Improves inference from sparse data with hybrid summary statistics.
problem Robust simulation-based inference from limited data.
method Augment traditional summary statistics with neural network outputs to maximize mutual information.
result Improves information extraction and makes inference robust in low-data settings.
Enhances weak lensing inference with neural summaries.
problem Extracting additional information from weak lensing convergence maps.
method Hybrid approach combining physics-based and neural summaries.
result Neural summaries extract up to 8 times more information than angular power spectra.
Paper explores models for summarizing AI agent policies.
problem Improving human understanding of AI agent behavior.
method Imitation learning-based approach to policy summarization.
result Matching summary extraction model to user model improves performance.
Corrects bias in Cox models using AI-extracted covariates.
problem Bias in Cox regression models due to AI-extracted covariates.
method Unified multivariate calibration framework to decompose and correct bias.
result Corrected Cox estimator reduces bias and achieves near-nominal coverage.
Paper introduces methods to automatically generate SOAP notes from patient-physician conversations.
problem Burden of creating digital SOAP notes by physicians.
method Cluster2Sent algorithm for summarizing patient-physician conversations.
result Cluster2Sent algorithm outperforms existing methods by 8 ROUGE-1 points.
Automates summarizing federal grant audits with machine learning.
problem Manual analysis of large federal grant audits is time-consuming and error-prone.
method Sentence clustering, k-means, proximity to centroids, human input for refinement.
result Automated summaries are comparable to human-generated ones using ROUGE metric.
BERT helps summarize lecture content efficiently.
problem Efficiently summarize lecture content for students.
method Used BERT for text embeddings and KMeans clustering.
result Improved text summarization for lecture content.
Few summaries enable automatic summarization of product reviews.
problem Lack of large labeled datasets for training supervised models in opinion summarization.
method Conditional Transformer model trained to generate summaries given other reviews, fine-tuned to predict summary properties.
result Few summaries (5-10) are sufficient to generate fluent, informative, and sentiment-preserving summaries.
The paper tackles robust submodular maximization under matroid constraints, providing approximation algorithms for summary extraction.
problem Maximizing submodular functions while ensuring high value even after deletions.
method Constant-factor approximation algorithms for centralized and streaming settings, considering both non-monotone and monotone objectives.
result Approximation algorithms with space complexity depending on matroid rank and deleted elements, achieving improved factors in monotone cases.
A new method uses PSO to optimize sentence weights for user-oriented document summaries.
problem Handling information overload in documents through efficient summarization.
method Particle Swarm Optimization (PSO) to identify and weight sentence features.
result Improved accuracy in summarization compared to previous methods.
Unified approach for selecting summary statistics in ABC.
problem Efficient inference from large datasets in likelihood-free methods.
method Characterizing and unifying three classes of summary statistics, minimizing expected posterior entropy.
result EPE-minimizing summaries lead to competitive posterior inference.
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.
Feature extraction has gained increasing attention in the field of machine learning, as in order to detect patterns, extract information, or predict future observations from big data, the urge of informative features is crucial. The process of extracting features is highly linked to dimensionality reduction as it impli…
Neural model extracts tokens as latent variables for text compression.
problem Compressing text using neural models.
method Extracting tokens with highest tf-idf scores or highest loss from a bidirectional language model.
result Extracting tokens as latent variables significantly outperforms state-of-the-art methods.
The paper extracts structured data from physician-patient conversations, reducing clerical burden.
problem Mining insights from physician-patient conversations for electronic health record documentation.
method Created a dataset of transcripts and summaries, extracted noteworthy utterances, and improved model performance.
result Extracting noteworthy utterances significantly boosts model performance for recognizing diagnoses and RoS abnormalities.
SummaryNet automates video summarisation using deep learning.
problem Creating informative video summaries from videos.
method Two-stream convolutional network for spatial and temporal features, encoder-decoder model for salient features, sigmoid regression with LSTM for frame probability.
result SummaryNet achieves comparable or better results than state-of-the-art methods on benchmark datasets.
Detecting PE malware files is now commonly approached using statistical and machine learning models. While these models commonly use features extracted from the structure of PE files, we propose that icons from these files can also help better predict malware. We propose an innovative machine learning approach to extra…
Model creates summaries of patient notes to save time and reduce errors.
problem Improper summarization of patient notes leads to inefficiencies and errors.
method Developed an LSTM model to sequentially label topics in history of present illness notes.
result Achieved an F1 score of 0.876, indicating the model's effectiveness.
The paper develops algorithms to find a robust summary of data under deletion, achieving good approximation guarantees.
problem Finding a summary of data that remains valuable even after some elements are deleted.
method Constant-factor approximation algorithms for deletion robust submodular maximization under matroid constraints.
result The algorithms provide good approximation guarantees for both centralized and streaming settings.
FedLog reduces communication in federated learning by sharing data summaries.
problem Significant communication overhead in federated learning with large model parameters.
method Shares minimal sufficient statistics via Bayesian inference and differential privacy.
result High learning accuracy with low communication overhead.
Models extract relevant EHR snippets to aid radiologists in diagnosis.
problem Difficulty in identifying relevant patient record information for diagnosis.
method Distantly supervised transformer-based neural model for extractive summarization.
result Models yield better extractive summaries than unsupervised approaches.
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.
Determinantal point processes (DPPs) are distributions over sets of items that model diversity using kernels. Their applications in machine learning include summary extraction and recommendation systems. Yet, the cost of sampling from a DPP is prohibitive in large-scale applications, which has triggered an effort towar…
New method extracts cosmological information from dark matter halo catalogues using graph neural networks.
problem Quantifying cosmological information from large-scale structure data.
method Implicit likelihood approach with Information Maximising Neural Networks (IMNNs) on graph representations of dark matter halo catalogues.
result Graph neural network summaries can extract information from noisy catalogues and improve parameter constraints.
SafeAccess identifies people in smart homes for safer access.
problem Enhancing safety and independence for people with disabilities.
method Change detection, Faster-RCNN, LBP/FaceNet, MTCNN, MMS.
result Average F-score of 0.97 for identifying friends/families/caregivers versus intruders/unknown.
This review compares extractive and abstractive summarization methods.
problem Improving abstractive summarization in natural language processing.
method Compared various approaches including supervised and unsupervised methods, deep learning, and NLP.
result Current research uses combinations of approaches, but abstractive summarization remains unsolved.
Study shows current simulations are insufficient for optimal neural network training in cosmology.
problem Insufficient training data for neural networks in cosmological inference.
method Empirical neural scaling law and Cramer-Rao bound to forecast training simulations needed.
result Current simulation suites do not provide sufficient training data for optimal neural network performance.
Combining global and local explanations improves user understanding of RL agents.
problem Challenges in explaining agent behavior due to large state spaces and delayed rewards.
method Integrating strategy summaries with saliency maps to provide both global and local explanations.
result Summaries including important states significantly improve user understanding of RL agents.
Graph-based semi-supervised learning for aspect term extraction.
problem Aspect term detection and sentiment analysis in reviews.
method Label spreading algorithm on graph sparsified by kNN for efficient classification.
result The approach achieves good results with limited labeled data.
Topological methods improve neuron analysis and tracer injection summary.
problem Traditional methods fail to capture the tree-like structure of neurons.
method Discrete Morse (DM) Theory for neuron skeletonization and consensus tree summarization.
result Significant performance improvements over non-topological methods.
Machine learning speeds up FLIM analysis in biomedical research.
problem Complex, slow, and computationally expensive FLIM analysis.
method Machine learning techniques for faster and smarter FLIM data extraction and interpretation.
result Higher accuracy in classifying and segmenting FLIM images compared to conventional methods.
Framework analyzes RL agents' behavior to explain their strengths and weaknesses.
problem Understanding and explaining RL agents' capabilities and limitations.
method Data analysis and visualization of interaction history to extract interestingness elements.
result Visual summaries help humans correctly perceive agents' strengths and weaknesses.
New mechanism for pure differential privacy on functional summaries using Laplace-like process.
problem Challenges in achieving differential privacy for complex, structured functional summaries.
method Independent Component Laplace Process (ICLP) mechanism for infinite-dimensional Hilbert space.
result Effective enhancement of utility of private summaries through oversmoothing.
Approximate Bayesian Computation (ABC) methods are used to approximate posterior distributions in models with unknown or computationally intractable likelihoods. Both the accuracy and computational efficiency of ABC depend on the choice of summary statistic, but outside of special cases where the optimal summary statis…
LIDS assesses LLM summaries with interpretable key words.
problem Challenges in evaluating the quality of LLM summaries.
method BERT-SVD-based direction metric and SOFARI for key word extraction.
result LIDS provides interpretable key words for layered themes.
Study evaluates LLMs for predicting Chinese stock movements using financial news sentiments.
problem Evaluating LLMs' ability to predict stock price movements using financial news sentiments.
method Standardized experimental procedure with three LLMs, each with unique performance enhancement methods.
result Developed quantitative trading strategies and conducted back-tests to assess LLMs' performance.
In this work, we present the Grounded Recurrent Neural Network (GRNN), a recurrent neural network architecture for multi-label prediction which explicitly ties labels to specific dimensions of the recurrent hidden state (we call this process "grounding"). The approach is particularly well-suited for extracting large nu…
Approximate Bayesian computation is an established and popular method for likelihood-free inference with applications in many disciplines. The effectiveness of the method depends critically on the availability of well performing summary statistics. Summary statistic selection relies heavily on domain knowledge and care…
Automatically learns summary features from time series data for likelihood-free inference.
problem Necessity of hand-tailored summary features for time series data in likelihood-free inference.
method Data-driven approach to automatically learn summary features.
result Learning summary features from data can outperform hand-crafted values in likelihood-free inference.
Text clustering method replaces centroids with summaries for interpretability and scalability.
problem Efficiently clustering text data while maintaining interpretability and scalability.
method k-NLPmeans and k-LLMmeans, which periodically replace numeric centroids with textual summaries.
result Consistently outperforms classical baselines and recent LLM-based clustering methods.
Scattering representations simplify SBI for images without extra compression.
problem Efficiently performing simulation-based inference on images with limited data.
method Use scattering representations for compression and learning, combined with spatial averaging and expressive density estimators.
result Scattering representations provide more information than traditional methods, without requiring additional simulations.
Bayesian neural networks improve with summary information and Dirichlet process.
problem Lack of prior knowledge in BNNs for complex architectures.
method Incorporates external summary information about predicted probabilities using a Dirichlet process.
result Improves model accuracy, uncertainty calibration, and robustness.
theft package simplifies feature extraction for time series analysis in R.
problem Lack of a unified access point and methodological pipelines for feature-based time series analysis.
method theft package provides a unified framework for computing features from six open-source time series feature sets.
result theft enables comprehensive quantification and interpretation of time series structure.
Plug-in robust NPE method adapts summaries independently of pretrained NPE.
problem Misspecification of neural posterior estimators under test data distribution.
method Minimum-distance summaries using maximum mean discrepancy (MMD).
result Substantial robustness gains with minimal additional overhead.
Two approaches use TDA and graph theory for tennis match prediction.
problem Predicting tennis match outcomes using network features.
method Lower-star filtration on player competitive networks, Random Forest model, modified Katz similarity index.
result TDA features alone can achieve above-chance prediction in tennis match outcomes.
PENs learn summary statistics for ABC using invariant neural architectures.
problem Learning summary statistics for approximate Bayesian computation (ABC).
method Partially exchangeable networks (PENs) that are invariant to block-switch transformations.
result PENs provide more reliable posterior samples with less training data.
Improved likelihood-free inference by localizing and refining low-dimensional approximations.
problem Poor performance of common likelihood-free methods in high-dimensional models.
method Localisation followed by refinement of low-dimensional summaries.
result Improved accuracy in marginal posteriors through localized and refined approximations.
Automatic summarisation is a popular approach to reduce a document to its main arguments. Recent research in the area has focused on neural approaches to summarisation, which can be very data-hungry. However, few large datasets exist and none for the traditionally popular domain of scientific publications, which opens …