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.
Graph neural networks speed up nonnegative matrix factorization.
A method learns matrix factorization from diverse matrices and applies the knowledge to unseen matrices.
Gradient descent proves global convergence for 4-layer matrix factorization.
Modeling dynamic user interests using neural matrix factorization.
Neural NMF discovers hierarchical topics in multilayer data.
New method efficiently learns positive-definite curvature for neural nets.
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…
NeuralIF uses neural networks to improve preconditioning for faster CG convergence.
Paper finds exact Hessian sharpness in deep matrix factorization.
New method compresses neural networks up to 14x with minimal performance loss.
Data often comes in the form of an array or matrix. Matrix factorization techniques attempt to recover missing or corrupted entries by assuming that the matrix can be written as the product of two low-rank matrices. In other words, matrix factorization approximates the entries of the matrix by a simple, fixed function-…
GD and NAG accelerate matrix factorization and neural networks.
Proposes a new model for image restoration combining deep learning and total variation.
New proof shows norms can't explain deep learning's implicit regularization.
Paper explores subdifferential chain rules for matrix factorization and related machine learning models.
Advances neural tri-factorization for clustering and discordance analysis of multi-typed data.
A new method for optimizing deep neural networks using TKFAC.
Nonnegative Boltzmann machines (NNBMs) are recurrent probabilistic neural network models that can describe multi-modal nonnegative data. NNBMs form rectified Gaussian distributions that appear in biological neural network models, positive matrix factorization, nonnegative matrix factorization, and so on. In this paper,…
Paper presents a deep learning method for estimating asset return precision matrices in noisy financial markets.
Revisits neural collaborative filtering vs. matrix factorization, showing dot product superiority.
The paper studies the loss landscape of regularized deep matrix factorization, revealing unique and sharp minimizers.
Efforts to understand the generalization mystery in deep learning have led to the belief that gradient-based optimization induces a form of implicit regularization, a bias towards models of low "complexity." We study the implicit regularization of gradient descent over deep linear neural networks for matrix completion …
The paper analyzes implicit regularization in tensor factorization using neural networks.
The paper explains implicit regularization in hierarchical tensor factorization and deep CNNs.
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…
Deep tensor factorization benefits from implicit regularization with polynomial growth.
New model reduces matrix factorization bias, yielding truly low-rank solutions.
A new method for learning Bayesian neural networks using layerwise inference.
The paper discusses a pooling mechanism to induce subsampling in graph structured data and introduces it as a component of a graph convolutional neural network. The pooling mechanism builds on the Non-Negative Matrix Factorization (NMF) of a matrix representing node adjacency and node similarity as adaptively obtained …
Olshausen and Field (OF) proposed that neural computations in the primary visual cortex (V1) can be partially modeled by sparse dictionary learning. By minimizing the regularized representation error they derived an online algorithm, which learns Gabor-filter receptive fields from a natural image ensemble in agreement …
In this paper, we revisit implicit regularization from the ground up using notions from dynamical systems and invariant subspaces of Morse functions. The key contributions are a new criterion for implicit regularization---a leading contender to explain the generalization power of deep models such as neural networks---a…
Deep learning improves covariance matrix estimation for better portfolio risk management.
Dropout is a simple yet effective algorithm for regularizing neural networks by randomly dropping out units through Bernoulli multiplicative noise, and for some restricted problem classes, such as linear or logistic regression, several theoretical studies have demonstrated the equivalence between dropout and a fully de…
Given a sparse rating matrix and an auxiliary matrix of users or items, how can we accurately predict missing ratings considering different data contexts of entities? Many previous studies proved that utilizing the additional information with rating data is helpful to improve the performance. However, existing methods …
Recently, Neural networks have seen a huge surge in its adoption due to their ability to provide high accuracy on various tasks. On the other hand, the existence of adversarial examples have raised suspicions regarding the generalization capabilities of neural networks. In this work, we focus on the weight matrix learn…
We propose a general theory for studying the \xl{landscape} of nonconvex \xl{optimization} with underlying symmetric structures \tz{for a class of machine learning problems (e.g., low-rank matrix factorization, phase retrieval, and deep linear neural networks)}. In specific, we characterize the locations of stationary …
Deep MF extracts hierarchical features from large data sets.
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…
Study confirms sparse coding in whole brain using MRI data.
New model mimics neural next item recommendation using Hankel matrices.
We develop a method to factorize symmetric sparse Boolean matrices efficiently.
Matrix completion is one of the key problems in signal processing and machine learning, with applications ranging from image pro- cessing and data gathering to classification and recommender sys- tems. Recently, deep neural networks have been proposed as la- tent factor models for matrix completion and have achieved st…
In this paper, we propose a provably correct algorithm for convolutive nonnegative matrix factorization (CNMF) under separability assumptions. CNMF is a convolutive variant of nonnegative matrix factorization (NMF), which functions as an NMF with additional sequential structure. This model is useful in a number of appl…
Cross-Domain Collaborative Filtering (CDCF) provides a way to alleviate data sparsity and cold-start problems present in recommendation systems by exploiting the knowledge from related domains. Existing CDCF models are either based on matrix factorization or deep neural networks. Either of the techniques in isolation m…
Random Feedback Alignment helps solve low-rank matrix factorization problems.
New method for hyperparameter tuning in sparse matrix factorization.
Random matrix theory predicts neural representations generalize well.
Latent factor models (LFMs) such as matrix factorization achieve the state-of-the-art performance among various Collaborative Filtering (CF) approaches for recommendation. Despite the high recommendation accuracy of LFMs, a critical issue to be resolved is the lack of explainability. Extensive efforts have been made in…