Paper tackles efficient evaluation of natural stochastic policies in offline RL.
problem Efficiency issues in evaluating natural stochastic policies due to unknown evaluation policy.
method Derive efficiency bounds for tilting and modified treatment policies, propose nonparametric estimators.
result Proposed estimators attain efficiency bounds under lax conditions and enjoy partial double robustness.
Stochastic models analyze traffic network performance.
problem Evaluate traffic system performance.
method Stochastic cell transmission models, preference functionals, Gaussian process regression.
result Illustrated in two case studies.
A new hybrid algorithm reduces stochastic gradient evaluations for nonconvex optimization.
problem Solving stochastic composite nonconvex optimization problems efficiently.
method Proposes a new hybrid variance-reduced proximal gradient method with a stochastic gradient estimator.
result Achieves optimal stochastic oracle complexity bound with one less gradient evaluation.
This paper optimizes portfolio management in incomplete markets with stochastic factors, considering periodic wealth evaluations.
problem Optimizing portfolio performance in an incomplete market model with stochastic factors and periodic wealth evaluations.
method Developed a martingale duality approach to find optimal portfolio processes and dual minimizers.
result Established the existence of optimal portfolio processes and identified dual minimizers as the 'least favorable' market completion.
Adaptive replication improves stochastic function optimization.
problem Challenges in accurately estimating functions with high variance.
method Trust-region-based Bayesian optimization with adaptive replication.
result Adaptive replication substantially improves solution accuracy and efficiency.
In this paper we study the problem of minimizing the average of a large number (n) of smooth convex loss functions. We propose a new method, S2GD (Semi-Stochastic Gradient Descent), which runs for one or several epochs in each of which a single full gradient and a random number of stochastic gradients is computed, fo…
New approach for prudent risk evaluation using model aggregation.
problem Risk evaluation and optimization under uncertainty.
method Model Aggregation (MA) approach based on stochastic dominance.
result Produces robust risk evaluation and distributional models.
Study variance-reduced method for estimating fixed points in Banach spaces.
problem Estimating fixed points of contractive operators in Banach spaces with noisy evaluations.
method Variance-reduced stochastic approximation scheme in Banach spaces.
result Establish non-asymptotic bounds for operator defect and estimation error.
Stochastic Bayesian Neural Network improves scalability and performance.
problem Challenges in calculating posterior distribution in Bayesian Neural Networks.
method Maximizes Evidence Lower Bound using Stochastic Evidence Lower Bound objective function.
result Demonstrates improved performance and scalability over previous algorithms.
Proposes a new resampling method for off-policy evaluation in stochastic control.
problem Estimating policy performance from data generated under a different policy.
method K-nearest neighbor resampling procedure for off-policy evaluation.
result Statistical consistency results for the proposed method under weak conditions.
Paper introduces a new multi-kernel algorithm for better gradient approximation.
problem Improving gradient approximation in high-dimensional problems.
method Develops a multi-kernel passive stochastic gradient algorithm with variance reduction.
result The multi-kernel algorithm performs better in high-dimensional problems.
The paper shows how shared random seeds can reduce variance in machine learning evaluations.
problem The statistical structure of comparative evaluation under shared random seeds is not well understood.
method An extended learning-based multi-agent economic simulator was used to demonstrate the effects of shared random seeds on variance reduction.
result Pairing seeds can reduce variance in machine learning evaluations, especially when outcomes are positively correlated at the seed level.
Stochastic optimization problems often involve the expectation in its objective. When risk is incorporated in the problem description as well, then risk measures have to be involved in addition to quantify the acceptable risk, often in the objective. For this purpose it is important to have an adjusted, adapted and eff…
Scalar dynamic risk measures for univariate positions in continuous time are commonly represented as backward stochastic differential equations. In the multivariate setting, dynamic risk measures have been defined and studied as families of set-valued functionals in the recent literature. There are two possible extensi…
Discretizations of Langevin diffusions provide a powerful method for sampling and Bayesian inference. However, such discretizations require evaluation of the gradient of the potential function. In several real-world scenarios, obtaining gradient evaluations might either be computationally expensive, or simply impossibl…
Study optimal portfolio management with periodic evaluations in stochastic models, considering convex constraints.
problem Optimal portfolio management under ratio-type periodic evaluations in stochastic factor models with convex trading constraints.
method Transformed infinite horizon optimal control problem into an auxiliary terminal wealth optimization problem. Introduced an auxiliary unconstrained optimization problem in a modified market model. Used martingale duality approach to establish dual minimizer and optimal unconstrained wealth process.
result Derived and verified the optimal constrained portfolio process for the original problem over an infinite horizon.
In this study, we develop a deterministic nonlinear filtering algorithm based on a high-dimensional version of Kitagawa (1987) to evaluate the likelihood function of models that allow for stochastic volatility and jumps whose arrival intensity is also stochastic. We show numerically that the deterministic filtering met…
BOSH optimizes functions with stochastic evaluations more efficiently and precisely.
problem Optimizing functions with noisy evaluations can lead to suboptimal solutions.
method BOSH uses a hierarchical Gaussian process to generate a growing pool of realizations.
result BOSH provides more efficient and higher-precision optimization than standard BO.
New methods improve temporal difference learning for policy evaluation in Markov decision processes.
problem Improving temporal difference learning for policy evaluation in Markov decision processes.
method Introduced variance-reduced forms of stochastic approximation to achieve non-asymptotic, instance-dependent optimality.
result Temporal difference learning is strictly suboptimal, but variance-reduced forms achieve optimality up to logarithmic factors.
Paper proposes a new method to speed up diffusion models.
problem High computational cost of sampling from diffusion models.
method Stochastic Runge-Kutta method for acceleration.
result Provable acceleration with reduced score function evaluations.
New simulation approaches to evaluating path-dependent options without matrix inversion issues nor Euler bias are evaluated. They employ three main contributions: Stochastic approximation replaces regression in the LSM algorithm; Explicit weak solutions to stochastic differential equations are developed and applied to …
Paper tackles offline SSP with value iteration for policy evaluation and learning.
problem Goal-oriented RL with offline data and cost minimization.
method Simple value iteration algorithms for OPE and offline policy learning.
result Strong instance-dependent bounds implying near-minimax optimal worst-case bounds.
Policy evaluation is a crucial step in many reinforcement-learning procedures, which estimates a value function that predicts states' long-term value under a given policy. In this paper, we focus on policy evaluation with linear function approximation over a fixed dataset. We first transform the empirical policy evalua…
New framework for evaluating ad auctions using stochastic modeling.
problem Challenges in evaluating deterministic ad auctions.
method Repurposed bid landscape model to approximate propensity scores, enabling robust OPE estimators.
result Remarkable alignment with online A/B test results, achieving 92% MDA in CTR prediction.
Stochastic zeroth-order (SZO), or gradient-free, optimization allows to optimize arbitrary functions by relying only on function evaluations under parameter perturbations, however, the iteration complexity of SZO methods suffers a factor proportional to the dimensionality of the perturbed function. We show that in scen…
Stochastic Stein Discrepancies improve inference efficiency.
problem Intractable computation of Stein discrepancies.
method Subsampled approximations of Stein operators.
result Stochastic Stein Discrepancies inherit convergence properties of standard SDs.
Stochastic parameterizations account for uncertainty in the representation of unresolved sub-grid processes by sampling from the distribution of possible sub-grid forcings. Some existing stochastic parameterizations utilize data-driven approaches to characterize uncertainty, but these approaches require significant str…
The paper addresses numerical integration issues in SV models, proposing a fast regime switching algorithm.
problem Numerical integration challenges in SV models, especially with high precision and low computational time.
method Proposes a fast regime switching algorithm to determine when higher precision arithmetic is needed.
result Shows that numerical quadratures need to be carefully chosen based on model parameters and parameter values.
We quantify content availability and user discovery opportunities in recommender systems.
problem Determining the maximum probability of recommending content to users.
method Stochastic reachability to compute upper bounds on recommendation likelihood.
result Reachability metrics can detect biases and diagnose user discovery limitations.
This paper proposes a stochastic variant of a classic algorithm---the cubic-regularized Newton method [Nesterov and Polyak 2006]. The proposed algorithm efficiently escapes saddle points and finds approximate local minima for general smooth, nonconvex functions in only O~(ε−3.5) stochastic gradien…
mAIS improves free energy evaluation efficiency.
problem Computational infeasibility of exact free energy evaluation.
method mAIS, a marginalized version of AIS.
result mAIS is more efficient under certain conditions.
Improved convergence for non-log-concave sampling.
problem Sampling from non-log-concave distributions.
method Novel conductance analysis of SGLD with auxiliary Markov Chain.
result SGLD achieves ε-sampling error with fewer evaluations.
Bayesian inference using stochastic neural networks ensembles.
problem Approximating Bayesian posterior distributions.
method Formulate stochastic ensembles of neural networks, train with variational inference, and evaluate using Monte Carlo dropout.
result Stochastic ensembles provide more accurate posterior estimates than other methods.
Stochastic structured prediction under bandit feedback follows a learning protocol where on each of a sequence of iterations, the learner receives an input, predicts an output structure, and receives partial feedback in form of a task loss evaluation of the predicted structure. We present applications of this learning …
In this chapter, we consider volatility swap, variance swap and VIX future pricing under different stochastic volatility models and jump diffusion models which are commonly used in financial market. We use convexity correction approximation technique and Laplace transform method to evaluate volatility strikes and estim…
New algorithm solves complex optimization problems without needing projections.
problem Optimizing nested functions under convex constraints with noisy evaluations.
method Projection-free conditional gradient-type algorithm for smooth stochastic multi-level composition optimization.
result The algorithm achieves ε-stationary solutions with complexity bounds independent of ε and T. Leveraging advances in variational inference, we propose to enhance recurrent neural networks with latent variables, resulting in Stochastic Recurrent Networks (STORNs). The model i) can be trained with stochastic gradient methods, ii) allows structured and multi-modal conditionals at each time step, iii) features a re…
The paper models financial asset prices with jumps and evaluates European option prices using numerical methods.
problem Modeling and pricing European options with jumps in delayed stochastic systems.
method Existence, uniqueness, and positivity of solutions to delayed stochastic differential equations with jumps. Application of Fourier transformation for analytical pricing and Monte-Carlo simulation with a logarithmic Euler-Maruyama scheme for numerical approximation.
result The logarithmic Euler-Maruyama scheme provides a positive and convergent method for approximating the solution to the delayed stochastic differential equations with jumps.
Paper proposes a weak approximation of reflection coupling for non-convex optimization.
problem Non-convex optimization problems with different drift terms.
method Proposes an approximate reflection coupling (ARC) for stochastic differential equations (SDEs).
result ARC converges weakly to the reflection coupling and can be applied to non-convex optimization.
Deep learning solves complex stochastic control with jumps.
problem Solving high-dimensional stochastic control tasks with jumps.
method Model-based approach using two neural networks, iteratively trained with objectives derived from the Hamilton-Jacobi-Bellman equation.
result Demonstrates effectiveness in solving complex high-dimensional stochastic control tasks.
We consider derivative-free algorithms for stochastic and non-stochastic convex optimization problems that use only function values rather than gradients. Focusing on non-asymptotic bounds on convergence rates, we show that if pairs of function values are available, algorithms for d-dimensional optimization that use …
Bayesian optimization reduces hyperparameter tuning cost for stochastic models.
problem Hyperparameter tuning under uncertainty in noisy function evaluations.
method Bayesian optimization framework for scale parameter in stochastic models, using statistical surrogate and closed-form optimizer.
result Significant reduction in computational cost (40 times fewer data points, 40-fold reduction in cost).
A new method for high-dimensional RBDO using stochastic emulators.
problem Efficient RBDO in high-dimensional settings.
method Unified stochastic representation, stochastic emulators, deterministic mapping.
result Significant computational gains in high-dimensional settings.
Bayesian optimization tackles non-convex, two-stage stochastic problems efficiently.
problem Solving non-convex, two-stage stochastic optimization problems with expensive, black-box evaluations.
method Knowledge-gradient-based acquisition function for joint optimization of first- and second-stage variables.
result Comparable and superior empirical results compared to alternatives.
In this paper, we prove some convergence results of a special case of optimistic policy iteration algorithm for stochastic shortest path problem. We consider both Monte Carlo and TD(λ) methods for the policy evaluation step under the condition that the termination state will eventually be reached almost surely.
Many machine learning algorithms minimize a regularized risk, and stochastic optimization is widely used for this task. When working with massive data, it is desirable to perform stochastic optimization in parallel. Unfortunately, many existing stochastic optimization algorithms cannot be parallelized efficiently. In t…
New method reduces mixture model evaluation cost for large models.
problem Computational infeasibility of evaluating all mixture components.
method Combining EM and Metropolis-Hastings for stochastic sampling.
result Significantly reduced computational cost for large models.
The path probability of a particle undergoing stochastic motion is studied by the use of functional technique, and the general formula is derived for the path probability distribution functional. The probability of finding paths inside a tube/band, the center of which is stipulated by a given path, is analytically eval…