arXiv research

FedSARSA converges with heterogeneous agents, achieving linear speed-up.

Paper adapts ACI for online multi-step time-series forecasting with coverage guarantees.

Model-based reinforcement learning is an appealing framework for creating agents that learn, plan, and act in sequential environments. Model-based algorithms typically involve learning a transition model that takes a state and an action and outputs the next state---a one-step model. This model can be composed with itse…

This work analyzes CoT prompting methods from a statistical estimation perspective.

Paper presents a copula-based method to efficiently generate correlated sample paths from multi-step time series models.

The paper introduces a multi-step loss function to improve model-based reinforcement learning.

The paper addresses Dyna-style RL's value hallucination issue by proposing a new algorithm.

Paper proposes a dual-level approach for multi-step forecasting of dynamical systems.

Neural CDEs correct errors in learned time-series models for better forecasting.

JANET improves time series prediction with adaptive uncertainty regions.

We examine the impact of learning Lipschitz continuous models in the context of model-based reinforcement learning. We provide a novel bound on multi-step prediction error of Lipschitz models where we quantify the error using the Wasserstein metric. We go on to prove an error bound for the value-function estimate arisi…

In many forecasting applications, it is valuable to predict not only the value of a signal at a certain time point in the future, but also the values leading up to that point. This is especially true in clinical applications, where the future state of the patient can be less important than the patient's overall traject…

This note provides an error bound for the Hartman-Watson integral's leading term.

The purpose of this paper is to propose a time-varying vector autoregressive model (TV-VAR) for forecasting multivariate time series. The model is casted into a state-space form that allows flexible description and analysis. The volatility covariance matrix of the time series is modelled via inverted Wishart and singul…

The paper calculates prices for multi-step barrier options under the Black-Scholes model.

Efficiently optimizes expensive functions with multi-step lookahead using one-shot optimization.

Develops AMITE for analyzing neural network nonlinearities.

Recently, a new multi-step temporal learning algorithm, called $Q(σ)$, unifies $n$-step Tree-Backup (when $σ=0$) and $n$-step Sarsa (when $σ=1$) by introducing a sampling parameter $σ$. However, similar to other multi-step temporal-difference learning algorithms, $Q(σ)$ needs much memory consumption and computation tim…

Proposes QDF to improve multi-step time-series forecasting.

The paper explores dynamic ensembles for multi-step forecasting.

Model predicts stock price changes and forecasts using tokenized data.

In this report, we derive a non-negative series expansion for the Jensen-Shannon divergence (JSD) between two probability distributions. This series expansion is shown to be useful for numerical calculations of the JSD, when the probability distributions are nearly equal, and for which, consequently, small numerical er…

Reinforcement learning has attracted great attention recently, especially policy gradient algorithms, which have been demonstrated on challenging decision making and control tasks. In this paper, we propose an active multi-step TD algorithm with adaptive stepsizes to learn actor and critic. Specifically, our model cons…

Deep learning has achieved impressive prediction performance in the field of sequence learning recently. Dissolved oxygen prediction, as a kind of time-series forecasting, is suitable for this technique. Although many researchers have developed hybrid models or variant models based on deep learning techniques, there is…

Energy price forecasting is a relevant yet hard task in the field of multi-step time series forecasting. In this paper we compare a well-known and established method, ARMA with exogenous variables with a relatively new technique Gradient Boosting Regression. The method was tested on data from Global Energy Forecasting …

The paper uses polyhedral expansions to capture the shape of compact metric spaces.

Model-based reinforcement learning (MBRL) aims to learn a dynamic model to reduce the number of interactions with real-world environments. However, due to estimation error, rollouts in the learned model, especially those of long horizons, fail to match the ones in real-world environments. This mismatching has seriously…

Proposes a graph dynamics prior for more accurate relational inference.

The main goal of the paper is to address the issue of the existence of Kempf's distortion function and the Tian-Yau-Zelditch (TYZ) asymptotic expansion for the Kepler manifold - an important example of non compact manfold. Motivated by the recent results for compact manifolds we construct Kempf's distortion function an…

Stratify unifies and improves multi-step forecasting strategies.

Multi-step passenger demand forecasting is a crucial task in on-demand vehicle sharing services. However, predicting passenger demand over multiple time horizons is generally challenging due to the nonlinear and dynamic spatial-temporal dependencies. In this work, we propose to model multi-step citywide passenger deman…

Achieving artificial visual reasoning - the ability to answer image-related questions which require a multi-step, high-level process - is an important step towards artificial general intelligence. This multi-modal task requires learning a question-dependent, structured reasoning process over images from language. Stand…

When environmental interaction is expensive, model-based reinforcement learning offers a solution by planning ahead and avoiding costly mistakes. Model-based agents typically learn a single-step transition model. In this paper, we propose a multi-step model that predicts the outcome of an action sequence with variable …

Looped Transformers learn to implement multi-step gradient descent for in-context learning.

Multi-step temporal difference (TD) learning is an important approach in reinforcement learning, as it unifies one-step TD learning with Monte Carlo methods in a way where intermediate algorithms can outperform either extreme. They address a bias-variance trade off between reliance on current estimates, which could be …

Study non-parametric value function estimation from a single path.

New theory explains how strong models can learn from weak ones.

For the efficient compensation of fiber nonlinearity, one of the guiding principles appears to be: fewer steps are better and more efficient. We challenge this assumption and show that carefully designed multi-step approaches can lead to better performance-complexity trade-offs than their few-step counterparts.

We provide faster algorithms for the problem of Gaussian summation, which occurs in many machine learning methods. We develop two new extensions - an O(Dp) Taylor expansion for the Gaussian kernel with rigorous error bounds and a new error control scheme integrating any arbitrary approximation method - within the best …

Time series forecasting gets much attention due to its impact on many practical applications. Higher-order neural network with recurrent feedback is a powerful technique which used successfully for forecasting. It maintains fast learning and the ability to learn the dynamics of the series over time. For that, in this p…

We consider closed-form approximations for European put option prices within the Heston and GARCH diffusion stochastic volatility models with time-dependent parameters. Our methodology involves writing the put option price as an expectation of a Black-Scholes formula and performing a second-order Taylor expansion aroun…

New Hermite approximations accelerate convergence with adaptive coordinate transformations.

Multi-step ahead forecasting is still an open challenge in time series forecasting. Several approaches that deal with this complex problem have been proposed in the literature but an extensive comparison on a large number of tasks is still missing. This paper aims to fill this gap by reviewing existing strategies for m…

In its simplest form, the traffic flow prediction problem is restricted to predicting a single time-step into the future. Multi-step traffic flow prediction extends this set-up to the case where predicting multiple time-steps into the future based on some finite history is of interest. This problem is significantly mor…

Paper provides Edgeworth expansions for network moments, improving accuracy of sampling distributions.

Diffusion-VAE tackles multi-step stock price prediction with stochastic noise.

Bagging is a device intended for reducing the prediction error of learning algorithms. In its simplest form, bagging draws bootstrap samples from the training sample, applies the learning algorithm to each bootstrap sample, and then averages the resulting prediction rules. We extend the definition of bagging from stati…

Quantile deep learning improves time series prediction accuracy and uncertainty quantification.