The availability of large amounts of time series data, paired with the performance of deep-learning algorithms on a broad class of problems, has recently led to significant interest in the use of sequence-to-sequence models for time series forecasting. We provide the first theoretical analysis of this time series forec…
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “time sequences”
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.
New flexible confidence sequences for robust statistical inference.
problem Creating robust statistical inference methods that work under mild assumptions.
method Proposed a new class of asymptotic time-uniform confidence sequences.
result Sharp asymptotic time-uniform confidence sequences achieved under mild assumptions.
IAE extracts innovations sequences for non-Gaussian processes.
problem Extracting innovations sequences for non-Gaussian processes.
method Causal convolutional neural network.
result IAE effectively detects anomalies in non-Gaussian data.
Develops a new point process model for detecting neural spike sequences.
problem Detecting sparse sequences of neural spikes in high-dimensional spike trains.
method A point process model that represents sequence occurrences as marked events in continuous time, with learnable time warping parameters.
result Demonstrates improved detection and modeling of neural spike sequences.
Set-Sequence model learns cross-sectional dynamics directly from time series data.
problem Predicting large cross-sections of time series data with latent cross-sectional dynamics.
method A model that learns cross-sectional structure directly, enhancing expressivity and eliminating manual feature engineering.
result Significantly outperforms strong baselines in equity portfolio optimization and loan risk prediction.
This paper proposes a method for modeling event sequences with ambiguous timestamps, a time-discounting convolution. Unlike in ordinary time series, time intervals are not constant, small time-shifts have no significant effect, and inputting timestamps or time durations into a model is not effective. The criteria that …
A new model captures variability in time series data.
problem Capturing high variability in time series data.
method Temporal latent variables and dynamic weight modifications.
result Demonstrated efficacy on various sequential data.
We suggest a novel method of clustering and exploratory analysis of temporal event sequences data (also known as categorical time series) based on three-dimensional data grid models. A data set of temporal event sequences can be represented as a data set of three-dimensional points, each point is defined by three varia…
nTreeClus clusters categorical sequences using tree-based learners and k-mers.
problem Challenges in clustering categorical and sequential data.
method nTreeClus uses Tree-based Learners, k-mers, and autoregressive models for categorical time series.
result nTreeClus outperformed baseline methods in various validation metrics.
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.
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.
An explicit section of the Laudenbach exact sequence of the mapping class group of connect sums of math.GT
We provide an explicit section for a mapping class group sequence.
problem Mapping class group of connect sums of .
method Provided an explicit section for the split exact sequence.
result Explicit section for the exact sequence.
This paper establishes for the first time the predictive performance of speed priors and their computational complexity. A speed prior is essentially a probability distribution that puts low probability on strings that are not efficiently computable. We propose a variant to the original speed prior (Schmidhuber, 2002),…
AverageTime uses simple averaging to enhance long-term time series forecasting.
problem Long-term time series forecasting with improved intra-sequence and cross-channel dependencies.
method Proposes AverageTime, a simple, efficient, and scalable forecasting model that reframes channel extraction as a stackable architecture.
result AverageTime surpasses state-of-the-art models in forecasting performance with near-linear complexity.
Spacetimeformer learns spatiotemporal relationships from data alone.
problem Forecasting multivariate time series with distinct spatial relationships.
method Transformers with dynamic graph connections learning interactions between space, time, and value.
result Competitive results on various time series prediction benchmarks.
Many real-world applications require robust algorithms to learn point processes based on a type of incomplete data --- the so-called short doubly-censored (SDC) event sequences. We study this critical problem of quantitative asynchronous event sequence analysis under the framework of Hawkes processes by leveraging the …
Time-based model improves recommendation performance.
problem Efficiently handling sequences of varying lengths in recommendation systems.
method Embedding layer and TSL attention-like mechanism with inner products.
result Model outperforms complex models on Taobao User Behavior dataset.
Continuous-time event sequences represent discrete events occurring in continuous time. Such sequences arise frequently in real-life. Usually we expect the sequences to follow some regular pattern over time. However, sometimes these patterns may be interrupted by unexpected absence or occurrences of events. Identificat…
Deep recurrent neural networks perform well on sequence data and are the model of choice. However, it is a daunting task to decide the structure of the networks, i.e. the number of layers, especially considering different computational needs of a sequence. We propose a layer flexible recurrent neural network with adapt…
Paper shows how online betting algorithms' regret can be used to create tight confidence sequences.
problem Estimating the expectation of random variables from samples and creating time-uniform confidence sequences.
method Converts the regret guarantee of universal portfolio algorithms into time-uniform concentration inequalities and confidence sequences.
result Numerically obtained confidence sequences are never vacuous and satisfy the law of iterated logarithm.
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.
For training the sequence-to-sequence voice conversion model, we need to handle an issue of insufficient data about the number of speech pairs which consist of the same utterance. This study experimentally investigated the effects of Mel-spectrogram augmentation on training the sequence-to-sequence voice conversion (VC…
Synergetic Learning of Heterogeneous Temporal Sequences for Multi-Horizon Probabilistic Forecastingcs.LG
Proposes a model for multi-horizon probabilistic forecasting of time series influenced by asynchronous events.
problem Forecasting time series influenced by asynchronous events is challenging.
method Introduces Variational Synergetic Multi-Horizon Network (VSMHN), a deep conditional generative model combining deep point processes and variational recurrent neural networks.
result Produces accurate, sharp, and realistic probabilistic forecasts.
We present a probabilistic model for unsupervised alignment of high-dimensional time-warped sequences based on the Dirichlet Process Mixture Model (DPMM). We follow the approach introduced in (Kazlauskaite, 2018) of simultaneously representing each data sequence as a composition of a true underlying function and a time…
Convergence Analysis of Real-time Recurrent Learning (RTRL) for a class of Recurrent Neural Networkscs.LG
RTRL optimizes long sequences without truncation, converging to loss minima.
problem Inaccuracies in TBPTT for long sequences.
method Online optimization with exact gradient calculation.
result RTRL converges to loss minima for a class of RNNs.
Improves sequence modeling with a flow-based recurrent mixture density network.
problem Sequence modeling and sequence-to-sequence mapping applications.
method Generalized recurrent mixture density networks using normalized flow transformations.
result Significantly improved fit to image sequences measured by log-likelihood.
Events in the world may be caused by other, unobserved events. We consider sequences of events in continuous time. Given a probability model of complete sequences, we propose particle smoothing---a form of sequential importance sampling---to impute the missing events in an incomplete sequence. We develop a trainable fa…
Accelerates signature kernel computation for sequences.
problem Severe computational bottleneck in computing signature kernel.
method Random Fourier features to accelerate signature kernel computation.
result Uniform approximation guarantees for unbiased estimator with linear computation time.
Sequence-to-sequence models with soft attention have been successfully applied to a wide variety of problems, but their decoding process incurs a quadratic time and space cost and is inapplicable to real-time sequence transduction. To address these issues, we propose Monotonic Chunkwise Attention (MoChA), which adaptiv…
This thesis investigates unsupervised time series representation learning for sequence prediction problems, i.e. generating nice-looking input samples given a previous history, for high dimensional input sequences by decoupling the static input representation from the recurrent sequence representation. We introduce thr…
In order to study large variations or fluctuations of finite or infinite sequences (time series), we bring to light an 1868 paper of Crofton and the (Cauchy-)Crofton theorem. After surveying occurrences of this result in the literature, we introduce the inconstancy of a sequence and we show why it seems more pertinent …
Undirected neural sequence models such as BERT (Devlin et al., 2019) have received renewed interest due to their success on discriminative natural language understanding tasks such as question-answering and natural language inference. The problem of generating sequences directly from these models has received relativel…
Interleaved RNNs detect fraud without costly features.
problem Real-time fraud detection in payment cards.
method Use interleaved sequence RNNs for fraud detection.
result Interleaved RNNs outperform state-of-the-art models in fraud detection.
Sequential modelling with self-attention has achieved cutting edge performances in natural language processing. With advantages in model flexibility, computation complexity and interpretability, self-attention is gradually becoming a key component in event sequence models. However, like most other sequence models, self…
A new framework predicts links in time-dependent networks using Bernoulli autoregression.
problem Predicting links in time-dependent networks with additional auxiliary information.
method A Bernoulli autoregressive model with regularization for link discovery.
result The model can discover new links not present in the data.
Seq2Tens uses tensors to efficiently represent sequences, improving performance on time series and video tasks.
problem Challenges in analyzing sequential data due to complex dependencies and non-commutativity.
method Uses tensor algebra to capture dependencies and low-rank tensor projections to manage computational complexity.
result State-of-the-art performance on multivariate time series classification and video generation benchmarks.
Neural network optimizes learning sequence for reading words.
problem Children struggle with learning to read words due to inconsistent spelling-sound correspondences.
method Used a neural network to structure learning trials to optimize generalization accuracy.
result Significant improvement in generalization accuracy compared to random or frequency-based sequences.
Hidden Markov Model (HMM) combined with Gaussian Process (GP) emission can be effectively used to estimate the hidden state with a sequence of complex input-output relational observations. Especially when the spectral mixture (SM) kernel is used for GP emission, we call this model as a hybrid HMM-GPSM. This model can e…
Traditional pairwise sequence alignment is based on matching individual samples from two sequences, under time monotonicity constraints. However, in many application settings matching subsequences (segments) instead of individual samples may bring in additional robustness to noise or local non-causal perturbations. Thi…
The -Alternator adapts to varying noise levels in sequences, improving robustness and performance.
problem Current models assume uniform noise levels, limiting performance on noisy temporal data.
method Introduces -Alternator using Vendi Score to dynamically adjust noise sensitivity.
result Outperforms Alternators and state-of-the-art models in trajectory prediction, imputation, and forecasting.
Models for sequential data such as the recurrent neural network (RNN) often implicitly model a sequence as having a fixed time interval between observations and do not account for group-level effects when multiple sequences are observed. We propose a model for grouped sequential data based on the RNN that accounts for …
Single-timescale analysis improves convergence in multi-sequence stochastic approximation.
problem Finite-time convergence of nonlinear stochastic approximation with multiple coupled sequences.
method Smoothness property of fixed points and analysis of fine-grained single-timescale SA.
result Improved iteration complexity for achieving ε-accuracy in multi-sequence single-timescale SA.
A comparison of SLDS and LSTM for pedestrian behavior prediction shows SLDS works better with shorter sequences.
problem Time-critical pedestrian behavior prediction in autonomous vehicles.
method Comparison of a switching linear dynamical system (SLDS) and a three-layered bi-directional LSTM neural network.
result SLDS achieves higher accuracy with shorter sequences (10 samples) compared to LSTM's 80% accuracy with 100 samples.
Sequence-to-sequence models predict resource usage for co-scheduled jobs in data centers.
problem Challenges in co-scheduling jobs due to resource interference and inefficiencies.
method Sequence-to-sequence models based on recurrent neural networks for workload interference prediction.
result Models accurately forecast resource usage trends from job profiles, improving scheduling decisions.
Test-time regression: a unifying framework for designing sequence models with associative memorycs.LG
Unified framework for sequence models using test-time regression.
problem Designing efficient sequence models with associative memory.
method Formalizing associative recall as regression over input tokens, deriving various sequence models.
result Clarifies the effectiveness of query-key normalization in softmax attention and offers new generalizations.
Near-optimal tests and confidence sequences for non-parametric data.
problem Flexible statistical inference and decision-making with non-parametric data.
method Classic delayed-start normal-mixture sequential probability ratio tests with asymptotic guarantees.
result Asymptotically optimal type-I error and expected rejection time guarantees.
GGP models multivariate time series with latent sub-sequences for diverse behaviors.
problem Modeling multivariate time series with diverse behaviors and patterns.
method Graph Gamma Process (GGP) linear dynamical systems with latent sub-sequences.
result GGP models exhibit good predictive performance and reveal interpretable latent patterns.