Efficiently samples latent functions in complex data models with sequential structure.
problem Inference of latent functions in probabilistic models with complex data likelihoods.
method Extends Markov chain Monte Carlo techniques to handle sequential structure, enabling efficient sampling of latent variables and parameters.
result Strong performance in growing-data settings, demonstrating scalability.
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.
Hybrid VAE-GAN model generates sequential data with spatial correlations.
problem Generating sequences with spatial correlations between frames.
method Semi-recurrent CNNs in encoder, generator, and discriminator; sampling subsequent frames from latent distributions.
result Maintains dependencies between frames in generated sequences.
New algorithm for efficient topic modeling in sequential data.
problem Efficient topic modeling in sequential data.
method Stochastic collapsed variational inference algorithm for hidden Markov models and hierarchical Dirichlet process hidden Markov models.
result Our inference is more efficient and accurate than uncollapsed version.
FAVAE learns disentangled representations from sequential data.
problem Learning disentangled and interpretable representations from sequential data.
method FAVAE uses the information bottleneck principle without supervision.
result FAVAE can disentangle multiple dynamic factors.
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.
Model learns disentangled, interpretable representations from sequential data without supervision.
problem Learning disentangled and interpretable representations from sequential data without supervision.
method Factorized hierarchical variational autoencoder with multi-scale priors.
result Model outperforms i-vector baseline in speaker verification and reduces word error rate by 35% in mismatched scenarios.
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.
Estimates LRD in sequential data, improving RNNs.
problem Quantifying LRD in sequential data for better RNNs.
method Principled estimation procedure based on LRD theory for real-valued time series.
result Estimates LRD reliably in user behavior and Wikipedia article writing.
Proposes handling ambiguity in sequential data predictions.
problem Handling uncertainty in sequential data predictions.
method Extension of MHP model to recurrent architectures, introducing a novel metric.
result Achieved promising results on various sequential data tasks.
PoPPy simplifies point process modeling and analysis.
problem Efficient modeling and analysis of sequential data.
method Flexible design and efficient learning of point process models.
result PoPPy enables large-scale point process analysis, simulation, and prediction.
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.
Generative models linked to sequential decision making for data imputation.
problem Data imputation challenges in various datasets.
method Formulated data imputation as an MDP, developed neural network models with guided policy search.
result Models effectively learn policies for diverse imputation problems.
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.
Novel approaches apply multi-label methods to sequential data tasks.
problem Applying multi-label methods to sequential data.
method Study connections between multi-label methods and Markovian models, develop novel approaches.
result Novel approaches outperform established methods in sequential prediction tasks.
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.
GenHMM combines neural networks with HMM for sequential data modeling.
problem Sequential data modeling challenges.
method Integrates neural network generative models into HMM framework.
result GenHMM improves likelihood computation and tractability.
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.
SNL trains autoregressive flows on simulated data to learn likelihood for Bayesian inference.
problem Intractable likelihood in simulator models.
method Trains autoregressive flow on simulated data to model likelihood.
result SNL is more robust, accurate, and requires less tuning than related methods.
Efficient methods for answering complex probabilistic queries in sequential data.
problem Complex probabilistic queries in sequential data.
method Broad class of novel approximation techniques for marginalization in sequential models.
result Efficient techniques for answering long-range probabilistic queries.
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 tackles continual learning in GANs for sequential distributions.
problem Catastrophic forgetting in GANs when learning sequentially.
method Adapting continual learning techniques to GANs for sequential data.
result GANs can now model and learn from a sequence of distinct distributions without forgetting.
Interpretable RNN uses sparse recovery for better performance.
problem Interpreting the internal workings of RNNs.
method Sequential Sparse Recovery + SISTA algorithm.
result SISTA-RNN achieves better performance and is more interpretable.
Stochastic WaveNet models sequential data with latent variables and dilated convolutions.
problem Modeling distribution of sequential data like speech and motions.
method Combines stochastic latent variables and dilated convolutions in WaveNet architecture.
result Obtains state-of-the-art performances on speech and handwriting datasets.
RANP improves neural processes for sequential data.
problem Capturing temporal order and recurrent structure from sequential data.
method Incorporated ANP into a recurrent neural network.
result RANP outperforms NPs and LSTMs in 1D regression and autonomous-driving tasks.
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.
Proposes a new RNN model for grouped sequential data with varying time intervals.
problem Implicitly models fixed time intervals between observations and lacks group-level effects.
method Mixed membership framework for RNN, learning group-level base parameter.
result Demonstrates dynamic topic modeling with evolving topic distributions over time.
Model-X test detects conditional independence in streaming data.
problem Detecting conditional independence in data streams with arbitrary dependency.
method Sequential testing inspired by model-X and testing by betting.
result Significantly reduces type-I error rate and enhances data efficiency.
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.
Extracts weighted automata from black box models for sequential data.
problem Global interpretability of black box models for symbolic sequential data.
method Spectral algorithm for extracting weighted automata from black boxes without access to inner representation.
result Approximation of black box models using inferred weighted automata is of high quality.
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.
Enhances feature extraction for sequential data using CNN and RNN.
problem Extracting features from sequential data efficiently.
method Integrates recurrent neural networks into convolutional layers for sequential data.
result Improves performance in audio classification tasks.
This paper develops a new method for online density estimation from noisy data.
problem Estimating probability density function from noisy streaming data.
method Quasi-Bayesian sequential deconvolution using Newton's algorithm.
result Sequential deconvolution estimate fn with large sample asymptotic guarantees. New method improves model training on sequential data.
problem Training latent variable models with ELBO limits.
method Introducing FIVO, a family of tighter bounds.
result FIVO leads to substantial improvements over ELBO.
Novel framework for kernel learning with sequential data.
problem Learning with sequential data, especially time series and sequences of graphs.
method Signature features as an ordered variant of sample moments, leading to sequentialized versions of static kernels.
result Sequential kernels efficiently computable for discrete sequences, approximating continuous moment form.
IRS approach handles high-dimension and sparsity in sequential data streams.
problem Challenges in modeling high-dimensional and sparse data streams with adaptive prior knowledge.
method Incorporates adaptive L1-penalty and inertia terms in the loss function.
result IRS approach outperforms state-space models in experimental studies and real data.
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.
Deep TSBNs learn sequential data with hierarchical SBNs and scalable learning.
problem Learning sequential dependencies in time-series data.
method Multi-layered hierarchical sigmoid belief networks (TSBNs) with scalable learning algorithms.
result Achieves state-of-the-art predictive performance and sequence synthesis.
A new model learns latent spaces for graph data.
problem Scalability and expressivity limitations in graph generative models.
method Sequential Graph Variational Autoencoder (SGVAE) that learns latent spaces directly from graph data.
result Promising results on a cycle dataset, but need for permutation relaxation.
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.
Develops methods for cooperative Bayesian inference.
problem Cooperation between learning agents.
method Sequential Bayesian inference approaches.
result Theoretical foundation for cooperative inference.
New model mimics neural next item recommendation using Hankel matrices.
problem Next item recommendation efficiency and structural knowledge capture.
method Tensor factorization with Hankel matrix representation.
result Model performs competitively with neural networks but is simpler.
Aligns text representations over time for better performance in sequential tasks.
problem Language evolution causes data drift in sequential tasks.
method Sequentially aligns learned representations to combat data drift.
result Sequential alignment outperforms strong baselines on various tasks.
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 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.
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.