Library · Simulation & modelling
What Monte Carlo Simulation got wrong, from 66 theses
Summary written by a model from the records below: Monte Carlo methods encounter critical operational limitations across engineering, physical transport, and statistical applications due to severe computational costs and slow convergence. Researchers frequently reject or abandon these stochastic simulations when statistical noise, correlation distortions, rare event estimation failures, and local mode entrapment compromise overall model fidelity. These records come from graduate theses, 2021 to 2026, each labeled with its degree where the repository states it, and each links to its thesis. They were extracted by language models reading the full text, so treat each as a lead to read, not a verdict.
Plus 8 problems the authors left open, listed at the end.
Failure modes, by theses reporting them
Select a mode to jump to its records.
Prohibitive computational cost and scaling bottlenecks in high-dimensional or iterative systems
Repeatedly evaluating Monte Carlo simulations inside optimization loops, dynamic programming updates, or large network models leads to intractable runtimes. In high-dimensional latent spaces and complex multi-machine systems, obtaining adequate estimation accuracy requires computational budgets that exceed practical operational limits.
Tried and failed
Monte Carlo simulation with fine mesh resolution applied to wildfire spread modeling. Outcome: did not converge. Reason: fine mesh stochastic simulations required thousands of runs to reach target error, exceeding practical computational budgets
Wildfire simulations to protect rural communities and avoid dire evacuations · Imperial · PhD
Considered and rejected
Considered and rejected: Rejected test-set MSE stopping criteria in dynamic programming because evaluating conditional expectations via Monte Carlo at every test state was computationally prohibitive.
Parsimonious Online Learning with Kernels and Random Features with Applications to Stochastic Optimal Control · EPFL · PhD
Considered and rejected
Considered and rejected: Rejected the Monte Carlo method for angular directional discretisation due to excessive computational cost required to reduce statistical sampling error.
CFD modelling of continuous baking tunnel ovens · Imperial · PhD
Considered and rejected
Considered and rejected: Rejected standard Monte Carlo simulation for multiscale tissue uncertainty propagation due to prohibitive computational burden.
Data analytics and mathematical modeling to advance cardiac care · Texas Tech · PhD
Considered and rejected
Considered and rejected: Rejected Monte Carlo NLS (MC-NLS) formulation for practical circuit simulations due to computational inefficiency.
Switching Dynamics in Ferroelectric Hf₀.₅Zr₀.₅O₂ Devices: Experiments and Models · MIT · PhD
Considered and rejected
Considered and rejected: Rejected Monte-Carlo simulation for compressor station availability evaluation due to high computational time, cost of execution, and lower precision compared to analytical binomial methods.
Introduction of social benefits to the tera – gas turbines and pipelines · Cranfield · PhD
Considered and rejected
Considered and rejected: Rejected transported PDF methods solved via stochastic Monte-Carlo particles for practical engine simulations due to prohibitive computational expense.
Conditional source-term estimation evaluations for partially-premixed flames · Oxford · PhD
Considered and rejected
Considered and rejected: Hamiltonian Monte Carlo / BAT.jl was rejected for KaFit due to the prohibitive computational cost of numerical finite-difference gradients in non-analytic models.
An Optimized Bayesian Analysis Framework for the KATRIN Experiment · MIT · PhD
Considered and rejected
Considered and rejected: Rejected exact likelihood integration via MCMC/Monte Carlo due to prohibitive computational costs in high-dimensional latent space q.
Semi-supervised and Representation Learning for Improved Classification and Stratification in EHR Data · Harvard · PhD
Considered and rejected
Considered and rejected: Directly incorporating stochastic Monte Carlo buckling simulations into the early-stage optimization loop was rejected due to prohibitive computational effort.
Integrative Form Finding and AI-Driven Human-in-the-Loop approach for Structural Optimization in Long-Span Architectural Design · Politecnico di Torino · PhD
Considered and rejected
Considered and rejected: Rejected solving the KKT system (2.6) directly via Monte Carlo gradient descent due to computational intractability of evaluating expected overage/underage integrals and derivatives.
Constrained Inventory Optimization on Complex Warehouse Networks · MIT · PhD
Considered and rejected
Considered and rejected: Rejected relying solely on Monte Carlo approximations or amortized explainers in isolation due to the slow inference convergence of Monte Carlo methods and the high approximation error of amortized models
Epistemic Limits of Trustworthy Machine Learning · Harvard · PhD
Considered and rejected
Considered and rejected: Rejected high-resolution photon Monte Carlo radiative transport (Prem et al. 2019) because rovibrational explicit modeling was computationally prohibitive and existing opacity model had <1% error.
Simulating Tvashtar's plume observed during the 2007 New Horizons Io flyby · UT Austin · PhD
Considered and rejected
Considered and rejected: Rejected full discrete stochastic Monte Carlo microsimulation in favor of analytical integration/multiplication directly on survival functions to save computation time.
Accounting for Heterogeneity in Health Decision Analysis · Harvard · PhD
Tried and failed
ensemble Markov Chain Monte Carlo sampling applied to multi-field cosmological inflation models. Outcome: infeasible cost. Reason: running chains to standard autocorrelation convergence thresholds required computationally prohibitive sample counts
Cosmic Echoes of the Early Universe: From Primordial Black Holes to Gravitational Waves · MIT · PhD
Considered and rejected
Considered and rejected: Markov-Chain Monte Carlo (MCMC) sampling for Bayesian harmonic inference; rejected because it became computationally intractable when scaling across spatially coherent networks of thousands of nodes.
Spatiotemporal tidal prediction and analysis through physics-informed machine learning · Oxford · PhD
Considered and rejected
Considered and rejected: Rejected joint likelihood inference via Monte Carlo EM due to high computational intensity and convergence issues.
Multivariate One-Sided Tests for Nonlinear Mixed-Effects Models with Incomplete Data · York University · PhD
Considered and rejected
Considered and rejected: Rejected direct sampling from raw Monte Carlo posterior histograms via MCMC/Metropolis-Hastings as prohibitively cumbersome and inefficient compared to parametric variational inference.
Sampling noise, non-differentiability, and numerical instability in optimization and recursion loops
Stochastic sampling introduces high variance, heteroskedasticity, and non-differentiable step behavior that disrupts gradient-based trajectory optimization. In iterative recursions and dynamic networks, this stochastic instability causes chaotic divergence, unphysical particle losses, or failure to reach steady-state balance.
Tried and failed
least squares Monte Carlo simulation applied to multi-uncertainty real options valuation. Outcome: unstable. Reason: regression exhibited severe heteroskedasticity across the multi-uncertainty life-cycle state space
Strategic investment decisions in remanufacturing and recycling for economic sustainability: An analysis using real options-based models · Iowa State · PhD
Tried and failed
Monte Carlo scenario generation with rolling volatility applied to stochastic asset allocation models. Outcome: unstable. Reason: scenario generation failed uniformity tests under true empirical volatility without artificial parameter dampening
Improving time series and cross-sectional momentum trading strategies using stochastic programming · Iowa State · PhD
Considered and rejected
Considered and rejected: Rejected using naive Monte Carlo simulation to evaluate expectation in state evolution for high dimensions (p in thousands) due to instability and inefficiency, replacing it with quantile discretization and closed-form conditional expectation.
Algorithmic Analysis And Statistical Inference Of Sparse Models In High Dimension · Penn · PhD
Tried and failed
single-batch Monte Carlo relaxation applied to coupled multiphysics transient simulations. Outcome: did not converge. Reason: extreme statistical noise stagnates convergence despite dampening numerical oscillations
Modeling Feedback Effects of Transient Nuclear Systems Using Monte Carlo · MIT · PhD
Tried and failed
Monte Carlo particle transport in high-fidelity CAD geometry applied to divertor vacuum pump particle balance. Outcome: unstable. Reason: caused numerical instability and unphysical particle loss instead of reaching steady-state balance
Understanding the Mechanisms that Determine the Edge Electron Density Profile in Tokamaks · MIT · PhD
Considered and rejected
Considered and rejected: Rejected direct differentiation of empirical Monte Carlo sums because derivatives become piecewise constant or zero, destroying convergence rates.
Multi-Level Monte Carlo Methods for Uncertainty Quantification and Risk-Averse Optimisation · EPFL · PhD
Considered and rejected
Considered and rejected: Rejected using the direct mode of Monte Carlo simulated estimates for progress projection due to instability when multiple local modes exist.
Deep Learning Classification of Spinal Osteoporotic Compression Fractures on Radiographs · University of Washington · PhD
Considered and rejected
Considered and rejected: Rejected Monte Carlo risk evaluation within the trajectory optimization loop due to non-smoothness, non-differentiability, and high sample complexity.
Considered and rejected
Considered and rejected: Removed statistical control variables from specific indirect effect models because the models failed to achieve convergence under standard and modified Monte Carlo parameters.
Teleworker Well-Being in COVID-19 as a Function of Change in the Work/Home Boundary: A Multilevel Response Surface Approach · Virginia Tech · Doctorate
Tried and failed
dynamic network simulation with Monte Carlo sampling applied to complex organizational communication systems. Outcome: unstable. Reason: extreme sensitivity to initial conditions caused chaotic divergence across trials
Measuring the Communicative Constitution of Partial Organizations as Complex Systems · Virginia Tech · Doctorate
Considered and rejected
Considered and rejected: Rejected Monte Carlo simulation for exogenous state transitions to avoid simulation noise and sample instability in the Bellman recursion.
Three Essays on Sustainable Operations: Renewable Energy Procurement, Battery Storage, and Equitable Work Scheduling · University of Washington · PhD
Failure to preserve dependencies, correlations, and physical domain constraints
Sampling independently from marginal distributions or omitting importance weights generates physically implausible parameter pairings and distorts downstream uncertainty bounds. Failing to account for underlying copulas, spatial inhomogeneities, and inter-variable correlations leads to severe variance overestimation and poor out-of-sample generalization.
Tried and failed
without-replacement resampling in sequential Monte Carlo applied to constrained language model decoding. Outcome: worse than baseline. Reason: hurt downstream execution accuracy compared to standard multinomial resampling
Scaling Bayesian inference for generative models via probabilistic programming · MIT · PhD
Tried and failed
Monte Carlo dropout for uncertainty quantification applied to spatiotemporal neural network predictions. Outcome: worse than baseline. Reason: produced overly narrow prediction intervals and degraded point prediction quality
Innovations in Urban Computing: Uncertainty Quantification, Data Fusion, and Generative Urban Design · MIT · PhD
Tried and failed
sampling product of experts without importance weighting applied to sequential Monte Carlo decoding with constraints. Outcome: worse than baseline. Reason: omitting importance weight corrections severely degraded approximation of the global target posterior distribution
Scaling Bayesian inference for generative models via probabilistic programming · MIT · PhD
Considered and rejected
Considered and rejected: Standard Monte Carlo simulation was rejected for calculating test p-values because the asymptotic limit distributions depend directly on the unknown underlying copula and its partial derivatives.
Nonparametric inference in dependence modelling · University of Windsor · PhD
Tried and failed
Monte Carlo simulation with fitted empirical distributions applied to multi-stage manufacturing scrap forecasting. Outcome: did not generalise. Reason: fitted distributions produced large forecast errors and severe variance overestimation at upper confidence intervals
Advancing design-to-build learning and scrap forecasting: Educational and analytical approaches to manufacturing optimization · Iowa State · PhD
Tried and failed
unconstrained Monte Carlo parameter sampling applied to parametric learning production modeling. Outcome: did not generalise. Reason: unbounded parameter combinations generated unrealistic negative gain correlations failing to reproduce empirical meta-analytic patterns
Self-regulated learning and treatment effect heterogeneity in educational interventions : a formal model and simulation study · UT Austin · PhD
Tried and failed
direct simulation modeling of detector shower shapes applied to calorimeter shower shape distribution tail. Outcome: did not generalise. Reason: out-of-the-box Monte Carlo simulations failed to accurately model the distribution tail
Differential measurements of Z and γ bosons produced with jets at the CMS experiment · Imperial · PhD
Tried and failed
Monte Carlo sampled independent deterministic inversions applied to correlated geophysical dispersion data. Reason: sampling strategy distorted output uncertainty bounds across frequencies
On the development of uncertainty-consistent one-dimensional shear wave velocity profiles from inversion of surface wave dispersion data · UT Austin · PhD
Considered and rejected
Considered and rejected: Rejected standard Monte Carlo random sampling from marginal parameter distributions because it creates dynamically inconsistent and physically implausible parameter pairings by ignoring variable correlations.
Scenario-Based Methodology for Predicting the Safety Benefits of Emerging Advanced Rider Assistance Systems (ARAS) · Virginia Tech · Doctorate
Considered and rejected
Considered and rejected: Rejected Monte Carlo simulation for demand scenario generation because standard sampling ignores inter-substation load correlation and pattern coincidences
Metodología para el emplazamiento y control de Facts en SEP aislados utilizando información distribuida A methodology for facts devices placement and control in isolated power systems using distributed information · University of Las Palmas de Gran Canaria · PhD
Considered and rejected
Considered and rejected: Standard Wolff cluster Monte Carlo rejected because suitability objective introduces spatial inhomogeneities that violate the algorithm's symmetry assumptions.
Physical Inference for Optimization and Design · Queen's University · PhD
Inferior convergence rate and efficiency compared to analytical methods or structured sampling
Direct Monte Carlo sampling often exhibits slow convergence, redundant point clustering, and higher sample complexity compared to Latin Hypercube sampling or closed-form directional integration. These efficiency deficits result in inferior policy returns and negligible accuracy improvements over simpler analytical and quasi-Monte Carlo baselines.
Tried and failed
Monte Carlo EM for joint MLE applied to bivariate mixed-effects models. Outcome: infeasible cost. Reason: High computational cost yielded negligible MSE improvement over simpler two-step composite estimators
Small area estimation and graphical model for complex surveys · Iowa State · PhD
Lost to a baseline
Monte Carlo returns (MCR) and Monte Carlo with value baseline (MCVB) achieved lower return, lower success rate, and lower trajectory ensemble entropy than actor-critic (AC) on the tabular 100-step random walk excursion problem.
Trajectory Ensembles and Machine Learning: From reinforcement learning for rare event sampling to training of neural network ensembles · Nottingham · PhD
Tried and failed
Monte Carlo volume integration over implicit boundaries applied to hydrostatic force computation. Outcome: did not converge. Reason: achieving relative accuracy below 10^-3 was challenging for Monte Carlo and Quasi-Monte Carlo integration
Considered and rejected
Considered and rejected: Rejected standard Bernoulli Monte Carlo sampling for mission success probability due to high discretization error and slow convergence compared to direction-based chi-squared integration.
Considered and rejected
Considered and rejected: Rejected pure Monte Carlo integration for TM optimization due to redundant clustered integration points.
Efficient diagnostics of complex mechanical systems · Leibniz Universität Hannover · PhD
Considered and rejected
Considered and rejected: Rejected Monte Carlo sampling for base scenario generation due to slow moment convergence compared to Latin Hypercube Sampling.
Machine Learning based Methods to Improve Power System Operation under High Renewable Pennetration · Virginia Tech · Doctorate
Considered and rejected
Considered and rejected: Rejected standard non-sequential Monte Carlo simulation (NSMCS) and other importance splitting variants (fixed-splitting, fixed number of successes) for generating systems short-term reliability due to non-Markovian static structure and population explosion risks.
OPERATIONAL RELIABILITY AND RISK EVALUATION FRAMEWORKS FOR SUSTAINABLE ELECTRIC POWER SYSTEMS · Saskatchewan · PhD
Considered and rejected
Considered and rejected: Rejected Monte Carlo time randomization across the cyclotron period due to introduced systematic seeding error and computational overhead, replacing it with the analytical kernel method
Measuring the anomalous precession frequency wa for the Muon g − 2 experiment · University of Washington · PhD
Considered and rejected
Considered and rejected: Rejected standard Markov Chain Monte Carlo (MCMC) sampling in favor of dynamic nested sampling (dynesty), because Python MCMC implementations do not provide a computationally efficient way to calculate the Bayesian evidence Z.
Providing new constraints on Europa's surface composition · Cornell · PhD
Severe sample inefficiency and inaccuracy when estimating rare events and tail probabilities
Direct Monte Carlo sampling struggles when failure regions or geometric target apertures have extremely small probabilities, requiring astronomical sample sizes to observe meaningful events. Without massive sample counts, the simulations yield zero reaction rates, severe relative errors, and gross underestimation of critical contingency cascades.
Tried and failed
Monte Carlo simulation for rare event reliability applied to multi-state degrading subsea systems. Outcome: infeasible cost. Reason: computationally expensive and inaccurate when estimating extremely small failure probabilities in complex systems
Advanced reliability analysis of complex offshore Energy systems subject to condition based maintenance. · Cranfield · PhD
Tried and failed
nested Monte Carlo calibration with neural SDEs applied to joint asset price and volatility calibration. Outcome: infeasible cost. Reason: GPU memory limits restricted nested Monte Carlo path counts, causing severe sampling errors and poor fits
Deep learning-based methods in the era of rough volatility · Imperial · PhD
Considered and rejected
Considered and rejected: Standard Monte Carlo simulation was rejected for generating cascading failure datasets because it severely underestimates N-3+ contingencies and yields ~0.1% cascade cases.
Real-time Prediction of Cascading Failures in Power Systems · Saskatchewan · PhD
Tried and failed
Monte Carlo particle transport with low history counts applied to dosimetric tally estimation in complex phantoms. Outcome: no signal. Reason: insufficient particle histories led to ~100% relative error tallies lacking statistical significance
Quantification and computational modelling of radiation doses while handling Neutron Activation Analysis samples · UT Austin · PhD
Tried and failed
Monte Carlo particle transport simulation applied to optically thin low cross-section regions. Outcome: no signal. Reason: Inadequate sampling and low capture cross-sections in thin regions caused zero reaction rates with high statistical variance.
Multi-disciplinary Modelling and Simulation of the High Temperature Test Reactor (HTTR) and Small Nuclear Rocket Engine (SNRE) · Imperial · PhD
Tried and failed
forward Monte Carlo ray tracing applied to radiative transfer to small aperture. Outcome: too slow. Reason: Extremely low probability of rays randomly hitting a small target aperture made convergence computationally intractable.
Development of a Water Cloud Radiance Model for Use in Training an Artificial Neural Network to Recover Cloud Properties from Sun Photometer Observations · Virginia Tech · Master's
Considered and rejected
Considered and rejected: Rejected simulating training points solely from ergodic distributions via Monte Carlo, as rare crisis regions lack sufficient mass and induce severe future-iteration instabilities
Essays in macro-finance and deep learning · EPFL · PhD
Poor mixing, mode collapse, and convergence failure in complex or multimodal state spaces
Markov Chain Monte Carlo and continuous-time variants struggle to traverse multimodal distributions, frequently becoming trapped in local optima and outputting overconfident posterior distributions. Disparities in transition rates and trajectory decorrelation in chaotic systems hinder proper mixing, preventing convergence within acceptable execution windows.
Tried and failed
kinetic Monte Carlo simulation applied to hopping transport with extreme rate disparities. Outcome: did not converge. Reason: extreme transition rate disparities between transport directions prevented convergence, requiring a Master Equation solver
Modelling the microstructure-charge transport relationship in organic semiconductors · Imperial · PhD
Tried and failed
Monte Carlo sampled correlation functions for covariance estimation applied to Hamiltonian reconstruction from quantum states. Outcome: did not converge. Reason: Monte Carlo sampling failed to converge energy variance and showed slow convergence of reconstructed coupling parameters
Computational Approaches to Frustrated Many-Body Systems · Cornell · PhD
Tried and failed
transition path sampling continuous-time Monte Carlo applied to finite-time tilted trajectory ensembles. Outcome: did not converge. Reason: fails to sample dynamical activity at long trajectory times without guided reference dynamics
Non-equilibrium dynamics and large deviations in stochastic lattice models via tensor networks · Nottingham · PhD
Considered and rejected
Considered and rejected: Rejected parameterizing initial PDF and optimizing via Maximum Likelihood Estimation with Monte Carlo integration because of convergence to local minima and lack of feasibility guarantees.
Koopman Operator Approach to Uncertainty Quantification and Decision-Making · Georgia Tech · PhD
Considered and rejected
Considered and rejected: Rejected Monte-Carlo optimization for molecular orientation exploration due to high risk of trapping in local minima.
Structure Formation during Organic Molecular Beam Deposition · Tübingen · PhD
Tried and failed
multilevel Monte Carlo path simulation applied to chaotic dynamical systems. Outcome: did not converge. Reason: Fine and coarse trajectory realizations decorrelate over long horizons, preventing variance reduction across levels.
Multi-Level Monte Carlo Methods for Uncertainty Quantification and Risk-Averse Optimisation · EPFL · PhD
Tried and failed
Markov Chain Monte Carlo data association applied to multimodal trajectory tracking. Outcome: did not converge. Reason: Failed to explore multiple modes, becoming stuck in local optima and yielding overconfident, incorrect posterior distributions.
Uncertainty Quantification and Structure Discovery for Scalable Behavior Science · MIT · PhD
Tried and failed
single-chain Metropolis-Hastings Markov chain Monte Carlo applied to compact graph partitioning and redistricting. Outcome: did not converge. Reason: Severe multimodal distribution hindered mixing, showing no convergence after days of execution.
Understanding and Mitigating Bias in Algorithms, Data, and Society · Georgia Tech · PhD
Physical transport modeling failures and tracking artifacts in heterogeneous media
Monte Carlo particle transport and ray tracing workflows fail when underlying nuclear databases lack necessary transition data or when microscale interaction models are not predictive. Applying complex variance reduction moves and particle splitting can also trigger stack overflows, corrupted particle weights, or extreme sensitivity to random spatial distributions.
Tried and failed
Monte Carlo radiation transport simulation applied to prompt gamma background continuum modeling. Reason: Incomplete nuclear database missing high-energy prompt gamma-ray transition data for shielding materials
Characterization of ²³⁹Pu with coincidence and anticoincidence methods · UT Austin · PhD
Tried and failed
Monte Carlo energy deposition and light transport simulation applied to heterogeneous powder-matrix scintillator composite. Reason: optical transport and microscale particle interaction modeling in heterogeneous powder suspension was not predictive
Gamma-Blind Fast Neutron Detection for Spent Nuclear Fuel Characterization · EPFL · PhD
Tried and failed
Monte Carlo translation moves applied to interfacial phase space sampling. Reason: Failed to improve move acceptance ratios during grand canonical sampling of interface configurations
Tried and failed
Monte Carlo event generator cross section modeling applied to forward lepton-nucleus scattering cross sections. Outcome: did not generalise. Reason: Inadequate modeling of nuclear effects and kinematics overpredicted cross sections at small forward scattering angles.
Lepton-Nucleus Constraints for Neutrino Interactions and Oscillations · MIT · PhD
Tried and failed
Monte Carlo particle transport simulation applied to randomly dispersed particulate fuel cores. Reason: extreme sensitivity to stochastic spatial particle distribution caused significant eigenvalue over-prediction
Multi-disciplinary Modelling and Simulation of the High Temperature Test Reactor (HTTR) and Small Nuclear Rocket Engine (SNRE) · Imperial · PhD
Left open by the authors
Problems the authors named and did not get to.
Left open
Investigate the relationship between Monte Carlo scenario generation reliability and stochastic programming portfolio solution performance across simulated market conditions. Blocker: No concrete experimental design, mathematical formulation of scenario reliability, or target metrics are specified.
Improving time series and cross-sectional momentum trading strategies using stochastic programming · Iowa State · PhD
Left open
Characterize the cost models for various supply chain resilience options and incorporate them into the Value at Risk Monte Carlo simulation framework. Blocker: Empirical cost data for enterprise supply chain resilience investment options is proprietary or restricted.
Strategic Approach for Assessing Supply Chain Resilience Investment Options · MIT · Master's
Left open
Implement statistical Weibull Monte Carlo simulation capabilities in Peri-CORE to assess TRISO fuel batch failure probabilities. Blocker: Requires access to the proprietary or unreleased Peri-CORE Abaqus Fortran subroutines developed in the thesis
Peridynamics and finite element simulations of TRISO Fuel under extreme operating conditions · Imperial · PhD
Left open
Derive convergence rates for Importance Support Points resampling and lookback adaptation in projected quasi-Monte Carlo methods. Blocker: Requires specialized theoretical mathematical analysis rather than software engineering.
Novel Experimental Design Techniques for Data Science · Georgia Tech · PhD
Left open
Calibrate the Opisthorchis viverrini spatial renewal model against empirical infection data from the Lower Mekong Basin using sequential Monte Carlo. Blocker: Access to empirical Opisthorchis viverrini surveillance and mobility data from the Lower Mekong Basin in Laos.
Infectious disease spread in connected communities · EPFL · PhD
Left open
Compare Monte Carlo approximations of crop insurance premiums from the fitted bivariate jump-diffusion model to empirical USDA premium values. Blocker: None
Statistical applications in actuarial science: From cryptocurrency to meme stocks to crop insurance · Iowa State · PhD
Left open
Evaluate pressure function equilibria using stochastic microsimulation with Monte Carlo modeling baseline and stochastic origin-destination demand. Blocker: None
Bridging the gap: unifying transportation planning and operations through enhanced travel demand modeling · UT Austin · PhD
Left open
Develop alternative coupling methods for Multi-Level Monte Carlo to restore variance decay in chaotic and turbulent high Reynolds number fluid flow simulations. Blocker: The unfinished work proposes a broad research direction without specifying concrete coupling formulations or validation benchmark cases
Multi-Level Monte Carlo Methods for Uncertainty Quantification and Risk-Averse Optimisation · EPFL · PhD
Who has worked on this
Authors of the public theses cited on this page, most-cited first.
- Sundar Subramaniam Ganesh · EPFL · PhD · 2022
Multi-Level Monte Carlo Methods for Uncertainty Quantification and Risk-Averse Optimisation - João Loula Guimarães de Campos · MIT · PhD · 2025
Scaling Bayesian inference for generative models via probabilistic programming - Emma Stewart · Imperial · PhD · 2025
Multi-disciplinary Modelling and Simulation of the High Temperature Test Reactor (HTTR) and Small Nuclear Rocket Engine (SNRE) - Xiaoshi Guo · Iowa State · PhD · 2021
Improving time series and cross-sectional momentum trading strategies using stochastic programming - Mohammad Ahnaf Sadat · Iowa State · PhD · 2026
Strategic investment decisions in remanufacturing and recycling for economic sustainability: An analysis using real options-based models - Xiaoxuan Hou · University of Washington · PhD · 2026
Three Essays on Sustainable Operations: Renewable Energy Procurement, Battery Storage, and Equitable Work Scheduling - Paolo Terranova · Virginia Tech · Doctorate · 2026
Scenario-Based Methodology for Predicting the Safety Benefits of Emerging Advanced Rider Assistance Systems (ARAS) - Weiran Xu · MIT · PhD · 2025
An Optimized Bayesian Analysis Framework for the KATRIN Experiment - Lucas W. Monteiro Paes · Harvard · PhD · 2025
Epistemic Limits of Trustworthy Machine Learning - Linshanshan Wang · Harvard · PhD · 2025
Semi-supervised and Representation Learning for Improved Classification and Stratification in EHR Data - Marco Andrés Miller Hernández · MIT · PhD · 2025
Understanding the Mechanisms that Determine the Edge Electron Density Profile in Tokamaks - Nikolaos Kalogeropoulos · Imperial · PhD · 2025
Wildfire simulations to protect rural communities and avoid dire evacuations
Checking a claim in this area?
We can run the same search on any method or claim. If nothing turns up, we will say so, and that proves nothing on its own.