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.
U-Nets use belief propagation for efficient image denoising and classification.
The paper reformulates U-Nets as wavelet-based models and applies this to hierarchical VAEs.
Enhances Transformer for hierarchical language understanding.
DS2CF-Net learns hierarchical representations with deep coupled factorization and enriched prior.
HGNet improves GNNs' ability to handle long-range interactions in graphs.
DSCF-Net learns deep features for clustering with robustness and locality preservation.
Oracle inequality for sparse neural nets adapts to unknown structure.
Deep neural networks have proved to be a very effective way to perform classification tasks. They excel when the input data is high dimensional, the relationship between the input and the output is complicated, and the number of labeled training examples is large. But it is hard to explain why a learned network makes a…
We derive generalization and excess risk bounds for neural nets using a family of complexity measures based on a multilevel relative entropy. The bounds are obtained by introducing the notion of generated hierarchical coverings of neural nets and by using the technique of chaining mutual information introduced in Asadi…
EASIER-net uses sparse networks to improve prediction accuracy for high-dimensional data.
This study considers a model of the income distribution of agents whose pairwise interaction is asymmetric and price-invariant. Asymmetric transactions are typical for chain-trading groups who arrange their business such that commodities move from senior to junior partners and money moves in the opposite direction. The…
MPHD transfers knowledge across different domains for Bayesian optimization.
GAMI-Tree uses model-based trees to fit low-order fANOVA models.
Hierarchical Bayesian networks and neural networks with stochastic hidden units are commonly perceived as two separate types of models. We show that either of these types of models can often be transformed into an instance of the other, by switching between centered and differentiable non-centered parameterizations of …
We compare three network portfolio selection methods; hierarchical clustering trees, minimum spanning trees and neighbor-Nets, with random and industry group selection methods on twelve years of data from the 30 Dow Jones Industrial Average stocks from 2001 to 2013 for very small private investor sized portfolios. We f…
The paper develops a new simulation technique for estimating conditional expectations in financial models.
Proposes polynomial neural networks for improved function approximation in various tasks.
Proposes HDBEN for heteroscedastic regression with improved sparsity and variance modeling.
Enhances POU-Nets with probabilistic noise model for efficient spatial data clustering.
HHAR-net uses neural networks to recognize human activities at different levels of abstraction.
Traditional approaches to Bayes net structure learning typically assume little regularity in graph structure other than sparseness. However, in many cases, we expect more systematicity: variables in real-world systems often group into classes that predict the kinds of probabilistic dependencies they participate in. Her…
We consider ill-posed inverse problems where the forward operator is unknown, and instead we have access to training data consisting of functions and their noisy images . This is a practically relevant and challenging problem which current methods are able to solve only under strong assumptions on the t…
The step of expert taxa recognition currently slows down the response time of many bioassessments. Shifting to quicker and cheaper state-of-the-art machine learning approaches is still met with expert scepticism towards the ability and logic of machines. In our study, we investigate both the differences in accuracy and…
SSH-Net: A Deep Neural Network for Predicting Failure Time Distribution Functions under Competing Risks with GPU Data
StaPLR improves Alzheimer's disease classification by identifying important MRI scan types and measures.
STanHop predicts multivariate time series with memory-enhanced capabilities.
Bayesian layer improves image segmentation and out-of-distribution detection.
New algorithms adaptively compete against complex environments with local regularities.
Current popular methods for Magnetic Resonance Fingerprint (MRF) recovery are bottlenecked by the heavy storage and computation requirements of a dictionary-matching (DM) step due to the growing size and complexity of the fingerprint dictionaries in multi-parametric quantitative MRI applications. In this paper we study…
Recently, graph neural networks have been adopted in a wide variety of applications ranging from relational representations to modeling irregular data domains such as point clouds and social graphs. However, the space of graph neural network architectures remains highly fragmented impeding the development of optimized …
ABoB optimizes online configuration tuning by clustering parameters and accelerating learning.
New algorithm trains neural nets on simple skills to learn complex tasks faster.
Sum-Product Networks (SPNs) are hierarchical, graphical models that combine benefits of deep learning and probabilistic modeling. SPNs offer unique advantages to applications demanding exact probabilistic inference over high-dimensional, noisy inputs. Yet, compared to convolutional neural nets, they struggle with captu…
A new recommender system uses slates and Thompson Sampling to improve diversity and click rates.
Generative Adversarial Net (GAN) has been proven to be a powerful machine learning tool in image data analysis and generation. In this paper, we propose to use Conditional Generative Adversarial Net (CGAN) to learn and simulate time series data. The conditions can be both categorical and continuous variables containing…
The vast majority of the neural network literature focuses on predicting point values for a given set of response variables, conditioned on a feature vector. In many cases we need to model the full joint conditional distribution over the response variables rather than simply making point predictions. In this paper, we …
Reducing communication in training large-scale machine learning applications on distributed platform is still a big challenge. To address this issue, we propose a distributed hierarchical averaging stochastic gradient descent (Hier-AVG) algorithm with infrequent global reduction by introducing local reduction. As a gen…
The paper explores discrete isothermic nets using checkerboard patterns in quadrilateral nets.
LIT-LVM improves linear predictors by estimating interaction terms with latent vectors.
We investigate the common underlying discrete structures for various smooth and discrete nets. The main idea is to impose the characteristic properties of the nets not only on elementary quadrilaterals but also on larger parameter rectangles. For discrete planar quadrilateral nets, circular nets, -nets and conical…
In this paper, we introduce transformations of deep rectifier networks, enabling the conversion of deep rectifier networks into shallow rectifier networks. We subsequently prove that any rectifier net of any depth can be represented by a maximum of a number of functions that can be realized by a shallow network with a …
Discretizes special surfaces using Koenigs nets.
We discuss discretization of Koenigs nets (conjugate nets with equal Laplace invariants) and of isothermic surfaces. Our discretization is based on the notion of dual quadrilaterals: two planar quadrilaterals are called dual, if their corresponding sides are parallel, and their non-corresponding diagonals are parallel.…
Classifies nets with area-preserving transformations into two types.
Defines CAMC discrete nets and their properties.
We study local and global approximations of smooth nets of curvature lines and smooth conjugate nets by respective discrete nets (circular nets and planar quadrilateral nets) with infinitesimal quads. It is shown that choosing the points of discrete nets on the smooth surface one can obtain second-order approximation g…
Circular nets with spherical parameter lines have geometric properties related to Darboux cyclides and terminating Laplace sequences.
Smart Close-out Netting aims to automate close-out netting processes.