A model for time-sequence analysis infers latent functions automatically.
problem Understanding the structure of multiple time-sequences.
method Bayesian nonparametric Poisson process allocation (BaNPPA) with Gaussian process latent functions.
result The model infers the number of latent functions automatically and is computationally efficient.
Learned factor graphs improve inference from time sequences using neural networks.
problem Inference from time sequences with limited labeled data.
method Combines model-based algorithms and data-driven ML tools for stationary time sequences.
result Learned factor graphs can accurately infer from small training sets.
Unsupervised framework learns symmetry from time sequences.
problem Learning symmetry from time sequences without labeled data.
method Meta-sequential prediction (MSP) framework that leverages stationary properties.
result Hidden disentangled structure emerges as a by-product of training.
This paper introduces a new neural ODE model for continuous-time sequence generation.
problem Representing and predicting continuous-time sequences with high accuracy.
method A neural emission model and neural ODE define the latent state evolution, with an Energy-based model for prior distribution.
result The model outperforms existing methods in various tasks, including long-horizon predictions.
Drawdowns measuring the decline in value from the historical running maxima over a given period of time, are considered as extremal events from the standpoint of risk management. To date, research on the topic has mainly focus on the side of severity by studying the first drawdown over certain pre-specified size. In th…
Paper improves deep learning models for cardiac potential reconstruction.
problem Improving generalization of sequence models for cardiac potential reconstruction.
method Constrained stochasticity and global aggregation of temporal information in latent space.
result Improved generalization of inverse reconstruction networks.
Mamba efficiently learns low-dimensional targets in-context via feature extraction.
problem Learning low-dimensional targets in context for computational efficiency.
method Test-time feature learning of a single-index model using Mamba's pretrained linear-time sequence model.
result Mamba achieves efficient in-context learning of low-dimensional targets via feature extraction.
Develops a RNN model to predict obesity status improvement using irregular activity data.
problem Predicting obesity status improvement using irregular activity data.
method Develops a RNN-based time-aware architecture to handle irregular observation times and extract relevant features from longitudinal patient records.
result Achieves an accuracy of 77-86% in predicting obesity status improvement.
We introduce a recursive adaptive group lasso algorithm for real-time penalized least squares prediction that produces a time sequence of optimal sparse predictor coefficient vectors. At each time index the proposed algorithm computes an exact update of the optimal ℓ1,∞-penalized recursive least squares (R…
TADA detects anomalies in time series using topological data analysis.
problem Detecting global changes in dependency structure between channels in multivariate time series.
method Topological Data Analysis for detecting anomalies in multivariate time series.
result The approach is more suitable for detecting global changes of correlation structures than existing methods.
This work tackles phaseless subspace tracking, recovering time-varying signals from phaseless projections.
problem Recovering time-varying signals from phaseless linear projections under gradual subspace change.
method Dynamic subspace tracking approach, leveraging gradual subspace change over time.
result Demonstrates feasibility of phaseless subspace tracking with gradual subspace change.
We first pursue the study of how hierarchy provides a well-adapted tool for the analysis of change. Then, using a time sequence-constrained hierarchical clustering, we develop the practical aspects of a new approach to wavelet regression. This provides a new way to link hierarchical relationships in a multivariate time…
The price of financial assets are, since Bachelier, considered to be described by a (discrete or continuous) time sequence of random variables, i.e a stochastic process. Sharp scaling exponents or unifractal behavior of such processes has been reported in several works. In this letter we investigate the question of sca…
This paper derives a diffusion approximation for a sequence of discrete-time one-sided limit order book models with non-linear state dependent order arrival and cancellation dynamics. The discrete time sequences are specified in terms of an R+-valued best bid price process and an Lloc2-valued volume process. …
GCRNNs improve graph problem solving with fewer parameters.
problem Graph process problems like earthquake epicenter identification and weather prediction.
method GCRNNs use convolutional filter banks and time-gated variations of GCRNNs (Gated GCRNNs) to improve performance.
result GCRNNs significantly improve performance over GNNs and another graph recurrent architecture.
MoChA splits sequences into chunks for efficient, online attention.
problem Efficiently decoding sequence-to-sequence models with soft attention.
method Adaptive chunking of input sequences for soft attention computation.
result MoChA models achieve state-of-the-art performance in online speech recognition and document summarization.
This work compresses sequences by treating them as continuous-time processes, enabling efficient discretization.
problem Efficient compression of sequences, especially with deep learning models that scale with sequence length.
method Treat sequences as continuous-time processes, learn efficient discretization, and decode at different time intervals.
result Automatic bit rate reductions in video and motion capture sequences using learned discretization.
Predicts disruptions in ADITYA tokamak 12 ms in advance.
problem Detecting disruptions in small tokamaks like ADITYA.
method Uses LSTM network trained on pre-processed tokamak diagnostics.
result Predicts disruptions 12 ms in advance with low computation cost.
Paper shows no finite time singularities for smooth conformal heat flow of harmonic maps.
problem Smoothness of conformal heat flow of harmonic maps.
method Combines harmonic map flow with metric evolution in conformal direction.
result No finite time singularity occurs for the flow, and under certain conditions, maps converge to a point.
Impute missing events in continuous-time sequences using particle smoothing.
problem Missing events in continuous-time sequences.
method Particle smoothing with trainable bidirectional LSTM proposals.
result Imputed sequences have low Bayes risk compared to ground truth.
A new algorithm optimizes time-varying functions with non-constant evaluation times.
problem Optimizing functions that change over time with varying evaluation times.
method Proposes a novel time-varying Bayesian optimization algorithm.
result Establishes a regret bound for the proposed algorithm.
The study examines how bias affects hypothesis formation in neural networks.
problem Characterizing the impact of bias on hypothesis formation in neural networks.
method An automated data-driven projection pursuit neural network to extract and select features for binary classification.
result The refinement of a working hypothesis converges to a robust multivariate perception of data.
RCNs match and exceed MLPs and SCNs in reinforcement learning tasks.
problem Efficiently learning rhythmic motion in reinforcement learning.
method Combining RNNs and SCN structures to create RCNs.
result RCNs outperform MLPs and SCNs across all environment tasks.
TSFMs show redundant components in layers, affecting their performance.
problem Redundant components in TSFMs layers impact their predictive accuracy.
method Mechanistic interpretability tools, ablations, logit attribution, theoretical framework.
result TSFMs are robust to ablations of entire layers and specific heads.
Compact model uses RBMs for sequence classification with fewer parameters.
problem Sequence classification with dynamic models and complex neural networks.
method Rolling RBMs over time for representation learning and temporal inference.
result Outperforms state-of-the-art models in melody and character recognition.
New method embeds RNN Seq2Seq models to visualize spatiotemporal data.
problem Visualizing and interpreting spatiotemporal data in sequence prediction tasks.
method Embedding approach to visualize and interpret RNN Seq2Seq model representations.
result Embedding space projections of RNN Seq2Seq models capture spatiotemporal dynamics.
Hybrid model combines graphical and learned inference for better data estimation.
problem Suboptimal estimation due to poor graphical model approximation of complex data generating process.
method Combines graphical inference with a learned inverse model structured as a graph neural network and formulated as a recurrent neural network.
result Hybrid model estimates chaotic trajectory more accurately than graphical or learned inference alone.
Generative diffusion models improve financial LOB simulation and forecasting.
problem High noise and complexity in financial LOB data makes deep generative models ineffective.
method Convert LOB data to images, apply diffusion models with inpainting for long-term sequence generation.
result Our method achieves state-of-the-art performance on LOB-Bench, improving coherence over local details.
RENAL test evaluates generative models for time series data.
problem Evaluating generative models for time series data is challenging.
method RENAL test uses recurrent neural networks to transform time series into conditionally independent data pairs for goodness-of-fit testing.
result RENAL test outperforms existing methods in evaluating generative models for time series data.
The paper proposes a novel model to forecast patent citations using multi-attention recurrent networks.
problem Forecasting forward citations to patents to discover emerging technologies.
method The approach employs a sequence-to-sequence model with an attention-of-attention mechanism to capture dependencies in multiple time sequences.
result The proposed model outperforms state-of-the-art models in forward citation forecasting.
This paper tackles non-convex phase retrieval with structured assumptions.
problem Phase retrieval with limited measurements and structure assumptions.
method Non-convex approaches with sample complexity guarantees.
result Sample-efficient recovery with structured signals/images.
Novel method detects changes in noisy dynamic networks.
problem Change detection in noisy dynamic networks with sparsity and degree heterogeneity.
method Adapted Procrustes analysis to embedded points for vertices in spectral embedding.
result CDP successfully detects various types of vertex-based changes.
Survey on RL for seq2seq models to solve exposure bias and inconsistency.
problem Exposure bias and inconsistency in seq2seq models.
method Combining RL methods with seq2seq models.
result Improved seq2seq performance through RL.
Machine learning predicts dam-break flood wave behavior accurately.
problem Predicting long-term wave behavior in dam-break floods.
method Solved Saint-Venant equations using Lax-Wendroff scheme, trained RC-ESN with flow depth data.
result RC-ESN model predicts 286 time-steps ahead with RMSE < 0.01, outperforming LSTM.