arXiv research

Analyzes non-Markovian environments in stochastic approximation.

Stochastic differential equation approximation for linear TD(0) under Markovian noise

Paper establishes convergence rates and concentration bounds for stochastic approximation and reinforcement learning with Markovian noise.

We develop a Markovian approximation for SVV models to compute hedging strategies.

We simplify a complex volatility model to make it easier to price options.

This work analyzes nonexpansive stochastic approximations with Markovian noise, proving convergence in reinforcement learning.

Improved approximations for rough Heston model reduce errors.

Paper derives convergence rates and confidence intervals for LSA with Markovian noise.

Paper analyzes CLT for TTSA with Markovian noise, broadening its applications.

In this paper, we present a discrete-type approximation scheme to solve continuous-time optimal stopping problems based on fully non-Markovian continuous processes adapted to the Brownian motion filtration. The approximations satisfy suitable variational inequalities which allow us to construct $ε$-optimal stopping tim…

State spaces of multifactor approximations of nonnegative Volterra processes are linear transformations of the nonnegative orthant.

Sparse Markovian Gaussian processes improve probabilistic model inference for large datasets.

Study on bias and extrapolation in LSA with Markovian data, showing bias reduction with Richardson-Romberg extrapolation.

Study on statistical inference for nonlinear stochastic approximation with Markovian data.

Study on bias of constant-step stochastic approximation with Markovian noise.

Two signature-based methods solve optimal stopping in non-Markovian frameworks.

Paper analyzes finite-time performance of SA in RL with Markovian noise.

Paper examines constant stepsize in LSA for Markovian data inference.

We analyze SA with Markovian data and nonlinear updates, overcoming prior limitations.

This study improves convergence of two-timescale SA under Markovian noise in reinforcement learning.

New bounds for SA with arbitrary norm contractions and Markovian noise.

Unified analytical tool for non-Markovian jump processes.

Paper analyzes Greedy-GQ for reinforcement learning with Markovian noise.

The ADO-Heston model approximates market implied skew in vanilla options.

Kernel analog forecasting studied for multiscale systems.

In this paper, we present a Longstaff-Schwartz-type algorithm for optimal stopping time problems based on the Brownian motion filtration. The algorithm is based on Leão, Ohashi and Russo and, in contrast to previous works, our methodology applies to optimal stopping problems for fully non-Markovian and non-semimartinga…

Paper provides exponential convergence guarantees for Iterative Markovian Fitting.

Paper analyzes convergence of Adam-type RL algorithms under Markovian sampling.

The paper analyzes convergence rates for stochastic approximation and reinforcement learning.

The paper develops methods to price options under rough volatility models using BSPDEs.

A new model for S&P 500 and VIX options pricing and calibration.

Optimal strategies are found for a repeated betting game using diffusion approximation.

This paper develops a Hoeffding inequality for the partial sums $\sum_{k=1}^n f (X_k)$, where $\{X_k\}_{k \in \mathbb{Z}_{> 0}}$ is an irreducible Markov chain on a finite state space $S$, and $f : S \to [a, b]$ is a real-valued function. Our bound is simple, general, since it only assumes irreducibility and finiteness…

Paper tackles non-Markovian control problems with new learning methods.

Rough volatility models are very appealing because of their remarkable fit of both historical and implied volatilities. However, due to the non-Markovian and non-semimartingale nature of the volatility process, there is no simple way to simulate efficiently such models, which makes risk management of derivatives an int…

A new measure predicts deep learning model performance.

Paper analyzes convergence of decentralized algorithms with noise and bias.

Unified framework for finite-sample RL algorithms using Lyapunov theory.

The paper analyzes stability of random matrix products with Markovian noise.

Signature portfolios approximate optimal wealth in non-Markovian markets.

A new method for online VI in SSMs using asymptotic contrast.

Efficient simulation scheme for rough Heston model reduces computational cost.

The paper provides mean-square error bounds for stochastic approximation algorithms.

Paper proves large deviation principle for stochastic approximations.

New algorithm solves complex stopping problems with robust optimization.

Maximal concentration bounds for stochastic approximation with heavy-tailed noise.

NO approximates non-Markovian BSDEs with polynomial scaling in 1/ε.

We describe a Markov latent state space (MLSS) model, where the latent state distribution is a decaying mixture over multiple past states. We present a simple sampling algorithm that allows to approximate such high-order MLSS with fixed time and memory costs.