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

4519021,3521,803 · Jun 202019922001200920172026
48 results for Sequential data modeling

This paper reviews methods for interpreting deep learning models with sequential data.

problem Limited interpretability of deep learning models in sequential data domains.
method Reviews and compares techniques for sequential interpretability.
result Current techniques have limitations and future research is needed.

Language models trained on chess board states outperform those on moves, even with causal masking.

problem Applying causal masking to spatial data for training unimodal language models.
method Trained bidirectional and causal self-attention models on both spatial (board-based) and sequential (move-based) chess data.
result Models trained on spatial board states achieve stronger playing strength than those trained on sequential data, even with causal masking.

Proposes LDIDPs for efficient sequential data generation from latent dynamical models.

problem Challenges in generating high-fidelity sequential samples from latent dynamical models.
method Utilizes implicit diffusion processes to sample from latent dynamical processes.
result Demonstrates accurate learning of dynamics and efficient generation of high-quality sequential data.

We consider the problem of inferring a latent function in a probabilistic model of data. When dependencies of the latent function are specified by a Gaussian process and the data likelihood is complex, efficient computation often involve Markov chain Monte Carlo sampling with limited applicability to large data sets. W…

2018-07-13abs ↗pdf ↗

EvoRate metric assesses learnability of sequential data by measuring predictive information.

problem Model misspecification due to misinterpreting patterns in sequential data.
method Predictive information framework based on mutual information between past and future.
result Temporal patterns fundamentally constrain learnability; optimal predictors cannot outperform intrinsic information limit.

An adversarial detector identifies anomalous sequences in sequential data.

problem Detecting anomalous sequences in one-class settings with limited data.
method Solves a minimax problem to find an optimal detector against the worst-case sequences from a generator, using marked point process model.
result Demonstrated good performance on simulations and real credit card fraud datasets.

A universal framework for constructing confidence sets using sequential likelihood mixing.

problem Constructing reliable confidence sets for realizable likelihood functions.
method Sequential likelihood mixing, integrating Bayesian inference and regret inequalities.
result Establishes fundamental connections and provable coverage guarantees for various inference techniques.

This paper discovers classification models from sequential data without prior knowledge.

problem Lack of prior knowledge in defining kernels for online classification.
method Adapts GP-based time-series structure discovery with SMC to learn new features from sequential data.
result Improves classification accuracy by 10% on real-world data.

Novel framework optimizes experiments for implicit models using mutual information.

problem Optimizing experiments for intractable implicit models.
method Sequential Bayesian Experimental Design using Mutual Information.
result Framework efficiently estimates parameters with few iterations.

Paper proposes a new method to handle missing data in medical records using sequential variational autoencoders.

problem Missing data in medical records due to sensor off-times and uneven data collection.
method Sequential variational autoencoders (VAEs) with a new methodology called Shi-VAE.
result Shi-VAE achieves the best performance in terms of both metrics compared to state-of-the-art methods.

Study when to replace machine learning models with new data.

problem When to switch machine learning models with new data sources.
method Unified economic and statistical framework linking learning-curve dynamics, data-acquisition, and retraining costs.
result Look-ahead sequential method outperforms other methods and approaches optimal value.

New method uses diffusion models for Bayesian inverse problems.

problem Solving Bayesian inverse problems with linear-Gaussian models.
method Decoupled Diffusion Sequential Monte Carlo (DDSMC) method.
result Asymptotically exact solution demonstrated on various data types.

SIM models user interests from long sequential behavior data, improving click-through rate prediction.

problem Challenges in capturing user interests with long user behavior sequences.
method SIM uses a cascaded search paradigm with two units: General Search Unit and Exact Search Unit.
result SIM achieves significant CTR and RPM lifts in Alibaba's display advertising system.

We propose the factorized action variational autoencoder (FAVAE), a state-of-the-art generative model for learning disentangled and interpretable representations from sequential data via the information bottleneck without supervision. The purpose of disentangled representation learning is to obtain interpretable and tr…

2019-02-22abs ↗pdf ↗

PoPPy is a Point Process toolbox based on PyTorch, which achieves flexible designing and efficient learning of point process models. It can be used for interpretable sequential data modeling and analysis, e.g., Granger causality analysis of multi-variate point processes, point process-based simulation and prediction of…

2018-10-23abs ↗pdf ↗

A new neural network model reduces features in high-dimensional sequential data.

problem Exponential growth in features of truncated signature transform in high-dimensional data.
method Proposes a neural network model inspired by Convolutional Neural Networks to address feature growth.
result Reduces the number of features efficiently in a data-dependent way.

A semi-recurrent hybrid VAE-GAN model for generating sequential data is introduced. In order to consider the spatial correlation of the data in each frame of the generated sequence, CNNs are utilized in the encoder, generator, and discriminator. The subsequent frames are sampled from the latent distributions obtained b…

2018-06-01abs ↗pdf ↗

The paper develops a method to learn cost-optimal sequential testing policies from retrospective data.

problem Learning cost-optimal sequential decision policies from retrospective data with missing test results.
method Doubly robust Q-learning framework with path-specific inverse probability weights.
result The method reduces testing cost without compromising predictive accuracy.

A new kernel Stein test assesses fit for variable-length sequential data.

problem Evaluating goodness of fit for varying-dimensional data like text documents of different lengths.
method Extends kernel Stein discrepancy (KSD) to variable-dimension settings by identifying appropriate Stein operators and proposing a novel KSD goodness-of-fit test.
result The proposed test performs well on discrete sequential data benchmarks.

CTGAN synthesizes population data for travel behavior simulation.

problem Synthesizing population data for agent-based transportation modeling.
method Composite Travel Generative Adversarial Network (CTGAN).
result Consistent and accurate generation of synthetic populations with tabular and sequential mobility data.

A new method uses active learning to improve bile duct stone evaluation.

problem Efficiently collecting necessary patient data in sequential healthcare decisions.
method Developed an active learning-based multistage sequential decision-making model.
result Improves estimation efficiency by 62%-1838% compared to baseline methods.

A new method uses CPD to efficiently model feature interactions in non-sequential data.

problem Efficiently modeling feature interactions in non-sequential data with high computational and memory costs.
method Implicitly represent model parameters as a tensor, factorize into a compact Tensor Train (TT) format, and use Canonical Polyadic (CP) Decomposition for invariance to feature ordering.
result The proposed CP-based predictor outperforms other TN-based predictors on sparse data and matches neural network performance on dense non-sequential tasks.

Diffusion Transformer captures spatial-temporal dependencies in sequential data.

problem Capturing rich spatial and temporal dependencies in sequential data.
method Established theoretical guarantees for diffusion transformers learning Gaussian process data.
result Spatial-temporal dependencies are captured within attention layers of diffusion transformers.

New method estimates treatment effects over time with unobserved confounders.

problem Estimating treatment effects from observational data with unobserved confounders.
method Sequential Deconfounder using Gaussian process latent variable model.
result Unbiased estimates of individualized treatment responses over time.

Detects data drift in deep learning models using neural embeddings.

problem Detecting changes in data distribution in deep learning models.
method Formulates drift detection in a sequential decision framework and introduces a loss function to balance false alarms and quick detection.
result Demonstrates improved ability to balance false alarms and quick detection in change detection.

We develop a model to predict effects of sequential interventions, clarifying their combined impact.

problem Uncertainty in generalizing behavioral predictions for combinations of interventions.
method Explicit model for composition of interventions, identifying their combined effect.
result Our compositional model aids prediction in sparse data conditions.

New algorithms extract low-dimensional representations from sequential data, revealing insights into complex processes.

problem Challenges in extracting low-dimensional representations from sequential, high-dimensional, sparse, and noisy data.
method Developed new clustering algorithms based on Block Markov Chains theory, validated on real-world data.
result These algorithms can successfully extract low-dimensional representations from real-world sequential data, revealing insights into complex processes.

We present a novel framework for kernel learning with sequential data of any kind, such as time series, sequences of graphs, or strings. Our approach is based on signature features which can be seen as an ordered variant of sample (cross-)moments; it allows to obtain a "sequentialized" version of any static kernel. The…

2016-01-29abs ↗pdf ↗

New methods optimize experiment selection for sequential data, improving model accuracy.

problem Optimizing experiment selection for sequential data in multidimensional cases.
method Adopting greedy experiment selection methods for maximum likelihood estimation.
result Proposed methods produce consistent and asymptotically normal estimators.

Paper proposes AdaBoost-assisted ELM for efficient online sequential classification.

problem Efficient online sequential classification with improved accuracy and stability.
method Utilizes AdaBoost for cost-sensitive learning and forgetting mechanism for stability.
result Achieves 94.41% accuracy on MNIST dataset with reduced standard deviation.