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.

169,051 papers · 148 categories

Trend · papers per month

237473710946 · Jun 202019922001200920182026
48 results for pointer networks

Graph Pointer Networks and hierarchical reinforcement learning solve combinatorial optimization problems like TSP.

problem Traveling Salesman Problem (TSP) with constraints.
method Graph Pointer Networks (GPNs) and hierarchical reinforcement learning.
result GPNs and hierarchical RL find optimal solutions for TSP and TSP with time windows.

PGNs dynamically infer and use graph structures to improve model generalization.

problem Static graph structures inferred by machine learning practitioners are often suboptimal for tasks.
method PGNs augment graphs with dynamically inferred pointers for improved model generalization.
result PGNs outperform unrestricted GNNs and Deep Sets on dynamic graph connectivity tasks.

Paper addresses shortcomings in pointer generator networks for summarization.

problem Extractive summaries and factual inaccuracies in generated text.
method Appends traditional linguistic information to teach networks on text structure.
result Feasibility and potential of additional cues for improved generation.

This study improves text summarization and fake news detection using neural models.

problem Improving text summarization and detecting fake news.
method Exploring and comparing different neural models for text summarization, including LSTM-encoder-decoder, pointer-generator networks, and transformers. Applying these models as a feature extractor for fake news detection.
result The proposed neural models enhance text summarization and improve fake news detection accuracy.

A new method uses machine learning to optimize user pairing and association in multicell NOMA networks.

problem Optimizing user pairing and association in multicell non-orthogonal multiple access (NOMA) systems.
method Formulated as a combinatorial optimization problem, solved using a Pointer Network (PtrNet) trained with deep reinforcement learning.
result Achieves near-optimal performance in terms of aggregate data rate, outperforming random heuristics by up to 30%.

We introduce a new neural architecture to learn the conditional probability of an output sequence with elements that are discrete tokens corresponding to positions in an input sequence. Such problems cannot be trivially addressed by existent approaches such as sequence-to-sequence and Neural Turing Machines, because th…

2015-06-09abs ↗pdf ↗

ADRL improves participant selection in MCS systems.

problem Designing a participant selection algorithm for different MCS systems with multiple goals.
method Auxiliary-task based deep reinforcement learning (ADRL) using transformers and pointer networks.
result ADRL outperforms other baselines in various MCS settings.

Paper proposes continuous residual layers for graph neural networks.

problem Low-pass filtering effect in GCN-based models.
method Integrates Ordinary Differential Equations (ODE) to produce outputs of continuous residual layers.
result Continuous residual layers achieve better results than non-residual modules in multiple layers.

Explains differences between WL and folklore-WL formulations in graph neural networks.

problem Understanding the differences between WL and folklore-WL formulations in graph neural networks.
method Visual explanation of differences between WL and folklore-WL formulations.
result Clarifies the differences between WL and folklore-WL formulations.

Felix Klein's so-called Erlangen Program was published in 1872 as professoral dissertation. It proposed a new solution to the problem how to classify and characterize geometries on the basis of projective geometry and group theory. The given translation was made in 1892 by Dr. M. W. Haskell and transcribed by N. C. Rug…

2008-07-20abs ↗pdf ↗

The recently presented idea to learn heuristics for combinatorial optimization problems is promising as it can save costly development. However, to push this idea towards practical implementation, we need better models and better ways of training. We contribute in both directions: we propose a model based on attention …

2018-03-22abs ↗pdf ↗

The paper explores how neural networks learn logical functions and their generalization error.

problem Learning logical functions with neural networks and understanding generalization error.
method Gradient descent on neural networks, analyzing noise-stability and Boolean influence.
result Gradient descent on certain neural architectures tends to favor low-degree representations, impacting generalization error.

This paper improves keyword recommendation for sponsored search using deep reinforcement learning.

problem Selecting keywords from given candidates considering internal and external competitions.
method Solves the combinatorial optimization problem of keyword recommendations with a modified pointer network structure trained in a deep reinforcement learning framework.
result Remarkable improvements in performance observed both offline and online.

Unsupervised summarization generates novel reviews reflecting consensus opinions.

problem Creating summaries that reflect subjective information in multiple documents.
method Generative model with hierarchical variational autoencoder, pointer-generator mechanism.
result Model produces fluent and coherent summaries reflecting common opinions.

This monograph aims at providing an introduction to key concepts, algorithms, and theoretical results in machine learning. The treatment concentrates on probabilistic models for supervised and unsupervised learning problems. It introduces fundamental concepts and algorithms by building on first principles, while also e…

2017-09-08abs ↗pdf ↗

In recent times, sequence-to-sequence (seq2seq) models have gained a lot of popularity and provide state-of-the-art performance in a wide variety of tasks such as machine translation, headline generation, text summarization, speech to text conversion, and image caption generation. The underlying framework for all these…

2018-05-24abs ↗pdf ↗

This paper reviews state-of-the-art mixed data clustering algorithms.

problem Clustering mixed data is challenging due to the difficulty in applying mathematical operations to feature values.
method Taxonomy and state-of-the-art review of mixed data clustering algorithms.
result Identification of five major research themes and analysis of strengths and weaknesses of methods.

This paper is intended as an introductory survey of a newly emerging field: a topological approach to the study of locally finite graphs that crucially incorporates their ends. Topological arcs and circles, which may pass through ends, assume the role played in finite graphs by paths and cycles. This approach has made …

2009-12-21abs ↗pdf ↗

Blockchain protocol improves traditional mutual funds with performance fees and investor protection.

problem Operational issues and performance fees in traditional mutual funds.
method Developed a blockchain protocol that integrates features of mutual funds and hedge funds.
result Blockchain can simplify performance fee calculations and protect investors.

New models improve morpheme segmentation in low-resource languages.

problem Improving morpheme segmentation in low-resource languages.
method Two new models: LSTM pointer-generator and sequence-to-sequence with hard monotonic attention.
result Novel models outperform existing ones by up to 11.4% accuracy in low-resource settings.

Unified framework for set-valued classification tackles ambiguous multi-class datasets.

problem Ambiguous multi-class datasets in modern statistics.
method Unified statistical framework encompassing various set-valued classification formulations.
result Infinite sample optimal strategies and plug-in principle for data-driven algorithms.

The Frank-Wolfe (FW) optimization algorithm has lately re-gained popularity thanks in particular to its ability to nicely handle the structured constraints appearing in machine learning applications. However, its convergence rate is known to be slow (sublinear) when the solution lies at the boundary. A simple less-know…

2015-11-18abs ↗pdf ↗

Digital risk scores predict depression and anxiety over 10 years.

problem Identifying individuals at risk of depression and anxiety.
method Developed a 10-year predictive algorithm using UKB cohort, selecting predictors via Cox proportional hazards model and DeepSurv.
result Highly discriminating models for depression and anxiety were developed.

Abstract: A comprehensive list of trading strategies and market insights.

problem Understanding trading strategies and market insights for implementation.
method Broad categorization into Delta-One and Derivative strategies based on trading expertise.
result Demonstrates how to cater to diverse market participants' preferences.

The area of online machine learning in big data streams covers algorithms that are (1) distributed and (2) work from data streams with only a limited possibility to store past data. The first requirement mostly concerns software architectures and efficient algorithms. The second one also imposes nontrivial theoretical …

2018-02-16abs ↗pdf ↗

RFN improves GCNs for road networks, outperforming state-of-the-art by 21%-40%.

problem Leveraging the structure of road networks effectively in machine learning tasks.
method Introducing RFN, a novel GCN specifically designed for road networks.
result RFN outperforms state-of-the-art GCNs by 21%-40% on road network tasks.