Solving complex, temporally-extended tasks is a long-standing problem in reinforcement learning (RL). We hypothesize that one critical element of solving such problems is the notion of compositionality. With the ability to learn concepts and sub-skills that can be composed to solve longer tasks, i.e. hierarchical RL, w…
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
48 results for “temporally extended tasks”
Deep reinforcement learning under signal temporal logic constraints using Lagrangian relaxationstat.ML
Study uses DRL with Lagrangian relaxation to solve temporal control tasks with STL constraints.
problem Optimal control problems with temporal logic constraints.
method Extended CMDP formulation, Lagrangian relaxation, two-phase constrained DRL algorithm.
result Demonstrated learning performance of the proposed algorithm through simulations.
A method uses RL to learn abstractions for planning, improving robot navigation and manipulation tasks.
problem Planning requires suitable abstractions for states and transitions, which RL struggles with for temporally extended tasks.
method Goal-conditioned policies learned with RL are incorporated into planning, with a latent variable model representing valid states.
result Our method significantly outperforms prior work on image-based robot navigation and manipulation tasks.
BrainCast predicts whole-brain fMRI time series from short scans.
problem Short scans reduce fMRI data quality and statistical power.
method Spatio-temporal forecasting framework for fMRI time series.
result BrainCast improves fMRI time series quality and prediction.
RCNPs extend equivariant neural processes to higher dimensions, improving performance on tasks with inherent symmetries.
problem Inherently equivariant tasks in spatio-temporal modeling, Bayesian Optimization, and continuous control.
method Relational Conditional Neural Processes (RCNPs) that extend equivariances to higher dimensions.
result Empirically competitive performance on tasks with equivariances.
TGAT learns node embeddings for evolving graphs, capturing both static and temporal features.
problem Learning node embeddings for dynamic graphs with evolving topological structures and temporal patterns.
method Temporal Graph Attention (TGAT) layer using self-attention and functional time encoding.
result TGAT model can inductively infer node embeddings for new and observed nodes as the graph evolves.
Transformer is a popularly used neural network architecture, especially for language understanding. We introduce an extended and unified architecture that can be used for tasks involving a variety of modalities like image, text, videos, etc. We propose a spatio-temporal cache mechanism that enables learning spatial dim…
Agents compose pre-trained policies for complex tasks, improving zero-shot performance.
problem Challenges in long-horizon predictions and estimating visitation distributions induced by policy sequences.
method Learn predictive jumpy world models of multi-step dynamics, enhancing predictions with a consistency objective.
result Compositional planning with jumpy world models yields, on average, a 200% relative improvement over primitive actions on long-horizon tasks.
A2MT learns agents to select which modalities to acquire at test time.
problem Learning agents to select modalities for multimodal temporal data acquisition.
method Perceiver IO architecture for active acquisition of multimodal temporal data.
result Agents successfully learn cost-reactive acquisition behavior on real-world datasets.
CUDC collects diverse data for offline RL by predicting future states.
problem Challenges in collecting task-agnostic data for offline RL.
method Adaptive temporal distances for curiosity-driven data collection.
result CUDC outperforms existing unsupervised methods in offline RL tasks.
Hierarchical reinforcement learning has demonstrated significant success at solving difficult reinforcement learning (RL) tasks. Previous works have motivated the use of hierarchy by appealing to a number of intuitive benefits, including learning over temporally extended transitions, exploring over temporally extended …
A new method for embedding temporal relationships in graphs.
problem Limited performance of existing time-aware graph embedding methods.
method Integrates temporal smoothness and task-oriented negative sampling.
result Improves performance in various tasks, especially entity/relationship/temporal scoping prediction.
We present the ConditionaL Neural Network (CLNN) and the Masked ConditionaL Neural Network (MCLNN) designed for temporal signal recognition. The CLNN takes into consideration the temporal nature of the sound signal and the MCLNN extends upon the CLNN through a binary mask to preserve the spatial locality of the feature…
HTMRL uses HTM for RL, adapting faster to changing environments.
problem Adapting to non-stationary environments in RL.
method Strictly HTM-based RL algorithm.
result HTMRL adapts faster to changing environments in a 10-armed bandit.
In this work, we present a method for node embedding in temporal graphs. We propose an algorithm that learns the evolution of a temporal graph's nodes and edges over time and incorporates this dynamics in a temporal node embedding framework for different graph prediction tasks. We present a joint loss function that cre…
DANR improves network regularization for spatio-temporal data.
problem Inadequate edge weights compromise network regularization.
method Discrepancy-aware network regularization (DANR) with ADMM.
result DANR achieves improved performance on various tasks.
Recent studies have demonstrated the power of recurrent neural networks for machine translation, image captioning and speech recognition. For the task of capturing temporal structure in video, however, there still remain numerous open research questions. Current research suggests using a simple temporal feature pooling…
Enhances speech emotion recognition by adapting to varying time scales.
problem Robust emotion recognition from speech audio with temporal variations.
method Introduces multi-time-scale (MTS) convolutional layers to CNNs.
result MTS layers improve generalization, especially on smaller datasets.
PMP extends GNNs to handle past states efficiently.
problem Efficient querying of data structures dependent on previous states.
method Persistent Message Passing (PMP) which persists past states through new nodes.
result Significantly outperforms GNNs in handling out-of-distribution data.
Prediction is arguably one of the most basic functions of an intelligent system. In general, the problem of predicting events in the future or between two waypoints is exceedingly difficult. However, most phenomena naturally pass through relatively predictable bottlenecks---while we cannot predict the precise trajector…
Temporal Pattern Mining (TPM) is the problem of mining predictive complex temporal patterns from multivariate time series in a supervised setting. We develop a new method called the Fast Temporal Pattern Mining with Extended Vertical Lists. This method utilizes an extension of the Apriori property which requires a more…
Generative adversarial networks create realistic equity option market simulations.
problem Limited real-world data for training and evaluating option trading strategies.
method Recurrent and temporal convolutional architectures with state compression.
result GANs outperform classical methods on benchmark metrics.
Trained recurrent networks are powerful tools for modeling dynamic neural computations. We present a target-based method for modifying the full connectivity matrix of a recurrent network to train it to perform tasks involving temporally complex input/output transformations. The method introduces a second network during…
Reinforcement Learning (RL) algorithms can suffer from poor sample efficiency when rewards are delayed and sparse. We introduce a solution that enables agents to learn temporally extended actions at multiple levels of abstraction in a sample efficient and automated fashion. Our approach combines universal value functio…
TCGPN improves stock forecasting by capturing temporal correlation patterns.
problem Stock forecasting with minimal periodicity and large node numbers.
method TCGPN uses Temporal-Correlation fusion encoder and pre-training methods to handle large datasets.
result TCGPN achieves state-of-the-art results on real stock market data.
Unified model improves multi-task learning by accounting for temporal misalignment.
problem Poor predictive performance and uncertainty quantification due to temporal misalignment in multi-task learning.
method Uses Gaussian processes to model correlations and includes a monotonic warp of the input data to account for temporal misalignment.
result Improves predictive performance and uncertainty quantification in multi-task learning.
The data in many disciplines such as social networks, web analysis, etc. is link-based, and the link structure can be exploited for many different data mining tasks. In this paper, we consider the problem of temporal link prediction: Given link data for times 1 through T, can we predict the links at time T+1? If our da…
ExNODE uses ODE to model sets with permutation equivariance.
problem Capturing intra-set dependencies in unordered sets.
method Exchangeable Neural ODE (ExNODE) using ODE.
result ExNODE achieves permutation equivariance for set modeling.
Motivated by electricity consumption metering, we extend existing nonnegative matrix factorization (NMF) algorithms to use linear measurements as observations, instead of matrix entries. The objective is to estimate multiple time series at a fine temporal scale from temporal aggregates measured on each individual serie…
We introduce the Adaptive Skills, Adaptive Partitions (ASAP) framework that (1) learns skills (i.e., temporally extended actions or options) as well as (2) where to apply them. We believe that both (1) and (2) are necessary for a truly general skill learning framework, which is a key building block needed to scale up t…
TD-Flow improves long-term predictions in agent learning.
problem Cumulative errors in step-by-step inference of future states.
method Leverages flow-matching techniques and a novel Bellman equation to learn accurate geometric horizon models.
result Significantly reduces errors at long horizons compared to prior methods.
Temporal networks representing a stream of timestamped edges are seemingly ubiquitous in the real-world. However, the massive size and continuous nature of these networks make them fundamentally challenging to analyze and leverage for descriptive and predictive modeling tasks. In this work, we propose a general framewo…
LVTINO improves high-definition video restoration with consistent temporal details.
problem Restoring high-definition video with fine spatial detail and temporal consistency.
method LVTINO uses Video Consistency Models to bypass frame-by-frame image-based LDMs, achieving perceptual quality and computational efficiency.
result Significant perceptual improvements over current methods, achieving state-of-the-art quality with minimal evaluations.
The paper improves reinforcement learning stability and efficiency with a new theoretical framework.
problem Stability and efficiency in reinforcement learning, especially in data-scarce scenarios.
method Theoretical framework using resampled - and -statistics to model experience replay, applied to policy evaluation and kernel ridge regression.
result Significant improvements in stability and efficiency, particularly in data-scarce scenarios.
Improved incremental sequence classification with temporal consistency.
problem Updating predictions as new sequence elements are revealed.
method Temporal-difference learning and a temporal-consistency condition for successive predictions.
result Optimizing a novel loss function improves data efficiency and predictive accuracy.
Proposes a new model for complex multivariate event data.
problem Modeling complex multivariate event data with spatio-temporal dynamics.
method Integrates spatial information into latent state evolution through learned temporal and spatial decay dynamics.
result Successfully recovers sensible temporal and spatial intensity structure in multivariate spatio-temporal point patterns.
Quantum reservoir computing tackles noisy quantum computers for temporal tasks.
problem Efficiently process input sequences on noisy quantum computers.
method Quantum reservoir computing using dissipative quantum dynamics.
result Small and noisy quantum reservoirs can handle high-order nonlinear temporal tasks.
Novel deep learning model for multivariate time series prediction.
problem Challenges in multivariate time series prediction with correlations and complex temporal patterns.
method Temporal Tensor Transformation Network (TTNT) that transforms multivariate time series into tensors for improved feature extraction.
result TTNT outperforms state-of-the-art methods in window-based predictions across various tasks.
Time-variant value function transfer method for RL.
problem Transfer learning with time-variant task distributions.
method Variational approach leveraging temporal structure.
result The proposed method outperforms time-invariant approach in experiments.
Using reinforcement learning to learn control policies is a challenge when the task is complex with potentially long horizons. Ensuring adequate but safe exploration is also crucial for controlling physical systems. In this paper, we use temporal logic to facilitate specification and learning of complex tasks. We combi…
Meta-learning has emerged as an important framework for learning new tasks from just a few examples. The success of any meta-learning model depends on (i) its fast adaptation to new tasks, as well as (ii) having a shared representation across similar tasks. Here we extend the model-agnostic meta-learning (MAML) framewo…
Comparing Deep Learning Models for the Task of Volatility Prediction Using Multivariate Dataq-fin.ST
Study compares deep learning models for volatility prediction using multivariate data.
problem Predicting volatility using multivariate data.
method Evaluated multiple deep learning models including MLP, RNN, TCN, and Temporal Fusion Transformer.
result Temporal Fusion Transformer and TCN variants outperform classical models and shallow networks.
Using Deep Operators to Create Spatio-temporal Surrogates for Dynamical Systems under Uncertaintystat.ML
DeepONets enhance spatial-temporal surrogates for structural dynamics.
problem Creating full spatial-temporal surrogates for dynamical systems under uncertainty.
method Proposed Full-Field Extended DeepONet (FExD) to learn full solution operator across multiple degrees of freedom.
result FExD achieves superior accuracy and computational efficiency compared to other models.
Language evolves over time in many ways relevant to natural language processing tasks. For example, recent occurrences of tokens 'BERT' and 'ELMO' in publications refer to neural network architectures rather than persons. This type of temporal signal is typically overlooked, but is important if one aims to deploy a mac…
Efficient Hierarchical Bayesian Inference for Spatio-temporal Regression Models in Neuroimagingstat.ML
Novel Bayesian framework for spatio-temporal neuroimaging data.
problem Inference on multi-task sparse hierarchical regression models with complex spatio-temporal dynamics.
method Flexible hierarchical Bayesian framework with Kronecker product covariance structure, majorization-minimization optimization, and Riemannian geometry.
result Improved performance on synthetic and real M/EEG data.
MTRGL learns temporal correlations from multi-modal data for improved pair trading.
problem Discerning temporal correlations among financial entities.
method Combines time series data and discrete features into a temporal graph, using a memory-based temporal graph neural network.
result MTRGL outperforms traditional methods in temporal graph link prediction and pair trading.
DMSTF models spatio-temporal data with deep Markov priors.
problem Analyzing nonlinear multimodal spatio-temporal dynamics.
method Deep Markov spatio-temporal factorization with stochastic variational inference.
result DMSTF outperforms other methods in predictive performance and clustering.
Neuro-inspired recurrent neural network algorithms, such as echo state networks, are computationally lightweight and thereby map well onto untethered devices. The baseline echo state network algorithms are shown to be efficient in solving small-scale spatio-temporal problems. However, they underperform for complex task…