Paper solves a control problem with robust methods.
problem Monotone mean-variance problems with stochastic coefficients.
method Finding saddle point through BSDEs with unbounded coefficients.
result Optimal control and value match mean-variance problems.
Optimizes MCMC chains with neural control variates.
problem Reducing variance in Markov Chain Monte Carlo (MCMC) simulations.
method Uses neural networks as control variates to minimize asymptotic variance.
result Derives optimal convergence rate under various ergodicity assumptions.
Improved LLM pre-training performance through better weight and variance control.
problem Improper weight and variance control in LLM pre-training affects downstream task performance.
method Introduced Layer Index Rescaling (LIR) and Target Variance Rescaling (TVR) techniques.
result Substantial improvements in downstream task performance (up to 4.6%) and reduced extreme activation values.
New method reduces inference variance for faster optimization.
problem High variance in black-box variational inference.
method Joint control variate addressing both data subsampling and Monte Carlo noise.
result Significantly reduced gradient variance, leading to faster optimization.
This work proposes using zero-variance control variates to reduce variance in pathwise gradient estimators for variational inference.
problem Pathwise gradient estimators in variational inference have high variance, leading to inefficient optimization.
method Apply zero-variance control variates to pathwise gradient estimators.
result Zero-variance control variates can significantly reduce the variance of pathwise gradient estimators without requiring complex assumptions.
A new method reduces variance in training discrete latent variable models.
problem High variance in stochastic gradient estimators for discrete latent variable models.
method Double control variates for score function estimators using Taylor expansions.
result Our method can have lower variance compared to other estimators.
Neural SDEs reduce variance in stochastic simulations.
problem Efficiency of Monte Carlo simulations in finance.
method Use neural SDEs with control variates parameterized by neural networks.
result Prove optimality conditions for variance reduction in SDEs with infinite activity.
New approach to optimal dividend control with mean-variance criterion.
problem Balancing expected dividends and variability in a singular control framework.
method Game-theoretic approach to find time-consistent equilibrium strategies.
result Verification theorem for MV singular dividend control problem.
This work improves variational inference by reducing gradient variance.
problem Hard optimization of flexible variational distributions.
method Control variate based on quadratic approximation of the model's mean and covariance.
result Significant improvement in gradient variance and optimization convergence.
We study the problem of empirical minimization for variance-type functionals over functional classes. Sharp non-asymptotic bounds for the excess variance are derived under mild conditions. In particular, it is shown that under some restrictions imposed on the functional class fast convergence rates can be achieved incl…
Meta-CVs leverage task similarity to reduce variance with limited data.
problem Reducing variance in Monte Carlo estimators with few samples.
method Meta-learning control variates for related tasks.
result Meta-CVs lead to significant variance reduction in settings with limited data.
New model optimizes portfolios over multiple periods using predictive control.
problem Optimizing multi-period portfolios with risk and variance objectives.
method Model Predictive Control with Mean-Variance and Risk Parity.
result 30x faster and more robust solutions compared to single period models.
VarGrad reduces variance in ELBO gradient estimation for variational inference.
problem Improving the variance of gradient estimators in variational inference.
method VarGrad uses a new log-variance loss to estimate the ELBO gradient, achieving lower variance than the score function method.
result VarGrad offers a lower variance gradient estimator compared to other methods.
Proposes variance reduction techniques for sliced Wasserstein distance estimation.
problem Intractability of estimating sliced Wasserstein distances.
method Uses control variates based on Gaussian approximations of projected measures.
result Significant reduction in variance of SW distance estimators.
Improves gradient estimation for discrete distributions with variance reduction techniques.
problem Excessive variance in gradient estimation for discrete distributions.
method Stein operators for discrete distributions and control variates.
result Substantially lower variance in gradient estimation.
This paper develops scalable control variates for Monte Carlo methods using stochastic optimization.
problem Reducing variance in Monte Carlo estimators for large-scale problems.
method Control variates based on Stein operators, optimized through stochastic optimization.
result Novel theoretical results and empirical validations show effective variance reduction.
In statistics and machine learning, approximation of an intractable integration is often achieved by using the unbiased Monte Carlo estimator, but the variances of the estimation are generally high in many applications. Control variates approaches are well-known to reduce the variance of the estimation. These control v…
New method reduces variance in complex probabilistic model optimization.
problem High variance in stochastic optimisation of complex models.
method Use recognition network to approximate optimal control variate for each mini-batch.
result Sub-optimal variance reduction is improved with new approach.
Variational inference is increasingly being addressed with stochastic optimization. In this setting, the gradient's variance plays a crucial role in the optimization procedure, since high variance gradients lead to poor convergence. A popular approach used to reduce gradient's variance involves the use of control varia…
Proposes a virtual bidding strategy for electricity markets using stochastic control.
problem Optimizing electricity prices in day-ahead and real-time markets.
method Modeling price differences as Brownian motion with meteorological variables, transforming into portfolio management problem.
result Developed a strategy to manage electricity prices efficiently.
New method reduces variance in Bayesian inverse problems.
problem High variance in Monte Carlo estimates for inverse problems.
method Conditional neural control variates based on Stein's identity.
result Substantial variance reduction across different inverse problems.
Dealing with high variance is a significant challenge in model-free reinforcement learning (RL). Existing methods are unreliable, exhibiting high variance in performance from run to run using different initializations/seeds. Focusing on problems arising in continuous control, we propose a functional regularization appr…
This paper addresses error bounds and posterior variance for Gaussian process regression.
problem Deriving performance guarantees for Gaussian process regression without prior knowledge.
method Lipschitz continuity and analysis of posterior variance function.
result Uniform error bounds for Gaussian process regression are derived.
It is well known that Markov chain Monte Carlo (MCMC) methods scale poorly with dataset size. A popular class of methods for solving this issue is stochastic gradient MCMC. These methods use a noisy estimate of the gradient of the log posterior, which reduces the per iteration computational cost of the algorithm. Despi…
The paper explores how control variates can reduce variance in Monte Carlo simulations, especially for Sobolev functions.
problem Efficiency of control variates in reducing variance for Monte Carlo simulations.
method Study of a specific quadrature rule using nonparametric regression-adjusted control variates.
result A specific quadrature rule can improve the Monte Carlo rate and achieve the minimax optimal rate under sufficient smoothness assumptions.
Paper improves variance control in importance weighted variational bounds.
problem Improving the variance of gradient estimators for IWAE.
method Develops a novel control variate that grows SNR as √K for large K.
result Empirically, the method yields superior variance reduction for generative models.
Proposes a new model to optimize investment plans with varying terminal times.
problem Improving the classical mean-variance model for continuous time investments.
method Uses stochastic optimal control and varying terminal time to determine optimal strategies.
result Optimal strategies and terminal times can be determined to minimize portfolio variance.
A/B testing improves marketing decisions by selecting effective stratification variables.
problem Improving the sensitivity of A/B testing through stratified sampling.
method Designing an algorithm to select a subset of stratification variables for variance reduction.
result The subset selection method outperforms other variance reduction techniques in A/B testing.
Improves diffusion models by controlling total variance and signal-to-noise-ratio.
problem Long sampling time in diffusion models.
method Total-Variance/Signal-to-Noise-Ratio (TV/SNR) disentangled framework.
result Improves generation performance by controlling TV and SNR independently.
Paper proposes SCott optimizer to reduce forecasting model training variance.
problem Large variance in gradient estimation for forecasting models.
method Stratified sampling and control variate to reduce gradient variance.
result SCott optimizer converges faster on time series forecasting problems.
Learning in models with discrete latent variables is challenging due to high variance gradient estimators. Generally, approaches have relied on control variates to reduce the variance of the REINFORCE estimator. Recent work (Jang et al. 2016, Maddison et al. 2016) has taken a different approach, introducing a continuou…
Study time-inconsistent control problems with model uncertainty, solving portfolio selection.
problem Time-inconsistent Markovian control problems under model uncertainty.
method Combining sub-game perfect strategies with adaptive robust stochastic methods.
result Solved numerically the mean-variance portfolio selection problem.
New objective reduces bias and variance in reinforcement learning derivatives.
problem Estimating derivatives in reinforcement learning with unknown dynamics.
method Derives an objective function compatible with any advantage estimators, allowing trade-off between bias and variance.
result Demonstrates effectiveness in both theoretical and practical settings.
MVPI framework optimizes risk in reinforcement learning, improving performance in robot simulations.
problem Optimizing risk in reinforcement learning control problems.
method Mean-Variance Policy Iteration (MVPI) framework for risk-averse control in MDPs.
result Risk-averse TD3 outperforms previous methods in robot simulation tasks.
Optimal investment and risk control strategies for insurers are derived using a time-consistent approach.
problem Optimal investment and risk control for insurers under mean-variance criterion.
method Introducing a deterministic forward auxiliary process to formulate a time-consistent problem.
result Optimal strategy and value function obtained in closed-form for the new problem.
Algorithm reduces variance in causal effect estimation from multiple datasets.
problem Unidentifiable average treatment effect in observational data due to selection bias.
method Constructs control variates using datasets where ATE is not identifiable to reduce variance.
result Significant reduction in variance of ATE estimate using control variates.
Paper explores two methods for optimal portfolio selection in financial markets.
problem Optimal portfolio selection for financial markets with jumps.
method Maximum principle and dynamic programming approach.
result Relationship between two methods and their adjoint processes.
Proposes variance reduction for optimizing permutation models.
problem High variance in gradient estimates for discrete latent variables.
method Control variates for the Plackett-Luce distribution.
result Optimization of black-box functions over permutations using SGD.
Develops a control framework for systemic risk under uncertainty.
problem Systemic risk under model uncertainty.
method Linear-quadratic mean-field control framework with viscosity solutions and verification theorems.
result Explicit feedback controls derived from a coupled Riccati system, preserving analytical tractability.
VAEs analyzed using harmonic analysis, showing how variance controls frequency content and robustness.
problem Understanding and optimizing VAEs for robustness and frequency control.
method Viewing VAE latent space as Gaussian space, deriving results on variance and frequency content, and demonstrating soft Lipschitz constraints.
result Increasing encoder variance reduces high frequency content and improves adversarial robustness.
Evolution Strategies (ES) are a powerful class of blackbox optimization techniques that recently became a competitive alternative to state-of-the-art policy gradient (PG) algorithms for reinforcement learning (RL). We propose a new method for improving accuracy of the ES algorithms, that as opposed to recent approaches…
Proposes a robust equilibrium strategy for mean-variance portfolio selection.
problem Time-inconsistency in mean-variance portfolio selection.
method Introduces a novel definition of robust equilibrium strategy and solves the corresponding PDE system.
result A classical solution to the PDE system implies a robust equilibrium strategy.
The paper solves TIC LQ control problems using stochastic differential games.
problem Time-inconsistent linear-quadratic stochastic control problems.
method Stochastic differential games, spike variation approach.
result Achieves Nash equilibrium for TIC problems, demonstrating impact of ambiguity aversion.
The paper proposes a new method to estimate optimal policies using MCMC.
problem Estimating the optimal policy for systems with unknown dynamics and reward functions.
method Using Markov Chain Monte Carlo to generate samples from the posterior distribution of parameters conditioned on optimality.
result The method provably converges to the globally optimal stochastic policy with similar variance to policy gradient methods.
Unified framework combines views and optimization for better portfolio management.
problem Optimizing portfolio weights with dynamic adjustment based on volatility.
method Dynamic sliding window adjusting horizon, factor estimates, BL posterior returns, and weights over time.
result Outperforms dynamic mean-variance optimization without BL views, providing stronger downside risk control.
Machine learning reduces variance in online experiment results.
problem Reducing variance in randomized controlled trials.
method Machine learning regression-adjusted treatment effect estimator (MLRATE).
result MLRATE reduces estimator variance by over 70% in A/A tests.
NCV uses neural networks to improve Monte Carlo integration.
problem Improving variance reduction in parametric Monte Carlo integration.
method NCV combines a normalizing flow and a neural network to approximate the integrand and solve the integral equation, with a neural importance sampler to estimate the difference.
result NCV achieves state-of-the-art performance in light transport simulation with reduced noise and negligible bias.
There are no known exact formulas for the valuation of a number of exotic options, and this is particularly true for options under discrete monitoring and for American style options. Therefore, one usually recourses to a Monte Carlo Simulation approach, amongst other numerical methods, to estimate the value of these op…