Paper proposes NNAFC for automatic financial factor construction.
problem Manual factor construction is time-consuming and prone to bias.
method NNAFC uses neural networks to automatically construct diversified financial factors.
result NNAFC outperforms GP in constructing more informative and diversified factors.
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.
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 L1-penalized networks. result Deep weight factorization outperforms shallow factorization and pruning methods consistently across various architectures and datasets.
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.
Bayesian inference improves neural network pruning efficiency.
problem Reducing computational and memory demands of large neural networks.
method Utilizes Bayesian inference to calculate Bayes factors for iterative pruning.
result Achieves desired levels of sparsity while maintaining competitive accuracy.
Paper compares neural networks and classical statistics for dementia prediction, highlighting interpretability of classical methods.
problem Tackles the challenge of interpreting risk factors for dementia prediction.
method Compares neural networks and classical statistics for dementia prediction.
result Classical statistics provide clearer interpretation of risk factors compared to neural networks.
Causal deep learning tackles causal inference using tensor factor analysis.
problem Addressing causal questions in data using neural networks.
method Tensor factor analysis and neural network architectures (causal capsules, tensor transformer, multilinear projection algorithm).
result Derives deep neural networks for causal inference with tensor factor analysis.
SPIDER uses deep neural networks for streaming tensor factorization.
problem Lack of effective approach for deep tensor factorization of streaming data.
method Bayesian neural networks with spike-and-slab prior, Taylor expansions, moment matching, and EPI framework.
result Effective incremental updates for latent factors and NN weights.
Deep neural networks decompose SDF into linear and nonlinear components.
problem Constructing accurate stochastic discount factors (SDFs) for pricing.
method Additive decomposition of a deep neural network trained to construct SDFs.
result The PTK representation delivers significant performance gains in equity data.
Proposes FATTNN for tensor-on-tensor regression with improved prediction and reduced computation.
problem Tensor-on-tensor regression with complex tensor structures and nonlinear relationships.
method Integrates tensor factor models into deep neural networks to handle nonlinearity and reduce data dimensionality.
result Significant improvements in prediction accuracy and computational efficiency over traditional methods.
Neural NMF discovers hierarchical topics in multilayer data.
problem Detecting latent hierarchical structure in multilayer data.
method Recursive application of nonnegative matrix factorization (NMF) in layers with backpropagation optimization.
result Neural NMF outperforms other hierarchical NMF methods in synthetic and real-world datasets.
The paper analyzes implicit regularization in tensor factorization using neural networks.
problem Understanding implicit regularization in tensor factorization.
method Dynamical systems perspective and gradient descent analysis.
result Gradient descent induces a form of greedy low tensor rank search.
A Bayesian nonparametric approach for continual learning using neural networks.
problem Catastrophic forgetting in neural networks during sequential task settings.
method Indian Buffet Process (IBP) prior for dynamic model expansion and factorization of weight matrices.
result The method promotes positive knowledge transfer between tasks and allows for dynamic model complexity.
Quantization of neural networks has become common practice, driven by the need for efficient implementations of deep neural networks on embedded devices. In this paper, we exploit an oft-overlooked degree of freedom in most networks - for a given layer, individual output channels can be scaled by any factor provided th…
A neural network model tackles high-dimensional data with latent structures.
problem Modeling high-dimensional data with latent low-dimensional structures.
method Integrates PCA and Soft PCA layers into neural network architecture for factor modeling and non-linear transformations.
result Demonstrates improved performance in forecasting and nowcasting with real-world data.
The paper explains implicit regularization in hierarchical tensor factorization and deep CNNs.
problem Understanding implicit regularization in complex neural network architectures.
method Theoretical analysis using dynamical systems to overcome challenges in hierarchy.
result Established implicit regularization towards low hierarchical tensor rank, equivalent to locality in CNNs.
GRU-PFG model extracts inter-stock correlations from stock factors using graph neural networks.
problem Limited effectiveness of models relying solely on stock factors for capturing stock correlations.
method Project stock factors into a graph and use graph neural networks to extract inter-stock correlations.
result Achieves better prediction results than models relying solely on stock factors and comparable to second category models.
DF2M uses deep neural networks within a factor model for high-dimensional functional time series forecasting.
problem Forecasting high-dimensional functional time series with explainability and accuracy.
method Bayesian nonparametric model based on Indian Buffet Process and multi-task Gaussian Process, incorporating a deep kernel function.
result DF2M provides better explainability and superior predictive accuracy compared to conventional deep learning models.
We consider the probabilistic analogue to neural network matrix factorization (Dziugaite & Roy, 2015), which we construct with Bayesian neural networks and fit with variational inference. We find that a linear model fit with variational inference can attain equivalent predictive performance to the regular neural networ…
A method learns matrix factorization from diverse matrices and applies the knowledge to unseen matrices.
problem Matrix factorization without shared rows or columns.
method Neural network meta-learned to minimize expected imputation error using MAP estimation.
result The method can impute missing values from unseen matrices efficiently.
MoNODEs improve neural ODEs by separating dynamic states from static factors.
problem Learning non-linear dynamics with variations across trajectories.
method Introduces time-invariant modulator variables to separate dynamic states from static factors.
result Consistently improves model generalization and far-horizon forecasting.
Modeling dynamic user interests using neural matrix factorization.
problem Challenging extraction of valuable insights from unstructured, high-dimensional, and dynamic online content data.
method Combines matrix factorization with neural networks to model nonlinear user and content factors.
result Accurately identifies nuanced and coherent consumption patterns of Boston Globe readers over five years.
Ricean channel model is widely used in wireless communications to characterize the channels with a line-of-sight path. The Ricean K factor, defined as the ratio of direct path and scattered paths, provides a good indication of the link quality. Most existing works estimate K factor based on either maximum-likelihood cr…
Deep neural network learns meaningful factors to predict stock returns.
problem Predicting excess returns of assets like Tesla stock.
method 5-layer deep neural network with gated activation layer to filter noise.
result Proposed model outperforms in predicting stock returns over 2,000 stocks.
SG-NTF completes HDI tensors with spectral mapping and spatio-temporal gating.
problem High-dimensional and incomplete tensor completion.
method Spectra-Guided Neural Tucker Factorization (SG-NTF) with Spatio-Temporal Co-Gating (STCG).
result Maintains competitive completion accuracy with parameter efficiency.
New method compresses neural networks up to 14x with minimal performance loss.
problem Compressing neural networks for real-time applications.
method Post-training rank-selection method called Rank-Tuning.
result High compression rates with minimal performance degradation.
NCPF model improves traffic data imputation with neural and tensor methods.
problem Pervasive missing data in traffic analysis due to sensor failures and gaps.
method Neural Canonical Polyadic Factorization (NCPF) integrating CP decomposition and deep learning.
result NCPF outperforms state-of-the-art baselines in urban traffic datasets.
Improved error correction using neural networks and belief propagation.
problem Inference in factor graphs with loops or poor approximations.
method Hybrid model combining FG-GNN and belief propagation.
result Hybrid model outperforms belief propagation in error correction 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 u as an input convex neural network and estimating the measure-preserving map M. result Practical neural implementation of Brenier's polar factorization theorem.
Traditional recommendation systems rely on past usage data in order to generate new recommendations. Those approaches fail to generate sensible recommendations for new users and items into the system due to missing information about their past interactions. In this paper, we propose a solution for successfully addressi…
NeuralIF uses neural networks to improve preconditioning for faster CG convergence.
problem Improving convergence of conjugate gradient method for large-scale sparse systems.
method Data-driven approach using graph neural networks to generate incomplete factorization.
result Data-driven preconditioners accelerate convergence of conjugate gradient method.
Learned factor graphs improve inference from time sequences using neural networks.
problem Inference from time sequences with limited labeled data.
method Combines model-based algorithms and data-driven ML tools for stationary time sequences.
result Learned factor graphs can accurately infer from small training sets.
Dual model predicts electricity spot prices using neural networks and wavelets.
problem Forecasting hourly electricity spot prices.
method Dual generalized long memory modelling with k-factor GARMA and G-GARCH models, using LLWNN and PSO for variance prediction.
result The hybrid k-factor GARMA-LLWNN model outperforms other methods in forecasting accuracy.
A new method for optimizing deep neural networks using TKFAC.
problem Optimizing deep neural networks with second-order methods.
method Proposes Trace-restricted Kronecker-factored Approximate Curvature (TKFAC) for Fisher information matrix approximation.
result TKFAC improves performance on deep network architectures compared to state-of-the-art algorithms.
The paper uses neural networks to price complex life insurance contracts with multiple risk factors.
problem Pricing equity-linked life insurance contracts with various stochastic risk factors.
method Assuming hedging to reduce local variance, the price is expressed as a system of non-linear PDEs. Reformulated as a backward SDE with jumps, solved numerically using neural networks.
result Neural networks provide an efficient numerical solution for pricing these complex contracts.
In this paper, we measure systematic risk with a new nonparametric factor model, the neural network factor model. The suitable factors for systematic risk can be naturally found by inserting daily returns on a wide range of assets into the bottleneck network. The network-based model does not stick to a probabilistic st…
Despite their increasing popularity and success in a variety of supervised learning problems, deep neural networks are extremely hard to interpret and debug: Given and already trained Deep Neural Net, and a set of test inputs, how can we gain insight into how those inputs interact with different layers of the neural ne…
Regularization is essential when training large neural networks. As deep neural networks can be mathematically interpreted as universal function approximators, they are effective at memorizing sampling noise in the training data. This results in poor generalization to unseen data. Therefore, it is no surprise that a ne…
EPFGNN models graph connections for better node classification.
problem Graph node classification issues due to feature aggregation.
method EPFGNN models graph as a Markov Random Field with explicit pairwise factors and a GNN backbone.
result EPFGNN improves semi-supervised node classification performance.
Tackling pattern recognition problems in areas such as computer vision, bioinformatics, speech or text recognition is often done best by taking into account task-specific statistical relations between output variables. In structured prediction, this internal structure is used to predict multiple outputs simultaneously,…
Most of the successful deep neural network architectures are structured, often consisting of elements like convolutional neural networks and gated recurrent neural networks. Recently, graph neural networks have been successfully applied to graph structured data such as point cloud and molecular data. These networks oft…
Unintended effects from scaling neural network outputs with adaptive learning rates.
problem Adaptive learning rate optimization's behavior is altered by output scaling, leading to misinterpretation.
method Presented a modified optimization algorithm to mitigate unintended effects.
result Adaptive learning rate's effectiveness is significantly impacted by output scaling, especially for small scaling factors.
The proliferation of healthcare data has brought the opportunities of applying data-driven approaches, such as machine learning methods, to assist diagnosis. Recently, many deep learning methods have been shown with impressive successes in predicting disease status with raw input data. However, the "black-box" nature o…
Techniques involving factorization are found in a wide range of applications and have enjoyed significant empirical success in many fields. However, common to a vast majority of these problems is the significant disadvantage that the associated optimization problems are typically non-convex due to a multilinear form or…
Shape adaptor learns flexible resizing factors for neural networks.
problem Fixed resizing layers limit network performance.
method Learnable reshaping factor for traditional resizing layers.
result Performance increases consistently across multiple datasets.
Advances neural tri-factorization for clustering and discordance analysis of multi-typed data.
problem Challenges in analyzing heterogeneous, multimodal relational data.
method Deep collective matrix tri-factorization for spectral clustering and cluster association learning.
result Demonstrates efficacy over previous non-neural approaches in clustering and discordance analysis.
We explore how neural networks train to zero loss, focusing on initial scale.
problem Understanding neural network training dynamics and zero loss.
method Macroscopic limits analysis of gradient descent dynamics.
result Gradient descent can drive deep neural networks to zero loss regardless of initialization.
Compact parameterization improves Bayesian neural network performance.
problem Improving performance of Bayesian neural networks using variational methods.
method Restricting variational distribution to a k-tied Normal distribution with low-rank factorization.
result Compact parameterization improves signal-to-noise ratio and convergence speed.