Dynamic model tracks word meanings over time.
problem Capturing semantic evolution of words over time.
method Latent diffusion process, variational inference algorithms.
result Higher predictive likelihoods and interpretable word trajectories.
GASC models semantic change in Ancient Greek texts using genre metadata.
problem Associating correct meanings in historical Ancient Greek texts.
method Develops a dynamic semantic change model leveraging genre metadata.
result Improves predictive performance on semantic change in Ancient Greek texts.
Informer improves financial market prediction accuracy with global time stamp features.
problem Intra-day minute-scale financial market prediction challenges.
method Informer network, a novel deep learning model with smaller computational complexity and global time stamp features.
result Informer achieves best performance on MAE, RMSE, and MAPE evaluation criteria across all datasets.
In this paper, we develop the continuous time dynamic topic model (cDTM). The cDTM is a dynamic topic model that uses Brownian motion to model the latent topics through a sequential collection of documents, where a "topic" is a pattern of word use that we expect to evolve over the course of the collection. We derive an…
A new model for time-dependent data with dependencies over time.
problem Modeling data with time-dependent features and dependencies.
method Introducing a new probabilistic model based on Poisson random fields and Indian buffet processes.
result Developed a nonparametric focused topic model for time-stamped text documents.
Incorporating the side information of text corpus, i.e., authors, time stamps, and emotional tags, into the traditional text mining models has gained significant interests in the area of information retrieval, statistical natural language processing, and machine learning. One branch of these works is the so-called Auth…
CDSA uses self-attention to impute missing values in multivariate, geo-tagged time series data.
problem Missing values in multivariate, geo-tagged time series data.
method Cross-Dimensional Self-Attention (CDSA) for sequence modeling across time, location, and sensor measurements.
result CDSA outperforms state-of-the-art methods in imputation and forecasting on real-world datasets.
Paper tackles learning time series models from noisy timestamps.
problem Learning time series detection models from temporally imprecise labels.
method Proposes a general learning framework accommodating different base classifiers and noise models.
result Significantly outperforms alternatives on real mobile health data.
ChatGPT snapshots predict future stock returns.
problem Predicting future stock returns using pre-cutoff text.
method Extracted LLM outlook scores from OpenAI snapshots.
result Outlook scores positively correlate with future stock returns.
RPE detects anomalies robustly in time-series data.
problem Detecting anomalies in time-series data efficiently and robustly.
method Window-based, robust projection step, closed-form algorithm.
result RPE can identify anomalies in time-stamp level and outperforms existing methods.
CLPF models continuous time-series data with improved representational power and variational approximations.
problem Fitting continuous time-series data with existing models faces challenges in representational power and variational quality.
method CLPF uses a time-dependent normalizing flow driven by a stochastic differential equation to decode continuous latent processes into continuous observables. Maximum likelihood optimization is achieved through a novel variational posterior process.
result CLPF outperforms state-of-the-art baselines on synthetic and real-world time-series data.
Paper introduces efficient methods for probabilistic querying of event sequences.
problem Hard queries about future events in continuous-time sequences.
method Importance sampling framework for addressing query types.
result Method is more efficient than naive simulation, often 1,000 times.
Proposes models for learning latent representations of evolving network vertices over time.
problem Inadequate models for capturing temporal smoothness in evolving networks.
method Proposes two models: retrofitted and linear transformation, to capture temporal smoothness.
result Proposed models significantly outperform existing models in temporal link prediction tasks.
BayOTIDE tackles imputation of irregularly sampled multivariate time series with uncertainty quantification.
problem Imputation of irregularly sampled multivariate time series with missing values and noises.
method BayOTIDE treats multivariate time series as a combination of low-rank temporal factors with different patterns, using Gaussian Processes (GPs) as functional priors and converting them into state-space priors for scalable online inference.
result BayOTIDE can handle imputation over arbitrary time stamps and offers uncertainty quantification and interpretability.
Deep learning shows ETF imbalances are more informative than market imbalances.
problem Determining causality between ETF and market imbalances.
method Deep learning econometric methodology applied to stock and ETF transactions.
result ETF imbalance messages are more informative than market imbalance messages.
Hybrid approach for large-scale network synchronization using KF and PTP.
problem Synchronization of large-scale networks in 5G.
method Combines Kalman Filtering and PTP for pairwise synchronization, and Factor Graphs and Belief Propagation for end-to-end synchronization.
result Error in offset estimation remains below 5 ns in simulations.
Model-based collaborative filtering analyzes user-item interactions to infer latent factors that represent user preferences and item characteristics in order to predict future interactions. Most collaborative filtering algorithms assume that these latent factors are static, although it has been shown that user preferen…
We present and test a sequential learning algorithm for the short-term prediction of human mobility. This novel approach pairs the Exponential Weights forecaster with a very large ensemble of experts. The experts are individual sequence prediction algorithms constructed from the mobility traces of 10 million roaming mo…
Reconstructs power grid dynamics from PMU measurements.
problem Reconstructing dynamic state matrix of power transmission grids.
method Maximum likelihood based convex estimators adapting to prior information.
result Fully data-driven method that works in near real-time.
A novel transformer model improves classification of partially ordered sequences.
problem Classification of partially ordered sequences with uncertainty in timestamps.
method Developed a transformer-based model for partially ordered sequences, benchmarked against set models.
result Transformer-based model outperforms set models on three datasets.
Paper proposes UIS-RNN for fully supervised speaker diarization.
problem Speaker diarization with unknown number of speakers and time-stamped labels.
method Parameter-sharing RNNs with interleaved states, ddCRP for clustering.
result 7.6% diarization error rate on NIST SRE 2000 CALLHOME.
DeepTravel uses neural networks to estimate travel time efficiently.
problem Estimating travel time of paths considering complex factors.
method Leverages deep neural networks with auxiliary supervision.
result DeepTravel outperforms existing approaches in estimating travel time.
New method learns cell trajectories and network interactions from single-cell data.
problem Network inference in systems biology from steady-state data.
method Min-entropy estimation for stochastic dynamics, leveraging both temporal and perturbational data.
result Jointly learns cellular trajectories and network interactions.
The paper tackles AI advice giving by considering adherence levels and defer options.
problem Inadequate consideration of human adherence to AI recommendations.
method Sequential decision-making model that considers adherence levels and incorporates a defer option.
result Specialized learning algorithms provide better convergence and empirical performance.
Post-estimation smoothing improves prediction accuracy with structural indices.
problem Using natural structural indices in machine learning without losing robustness.
method A post-estimation smoothing operator that separates from the original predictor.
result Post-estimation smoothing improves accuracy over original predictors under simple conditions.
A new platform predicts object movements without needing specific context.
problem Predicting the next position of movable objects.
method λ-Architecture for batch and stream analytics, combining for improved accuracy.
result Combining λ-Architecture parts improves overall accuracy and performance.
Scene text magnifier enhances readability for visually impaired.
problem Helps visually impaired read natural scene text.
method Four CNN-based networks: character erasing, extraction, magnify, synthesis.
result Effective text magnification without background alteration.
The paper classifies actions of a specific group on certain manifolds.
problem Classifying analytic actions of a specific semi-orthogonal group on manifolds.
method Adapting Uchida's construction, the paper explicitly constructs actions on specific manifolds and demonstrates that any action is covered by these.
result Any analytic action of the semi-orthogonal group on a closed, connected manifold is covered by the constructed actions.
W-RNN improves text classification by extracting serialized text semantics.
problem Semantic constraint in sparse representation classification methods.
method Weighted RNN using word vectors and recurrent neural networks.
result W-RNN outperforms other methods in precision, recall, F1, and loss values.
MPE models traffic trajectory data to predict next locations.
problem Predicting next locations from traffic trajectory data.
method Mobility pattern embedding model MPE.
result MPE significantly outperforms state-of-the-art methods in next location prediction.
The paper solves the Nielsen realization problem for high degree del Pezzo surfaces.
problem Which finite subgroups of the mapping class group of a del Pezzo surface lift to the diffeomorphism group?
method Classification and partial answers for d≥7, equivariant connected sum for d=6. result Complete classification for d≥7, partial answer for d=6. This paper tackles text infilling, a task of filling missing text portions, and presents a self-attention model that outperforms other methods.
problem The task of filling missing text portions, especially when the number and length of missing portions are unknown.
method A self-attention model with segment-aware position encoding and bidirectional context modeling, trained on extensive supervised data.
result The self-attention model significantly outperforms other approaches, setting a strong baseline for future research.
A new text representation model combines CNN and VAE for better semantic extraction.
problem Difficult to effectively extract semantic features and distinguish polysemy in text data.
method Integrates CNN for feature extraction and VAE for consistent Gaussian distribution.
result The model outperforms traditional classification algorithms in text classification tasks.
New families of Lie groups with special foliations discovered.
problem Characterizing left-invariant foliations on semi-Riemannian Lie groups.
method Classifying foliations generated by specific subgroups.
result Constructing new families of Lie groups with conformal minimal foliations.
Improved text summarization using belief propagation on weighted bipartite graphs.
problem Text summarization from a graph theory perspective.
method Generalized belief propagation algorithm for weighted bipartite graphs.
result Our algorithm outperforms greedy methods in text summarization tasks.
New TC variant dTC better fits motion planning for some systems.
problem Improving motion planning for autonomous systems.
method Defined and computed new homotopy invariant dTC.
result dTC and dcat provide better motion planning solutions.
The study combines social interaction data into a single network, identifying stable groups of chimpanzees.
problem Identifying stable groups of chimpanzees based on social interactions over time.
method Network representation, weighted proximity weights, principled loss function, statistical tests.
result The approach detects stable groups of chimpanzees that stay related for a significant length of time.
Two algorithms find local minima faster in finite-sum and general stochastic optimization.
problem Finding local minima in finite-sum and general stochastic nonconvex optimization.
method Stochastic Nested Variance Reduction (SNVRG) + Neon2.
result Achieves better gradient complexity for convergence to (ε,εH)-second-order stationary points. StoryGen uses images to generate coherent text from multiple images.
problem Generating coherent text from multiple images.
method Designing a Relational Text Data Generator algorithm to relate features from plural images.
result The model can generate meaningful paragraphs containing extracted features from input images.
A neural RNN model adapts time steps for non-stationary time series data.
problem Modeling and forecasting non-stationary time series with sharp changes.
method RNN-ODE-Adap model using neural ODE and adaptive time steps.
result Consistent estimation of intensity function for Hawkes-type data.
Projective naturality proved for Heegaard Floer homology.
problem Proving naturality of Heegaard Floer invariants under diffeomorphisms.
method Showed Heegaard Floer invariants yield functors to transitive systems in a projectivized category of Z[U]-modules. result Established Heegaard Floer invariants as functors to transitive systems in a projectivized category.
Construct model Higgs bundles in exceptional components of Sp(4, R) character variety.
problem Constructing model Higgs bundles in exceptional components of the Sp(4, R) character variety.
method Using the gluing construction for Higgs bundles over connected sums of Riemann surfaces and solutions to the Sp(4, R)-Hitchin equations.
result Provide model Higgs bundles in all 2g-3 exceptional components of the maximal Sp(4, R)-Higgs bundle moduli space.
This paper tackles efficient learning for factorial marked temporal point processes.
problem Efficient learning for factorial marked temporal point processes.
method Decoupled learning method with two procedures: ADM-M and Fast ISTA, and a reformulated Logistic Regression model.
result Empirical results show the efficiency of the decoupled and reformulated method.
Paper generates diverse, readable adversarial texts from scratch.
problem Text classification models are easily fooled by adversarial examples.
method Trained a conditional variational autoencoder (VAE) with adversarial loss and utilized GANs to generate consistent adversarial texts.
result Successfully generates adversarial texts with higher success rate and acceptable quality.
Unified framework improves NLP tasks by converting diverse problems into text-to-text format.
problem Improving natural language processing tasks through transfer learning.
method Unified text-to-text transformer framework, comparing various pre-training objectives and architectures.
result Achieved state-of-the-art results on multiple NLP benchmarks.
SCROLLS benchmarks long text NLP tasks, improving existing models.
problem Short NLP benchmarks ignore long texts; SCROLLS addresses this.
method Handpicked long-text datasets for summarization, QA, and inference tasks.
result Improvement potential on SCROLLS tasks, as indicated by initial baselines.
Framework for continuous-time network data representation learning.
problem Learning reliable representations of dynamic network interactions.
method Three-stage process: intensity estimation, projection learning, evolving node representation construction.
result Trajectories satisfy structural and temporal coherence, providing robust inference.
Contextual bandits study how reward variance affects regret bounds.
problem Investigating how small reward variance impacts regret bounds in contextual bandits.
method Analyzing two types of adversaries and function approximation complexities.
result Regret bounds are influenced by the eluder dimension and reward variance.