications for data representation.
method Analyzes the fundamental problem of indeterminacy in latent factor projections and discusses its implications for data representation.
result Latent factor determinacy across all facets is achieved when the feature-dimension grows to infinity.

Machine learning models outperform traditional econometric methods for forecasting term structure of government bonds

problem Forecasting the term structure of government bonds
method Combining traditional econometric models with neural network architectures
result Neural network models consistently outperform traditional models in both forecasting accuracy and portfolio performance

Paper uses machine learning to uncover nonlinear dynamics in CAT bond pricing.

problem Traditional linear models miss nonlinear relationships in CAT bond pricing.
method Advanced machine learning techniques applied to CAT bond transaction records.
result Machine learning enhances CAT bond pricing accuracy and reveals complex risk interactions.