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.

168,742 papers · 148 categories

Trend · papers per month

3987961,1941,592 · Jun 202019922001200920172026
48 results for direct learning

Local causal structure learning aims to discover and distinguish direct causes (parents) and direct effects (children) of a variable of interest from data. While emerging successes have been made, existing methods need to search a large space to distinguish direct causes from direct effects of a target variable \emph{T…

2019-10-03abs ↗pdf ↗

Proposes a novel approach using vector cross product to preserve directional edges in directed graphs.

problem Preserving directional edges in directed graphs for tasks like link prediction and node recommendation.
method Integrates the non-commutative property of vector cross product into a Siamese neural network to learn N-dimensional embeddings.
result Low-dimensional embeddings effectively preserve directional properties and outperform state-of-the-art methods.

Stochastic Gradient Descent shows directional bias with moderate learning rates, impacting optimization outcomes.

problem Understanding the bias of SGD with moderate learning rates in practical scenarios.
method Analyzing SGD and GD on an overparameterized linear regression problem.
result SGD converges along large eigenvalue directions, GD along small ones, affecting early stopping outcomes.

The paper studies kernel smoothing and mean shift for directional data, deriving convergence rates and mode estimation.

problem Statistical and computational problems of kernel smoothing for directional data.
method Generalization of mean shift to directional data, derivation of convergence rates, and investigation of mode estimation.
result Statistical convergence rates of directional KDE and its derivatives, ascending property of directional mean shift, and mode estimation.

Detects adversarial directions to make reinforcement learning policies more robust.

problem Adversarial attacks exploit non-robust directions in reinforcement learning policies, leading to instability.
method Local quadratic approximation of deep neural policy loss to identify non-robust directions.
result Provides a theoretical basis for distinguishing safe from adversarial observations.

Minimalistic model captures head direction system properties.

problem Representing head direction system in a high-dimensional space.
method A minimalistic representation model of the rotation group U(1), including fully connected and convolutional versions.
result Emergence of Gaussian-like tuning profiles and 2D circle geometry in both model versions.

The paper addresses challenges in edge deep learning for IoT, proposing new directions.

problem Challenges in large-scale deep learning adoption for IoT devices.
method Unified view targeting three research directions: federated learning, data-independent deployment, and communication-aware inference.
result A network-centric approach is needed for edge intelligence.

Study uses deep learning to predict asset prices, finds complex target processes lead to meaningless predictions.

problem Complexity of successful price prediction models hinders understanding.
method Deep learning models for high-frequency price prediction, focusing on volatility and directional prediction.
result Inadequately defined target price process renders predictions meaningless.

Machine learning models predict EUR/USD currency direction with 58.52% accuracy.

problem Predicting the directional movement of EUR/USD in the Foreign Exchange market.
method Comparative analysis of machine learning models, including decorrelated and non-decorrelated feature sets, and meta-estimators.
result 58.52% accuracy for one-day ahead forecasts.

Proposes new stochastic algorithms for multi-objective optimization.

problem Multi-objective optimization in machine learning problems.
method Direction-oriented multi-objective formulation and Stochastic Direction-oriented Multi-objective Gradient descent (SDMGrad).
result Stochastic algorithms converge to Pareto stationary points with improved complexities.

TSAM predicts directed temporal links using GCN and self-attention.

problem Predicting links in directed temporal networks.
method GCN, self-attention mechanism, autoencoder architecture, graph attentional layers, graph convolutional layers, graph recurrent unit layer.
result TSAM outperforms benchmarks on four realistic networks.

Autoencoders are a deep learning model for representation learning. When trained to minimize the distance between the data and its reconstruction, linear autoencoders (LAEs) learn the subspace spanned by the top principal directions but cannot learn the principal directions themselves. In this paper, we prove that $L_2…

2019-01-23abs ↗pdf ↗

A new method learns node embeddings for signed directed networks by capturing both first-order and high-order topologies.

problem Learning representative node embeddings for signed directed networks considering both first-order and high-order topologies.
method Proposes a decoupled variational embedding (DVE) method that leverages a specially designed auto-encoder structure to capture both first-order and high-order topologies.
result Extensive experiments on real-world datasets show the effectiveness of DVE in link sign prediction and node recommendation tasks.

Efficient algorithm for self-directed learning of convex clusters on graphs.

problem Self-directed classification of nodes on graphs with convex clusters.
method Developed efficient algorithms for (geodesically) convex clusters on graphs.
result Polynomial runtime algorithm with 3(h(G)+1)4lnn3(h(G)+1)^4 \ln n mistakes for graphs with two convex clusters.

Novel Haar-Laplacian for directed graphs enhances spectral graph applications.

problem Lack of suitable Laplacian for directed graphs in spectral graph theory.
method Inspired by Haar-like transformation, introduces a Hermitian matrix preserving direction and weight.
result HaarNet outperforms in weight prediction and denoising on directed graphs.

Direct Feedback Alignment performs well on diverse deep learning tasks and architectures.

problem The limitations of backpropagation in parallelizing and scaling to modern deep learning tasks.
method Direct Feedback Alignment approach applied to neural view synthesis, recommender systems, geometric learning, and natural language processing.
result Direct Feedback Alignment successfully trains a wide range of state-of-the-art deep learning architectures with performance close to fine-tuned backpropagation.

We propose a method to learn causal response representations through direct effect analysis.

problem Uncovering direct causal effects in complex, multivariate settings.
method Our method bridges conditional independence testing with causal representation learning, formulating an optimisation problem to maximise evidence against conditional independence.
result The largest eigenvalue distribution can be bounded by an FF-distribution, providing testable conditional independence.

Improved SSD for faster and more accurate goodness-of-fit tests and model learning.

problem Optimal slicing directions for SSD are computationally expensive and sub-optimal.
method Relaxed optimal slicing requirement, active sub-space construction, spectral decomposition.
result 14-80x speed-up in goodness-of-fit tests compared to gradient-based alternatives.

Study reveals how neural network architectures bias their learning based on feature directions.

problem Understanding how neural network architectures bias their learning based on feature directions.
method Defined neural anisotropy directions (NADs) to encapsulate the directional inductive bias of architectures and provided an efficient method to identify them.
result NADs characterize the features used by CNNs to discriminate between different classes for the CIFAR-10 dataset.

TQF models multivariate uncertainty by learning conditional quantiles.

problem Challenges in fully nonparametric estimation of multivariate conditional distributions.
method Tomographic Quantile Forests (TQF) learns conditional quantiles of directional projections.
result TQF reconstructs multivariate conditional distribution efficiently without convexity restrictions.

REGAIN learns optimal auxiliary directions for forecast reconciliation.

problem Forecast reconciliation from fixed systems; identifying useful auxiliary directions.
method REGAIN learns normalized auxiliary directions, forecasts induced series, and selects directions by loss reduction.
result Gain-selected auxiliary directions improve forecast quality, especially for residual uncertainty.

Study evaluates and compares traditional and causal machine learning methods for estimating direct price effects of environmental amenities.

problem Estimating direct price effects of environmental amenities in housing markets.
method Empirical Monte Carlo simulation to compare traditional regression and causal machine learning approaches.
result Causal Machine Learning (CML) methods, particularly causal forest DID, perform comparably to generalized DID in most scenarios.

Estimates causal effects using machine learning for binary treatment and mediator.

problem Estimating direct and indirect quantile treatment effects under selection-on-observables.
method Double/debiased machine learning estimators based on efficient score functions.
result Uniform consistency and asymptotic normality of effect estimators.

Unsupervised method discovers interpretable directions in GAN latent space.

problem Discovering interpretable directions in GAN latent space without supervision.
method Model-agnostic procedure to identify directions corresponding to semantic manipulations.
result Findings include directions for background removal and competitive saliency detection performance.

Machine learning predicts critical points for directed percolation models.

problem Determining critical points for directed percolation models.
method Supervised and unsupervised machine learning algorithms (CNN and DBSCAN) were used.
result Machine learning accurately predicts critical points for both models.

We identify direct causes of a target variable from observational data without full DAG identifiability.

problem Learning direct causes of a target variable from observational data.
method Developed algorithms under relaxed identifiability assumptions for one environment without interventions.
result Identifiable set of direct causes from observational data under specific assumptions.

PyTorch Geometric Signed Directed fills the gap for GNNs on signed and directed graphs.

problem Lack of unified software packages for GNNs on signed and directed networks.
method Developed a software package with GNN models, synthetic and real-world data, and evaluation metrics.
result Demonstrates the effectiveness of the implemented methods through experiments.

This work improves structured prediction by learning the balance between signal and random noise.

problem Structured prediction with random perturbations.
method Learning the variance of randomized structured predictors to balance signal and noise.
result Learning the balance improves structured prediction effectiveness.