arXiv research

This work compresses sequences by treating them as continuous-time processes, enabling efficient discretization.

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…

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…

Develops a framework for modeling set-valued data in continuous-time.

Continuous time analysis of bubble formation in harmonic maps.

Paper introduces efficient methods for probabilistic querying of event sequences.

This paper introduces a new neural ODE model for continuous-time sequence generation.

Rough Transformers improve time series modeling with lower costs and better performance.

ADD-THIN improves TPP forecasting by handling long-term data sequences.

Neural SDEs model continuous sequences using neural networks.

S2P2 model improves predictive likelihoods for MTPPs.

We address the problem of combining sequence models of symbolic music with user defined constraints. For typical models this is non-trivial as only the conditional distribution of each symbol given the earlier symbols is available, while the constraints correspond to arbitrary times. Previously this has been addressed …

Study shows financial value of weak information converges in discrete vs continuous markets.

CT-OT Flow estimates continuous-time dynamics from discrete snapshots.

Improved neural models for diverse user event sequences.

TG-GAN models dynamic graph evolution for continuous-time temporal graphs.

This paper considers a sequence of discrete-time random walk markets with a safe and a single risky investment opportunity, and gives conditions for the existence of arbitrages or free lunches with vanishing risk, of the form of waiting to buy and selling the next period, with no shorting, and furthermore for weak conv…

Representations of sequential data are commonly based on the assumption that observed sequences are realizations of an unknown underlying stochastic process, where the learning problem includes determination of the model parameters. In this context the model must be able to capture the multi-modal nature of the data, w…

In the continuous time mean-variance model, we want to minimize the variance (risk) of the investment portfolio with a given mean at terminal time. However, the investor can stop the investment plan at any time before the terminal time. To solve this kind of problem, we consider to minimize the variances of the investm…

We study the optimal investment problem for a continuous time incomplete market model such that the risk-free rate, the appreciation rates and the volatility of the stocks are all random; they are assumed to be independent from the driving Brownian motion, and they are supposed to be currently observable. It is shown t…

Model proposes neural network for continuous time dynamics with inductive biases.

LS4 models time-series with latent states, outperforming previous methods.

Survey on modeling event sequences through temporal processes.

Develops a new point process model for detecting neural spike sequences.

The discrete-time GARCH methodology which has had such a profound influence on the modelling of heteroscedasticity in time series is intuitively well motivated in capturing many `stylized facts' concerning financial series, and is now almost routinely used in a wide range of situations, often including some where the d…

The original Kelly criterion provides a strategy to maximize the long-term growth of winnings in a sequence of simple Bernoulli bets with an edge, that is, when the expected return on each bet is positive. The objective of this work is to consider more general models of returns and the continuous time, or high frequenc…

We prove the existence of optimal strategies for agents with cumulative prospect theory preferences who trade in a continuous-time illiquid market, transcending known results which pertained only to risk-averse utility maximizers. The arguments exploit an extension of Skorohod's representation theorem for tight sequenc…

In this paper, two Q-learning (QL) methods are proposed and their convergence theories are established for addressing the model-free optimal control problem of general nonlinear continuous-time systems. By introducing the Q-function for continuous-time systems, policy iteration based QL (PIQL) and value iteration based…

Method learns CTMC models from steady-state data, predicting unseen states.

Improved prediction algorithm for 'easy' sequences with reduced regret.

In this paper we propose the notion of continuous-time dynamic spectral risk-measure (DSR). Adopting a Poisson random measure setting, we define this class of dynamic coherent risk-measures in terms of certain backward stochastic differential equations. By establishing a functional limit theorem, we show that DSRs may …

Many events occur in the world. Some event types are stochastically excited or inhibited---in the sense of having their probabilities elevated or decreased---by patterns in the sequence of previous events. Discovering such patterns can help us predict which type of event will happen next and when. We model streams of d…

Novel approach to learn CTBNs from data with minimal interventions.

This primer explains diffusion models in general state spaces.

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…

Paper introduces second-order Esscher densities for continuous-time models.

Faster policy learning via continuous-time gradients.

EventFlow forecasts event sequences without autoregression, improving accuracy.

Geometric tempering improves sampling from distributions, with exponential convergence rates.

Continuous time framework for discrete data denoising models.

In this paper, a method of prediction on continuous time series variables from the production or flow -- an LSTM algorithm based on multivariate tuning -- is proposed. The algorithm improves the traditional LSTM algorithm and converts the time series data into supervised learning sequences regarding industrial data's f…

Survey of TPPs from Bayesian, neural, and LLM perspectives.

Improved MLE for Hawkes Processes stabilizes unstable optimization.

Develops DPG methods for continuous-time RL with deterministic policies.

Study analyzes a new algorithm for complex optimization problems.

GTEA learns node representations in temporal interaction graphs.

Rough Transformers improve efficiency for medical time-series data.

In many physical, social or economical phenomena we observe changes of a studied quantity only in discrete, irregularly distributed points in time. The stochastic process used by physicists to describe this kind of variables is the Continuous Time Random Walk (CTRW). Despite the popularity of this type of stochastic pr…