Paper: arXiv 2311.12330

Abstract

Although stochastic models driven by latent Markov processes are widely used, the classical importance sampling methods based on the exponential tilting for these models suffers from the difficulties in computing the eigenvalues and associated eigenfunctions and the plausibility of the indirect asymptotic large deviation regime for the variance of the estimator. We propose a general importance sampling framework that twists the observable and latent processes separately using a link function that directly minimizes the estimator’s variance. An optimal choice of the link function is chosen within the locally asymptotically normal family. We show the logarithmic efficiency of the proposed estimator. As applications, we estimate an overflow probability under a pandemic model and the CoVaR, a measurement of the co-dependent financial systemic risk. Both applications are beyond the scope of traditional importance sampling methods due to their nonlinear features.

Complexity vs Empirical Score

  • Math Complexity: 8.5/10
  • Empirical Rigor: 4.0/10
  • Quadrant: Lab Rats — theoretically deep, empirically untested

Why this score: The paper presents advanced theoretical concepts such as locally asymptotically normal families and logarithmic efficiency, which require sophisticated mathematical tools; while it includes numerical examples and simulation applications, it lacks the backtest-ready, code-heavy implementation typical of high empirical rigor.

Research Flowchart

  flowchart TD
  A["Research Goal: Develop efficient IS<br/>for latent Markov models"] --> B{"Key Methodology"}
  B --> C["Separate twisting of observable<br/>and latent processes"]
  B --> D["Optimal link function via<br/>locally asymptotically normal family"]
  C & D --> E["Computational Process:<br/>Minimize estimator variance"]
  E --> F["Data/Inputs:<br/>Nonlinear Markov processes"]
  E --> G["Prove Logarithmic Efficiency"]
  F --> H["Applications & Outcomes"]
  G --> H
  subgraph H ["Applications & Outcomes"]
      H1["Pandemic Model:<br/>Overflow probability estimation"]
      H2["Finance (CoVaR):<br/>Systemic risk measurement"]
  end
  H --> I["Key Outcome:<br/>General framework beyond<br/>traditional exponential tilting"]

Cited References (123)

  1. Importance sampling for portfolio credit risk (2005)
  2. Large deviations of uniformly recurrent Markov additive processes (1985)
  3. On moments of the first ladder height of random walks with small drift (1992)
  4. Limit theorems for stopped functionals of M arkov renewal processes (1999)
  5. Stochastic Simulation: Algorithms and Analysis (2007)
  6. Approximating martingales for variance reduction in M arkov process simulation (2002)
  7. Numerical Solution of Stochastic Differential Equations (2010)
  8. A new approach to the limit theory of recurrent M arkov chains (1978)
and 115 more
  1. Strict stationary of generalized autoregressive processes (1992)
  2. Moderate deviations and associated L aplace approximations for sums of independent random vectors (1992)
  3. An Introduction to the Bootstrap (1994)
  4. Random difference equations and renewal theory for products of random matrices (1973)
  5. SPRT and CUSUM in hidden Markov models (2003)
  6. Asymptotic behavior for M arkovian iterated function systems (2021)
  7. Iterated random functions (1999)
  8. Introduction to Rare Event Simulation (2004)
  9. Importance sampling in the Monte Carlo study of sequential tests (1976)
  10. Importance sampling techniques for the multidimensional ruin problem for general Markov additive sequences of random vectors (2002)
  11. Importance sampling, large deviations, and differential games (2004)
  12. On L yapunov inequalities and subsolutions for efficient importance sampling (2012)
  13. Efficient exponential tilting for portfolio credit risk (2019) — link
  14. On an automatic and optimal importance sampling approach with applications in finance (2016)
  15. Counterexamples in importance sampling for large deviations probabilities (1997)
  16. Portfolio value-at-risk with heavy-tailed risk factors (2002)
  17. Efficient simulation of value-at-risk with heavy-tailed risk factors (2011)
  18. Efficient importance sampling for events of moderate deviations with applications (2004)
  19. Genealogical particle analysis of rare events (2005)
  20. Variance reduction for Monte Carlo simulation in a stochastic volatility environment (2002)
  21. Markov additive processes I. Eigenvalue properties and limit theorems (1987)
  22. Markov additive processes II. Large deviations (1987)
  23. Markov additive processes. I (1972)
  24. Markov additive processes. II (1972)
  25. Poisson equation, moment inequalities and quick convergence for Markov random walks (2000)
  26. Computing rare-event probabilities for affine models and general state space Markov processes (2011)
  27. Options on realized variance by transform methods: a non-affine stochastic volatility model (2012)
  28. A parametric nonlinear model of term structure dynamics (1999)
  29. CoVaR (2016)
  30. Systemic risk measurement: Multivariate GARCH estimation of CoVaR (2013)
  31. Time-varying systemic risk: Evidence from a dynamic copula model of cds spreads (2018)
  32. Multi-CoVaR and Shapley value: a systemic risk measure (2013)
  33. Asymptotically optimal importance sampling and stratification for pricing path-dependent options (1999)
  34. Monte Carlo methods for security pricing (1997)
  35. A sequential Monte Carlo approach to computing tail probabilities in stochastic models (2011)
  36. Saddlepoint approximations and nonlinear boundary crossing probabilities of M arkov random walks (2003)
  37. Estimation in hidden M arkov models via efficient importance sampling (2007)
  38. Uniform M arkov renewal theory and ruin probabilities in M arkov random walks (2004)
  39. Multivariate Markov-switching models and tail risk interdependence (2013) — link
  40. VAR for VaR : Measuring tail dependence using multivariate regression quantiles (2015)
  41. Monte Carlo methods for value-at-risk and conditional value-at-risk: a review (2014)
  42. Markov Chains and Stochastic Stability (2012)
  43. Asymptotically efficient strategies for a stochastic scheduling problem with order constraints (2000)
  44. Analysis of an importance sampling estimator for tandem queues (1995)
  45. Markov-modulated single-server queueing systems (1994)
  46. Fast simulation of rare events in queueing and reliability models (1995)
  47. Stochastic optimization with importance sampling for regularized loss minimization (2015)
  48. Stochastic gradient descent as approximate bayesian inference (2017)
  49. Adam: A method for stochastic optimization (2014) — link
  50. A primer on stochastic epidemic models: Formulation, numerical simulation, and analysis (2017)
  51. Data-based analysis, modelling and forecasting of the COVID-19 outbreak (2020)
  52. Importance sampling for stochastic simulations (1989)
  53. On large deviations theory and asymptotically efficient Monte Carlo estimation (1990)
  54. On importance resampling for the bootstrap (1991)
  55. On the choice of alternative measures in importance sampling with Markov chains (1995)
  56. Potentially unlimited variance reduction in importance sampling of Markov chains (1996)
  57. Adaptive importance sampling technique for Markov chains using stochastic approximation (2006)
  58. Optimal importance sampling parameter search for L 'e vy processes via stochastic approximation (2009)
  59. Optimal importance sampling for credit portfolios with stochastic approximation (2005)
  60. Optimizing adaptive importance sampling by stochastic approximation (2018)
  61. Rare-event simulation techniques: An introduction and recent advances (2006)
  62. Markov-Modulated Processes and Semiregenerative Phenomena (2008)
  63. State-dependent importance sampling for rare-event simulation: An overview and recent advances (2012)
  64. A contribution to the mathematical theory of epidemics (1927)
  65. Asymptotics in Statistics: Some Basic Concepts (2012)
  66. Asymptotic expansions in multidimensional Markov renewal theory and first passage times for Markov random walks (2001)
  67. Asymptotic representations for importance-sampling estimators of value-at-risk and conditional value-at-risk (2010)
  68. A general framework of importance sampling for value-at-risk and conditional value-at-risk (2009)
  69. Regime switching models (2010)
  70. Affine point processes: Approximation and efficient simulation (2015)
  71. Duality theory and simulation in financial engineering (2003)
  72. Pricing American options: A duality approach (2004)
  73. Evaluating portfolio policies: A duality approach (2006)
  74. Monte Carlo Methods in Financial Engineering (2004)
  75. Markov Chain Monte Carlo : An introduction for epidemiologists (2013)
  76. Bank Risk Management: Theory (1999)
  77. Exploring Monte Carlo simulation applications for project management (2007)
  78. Combining Monte Carlo simulation with heuristics for solving the inventory routing problem with stochastic demands (2012)
  79. Positive Harris recurrence of the CIR process and its applications (2013)
  80. Stationarity and geometric ergodicity of BEKK multivariate GARCH models (2011)
  81. Asymptotic theory for a vector ARMA-GARCH model (2003)
  82. Discrete-Time Affine$^ Q $ Term Structure Models with Generalized Market Prices of Risk (2010)
  83. Simulation of square-root processes (2010)
  84. A probabilistic proof of the P erron– F robenius theorem (2023)
  85. Importance sampling for M arkov chains: Asymptotics for the variance (1994)
  86. A guide to sample average approximation (2015)
  87. Estimation of particle transmission by random sampling (1951)
  88. Statistical methods in neutron diffusion (1947)
  89. A modified SIRD model to study the evolution of the COVID-19 pandemic in Spain (2021)
  90. EKF-SIRD model algorithm for predicting the coronavirus (COVID-19) spreading dynamics (2022)
  91. Chinese and Italian COVID-19 outbreaks can be correctly described by a modified SIRD model (2020)
  92. Forecasting Covid-19 in the United Kingdom: A dynamic SIRD model (2022)
  93. Stability of nonlinear AR-GARCH models (2008)
  94. A tutorial on the cross-entropy method (2005)
  95. The Cross-Entropy Method: A Unified Approach to Combinatorial Optimization, Monte-Carlo Simulation and Machine Learning (2004)
  96. Subsolutions of an I saacs equation and efficient schemes for importance sampling (2007)
  97. Dynamic Importance Sampling for Queueing Networks (2007)
  98. Dynamic Importance Sampling for Uniformly Recurrent M arkov Chains (2005)
  99. State-dependent importance sampling for regularly varying random walks (2008)
  100. State-dependent importance sampling and large deviations (2006)
  101. Importance sampling for multiscale diffusions (2012)
  102. Importance sampling for slow-fast diffusions based on moderate deviations (2020)
  103. Optimal importance sampling with explicit formulas in continuous time (2008)
  104. Small noise expansion and importance sampling (1997)
  105. Variance reduction for simulated diffusions (1994)
  106. Moment explosions and stationary distributions in affine diffusion models (2010)
  107. Portfolio Credit Risk with Extremal Dependence: Asymptotic Analysis and Efficient Simulation (2008)
  108. Importance sampling for a simple M arkovian intensity model using subsolutions (2022)
  109. A deep learning approach for rare event simulation in diffusion processes (2024)
  110. Solving high-dimensional Hamilton–Jacobi–Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space (2021)
  111. Deep learning for Markov chains: Lyapunov functions, Poisson’s equation, and stationary distributions (2026)
  112. Computing VaR and CVaR using stochastic approximation and adaptive unconstrained importance sampling (2009)
  113. Unconstrained recursive importance sampling (2010)
  114. Adaptive importance sampling for efficient stochastic root finding and quantile estimation (2024)
  115. Stochastic Optimization with Optimal Importance Sampling (2025) — link

0 of 123 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.