Active inference minimizes expected free energy for optimal behavior.
problem Understanding and optimizing behavior in complex systems.
method Combines Bayesian decision theory, optimal Bayesian design, and the free energy principle.
result Active inference emerges as a unified framework for information-seeking, utility maximization, and goal-directed behavior.
Proposes data-driven methods for estimating conditional expectations.
problem Estimating conditional expectations when underlying density is unknown.
method Data-driven techniques to directly estimate conditional expectations from training data.
result Extends data-driven method to solve nonlinear equations in stochastic optimization.
New unbiased gradient estimators for complex optimization problems.
problem Unbiased and variance-limited gradient estimation for conditional stochastic optimization.
method Developed multilevel Monte Carlo gradient estimators for conditional stochastic optimization problems.
result Unbiased and finite variance gradient estimators for conditional stochastic optimization problems.
State-level minimum Bayes risk (sMBR) training has become the de facto standard for sequence-level training of speech recognition acoustic models. It has an elegant formulation using the expectation semiring, and gives large improvements in word error rate (WER) over models trained solely using cross-entropy (CE) or co…
Study optimal investment and consumption in incomplete markets with nonlinear expectations.
problem Utility maximization in incomplete markets with general constraints.
method Utilizes g-martingale method to solve optimization problem for various utility functions. result Characterizes optimal investment-consumption strategy through quadratic BSDE solutions.
Study shows equivalence of four risk constraints in non-concave optimization problems.
problem Investigating risk constraints in non-concave optimization for financial companies.
method Analytical solutions for four risk constraints (ES, EDS, VaR, AVaR) under non-concave optimization.
result All four risk constraints lead to the same optimal solution, differing from concave optimization.
Paper proposes an unbiased optimization method for Bayesian experimental design.
problem Maximizing expected information gain in Bayesian experimental design.
method Randomized multilevel Monte Carlo (MLMC) method combined with stochastic gradient descent.
result An unbiased estimator for the gradient of expected information gain.
Paper solves optimization problems with convex expectation constraints using a new algorithm.
problem Minimizing convex expectation functions with inequality convex expectation constraints.
method Stochastic Augmented Lagrangian-Type Algorithm (Stochastic Linearized Proximal Method of Multipliers).
result Algorithm achieves O(K−1/2) convergence rates for objective reduction and constraint violation. The paper confirms a conjecture about optimal expected utility in markets with insider information.
problem Optimal expected utility in markets with insider information.
method An extension of the Black-Scholes-Merton model with a sequence of discrete-time economies.
result Optimal expected utility converges to the classic model when conditions are met.
We develop a theory for solving continuous time optimal stopping problems for non-linear expectations. Our motivation is to consider problems in which the stopper uses risk measures to evaluate future rewards.
We study the existence of optimal actions in a zero-sum game infτsupPEP[Xτ] between a stopper and a controller choosing a probability measure. This includes the optimal stopping problem infτE(Xτ) for a class of sublinear expectations E(⋅) such as the G-expectation. We show that …
The paper analyzes risk measures and optimal reserve allocation strategies.
problem Risk measures and optimal reserve allocation across multiple lines of business.
method Formalizes expected maximum deficit, introduces implicitly bounded risk measures, and proposes capital allocation approaches.
result Theoretical results on static and dynamic coherence, convexity, and exact optimizations of aggregate minimum reserves.
A new method approximates expected empirical loss for stochastic deep learning tasks.
problem Determining optimal step sizes for stochastic gradient descent in deep learning.
method Applying one-dimensional function fitting to noisy losses of vertical cross sections to approximate expected empirical loss.
result The method leads to a robust and straightforward optimization method that performs well across datasets and architectures.
This paper discusses the sensitivity of the long-term expected utility of optimal portfolios for an investor with constant relative risk aversion. Under an incomplete market given by a factor model, we consider the utility maximization problem with long-time horizon. The main purpose is to find the long-term sensitivit…
Efficiently designs experiments without integrating posterior distributions.
problem Computational inefficiency in Bayesian experimental design for PDE-based models.
method Likelihood-free approach using ANN to approximate conditional expectation.
result Significant reduction in observation model evaluations.
Quantum algorithm speeds up nested expectation estimation by nearly quadratically.
problem Estimating repeatedly nested expectations with quantum computing.
method Proposes a quantum algorithm achieving nearly quadratic speedup over classical methods.
result Achieves nearly quadratic speedup for RNEs, up to logarithmic factors.
Optimal financial strategies minimize risk under uncertain models.
problem Maximizing utility in financial markets with model uncertainty.
method Optimized strategies converge to those with minimal norm as uncertainty increases.
result Optimal strategies with minimal norm emerge as uncertainty grows.
We propose a novel, theoretically-grounded, acquisition function for Batch Bayesian optimization informed by insights from distributionally ambiguous optimization. Our acquisition function is a lower bound on the well-known Expected Improvement function, which requires evaluation of a Gaussian Expectation over a multiv…
The study finds lottery tickets with positive expected returns are not worth buying.
problem Determining which lottery tickets have positive expected returns.
method Elementary portfolio analysis to evaluate investment strategies.
result Optimal investment strategy includes a very small allocation for lottery tickets with positive expected returns.
In this paper we will discuss the optimal risk transfer problems when risk measures are generated by G-expectations, and we present the relationship between inf-convolution of G-expectations and the inf-convolution of drivers G.
We consider an infinite dimensional optimization problem motivated by mathematical economics. Within the celebrated "Arbitrage Pricing Model", we use probabilistic and functional analytic techniques to show the existence of optimal strategies for investors who maximize their expected utility.
Two approaches integrate qualitative views into portfolio optimization, showing aggregation methods outperform robust optimization.
problem Incorporating qualitative views into portfolio optimization models.
method Robust optimization and order aggregation methods.
result Aggregation methods outperform robust optimization in portfolio performance analysis.
In this paper, we focus on the problem of stochastic optimization where the objective function can be written as an expectation function over a closed convex set. We also consider multiple expectation constraints which restrict the domain of the problem. We extend the cooperative stochastic approximation algorithm from…
Optimizes target value in stochastic black box functions.
problem Finding input to minimize expected squared error to target value.
method Derives acquisition functions for expected improvement, probability of improvement, and lower confidence bound, assuming Gaussian aleatoric effects.
result Acquisition functions can outperform classical Bayesian optimization under certain conditions.
Optimal strategy identified for minimizing regret in fixed-budget best arm selection.
problem Minimizing expected simple regret in fixed-budget best arm selection.
method Two-Stage (TS)-Hirano-Imbens-Ridder (HIR) strategy using HIR estimator.
result TS-HIR strategy is asymptotically minimax optimal.
Optimizes treatment allocation using covariates for better outcomes.
problem Improving treatment allocation in multi-armed bandit problems.
method Maximizes a functional of the conditional potential outcome distribution.
result Developed expected regret lower bounds and near minimax optimal policy.
The expected utility operators introduced in a previous paper, offer a framework for a general risk aversion theory, in which risk is modelled by a fuzzy number A. In this paper we formulate a coinsurance problem in the possibilistic setting defined by an expected utility operator T. Some properties of the optimal …
Establishes geometric convergence of iterative optimization algorithms.
problem Analyzes convergence of iterative optimization algorithms under general assumptions.
method General framework for iterative optimization algorithms, proving asymptotic geometric convergence and providing convergence rates.
result Asymptotic geometric convergence of iterative optimization algorithms with exact rate.
A classical portfolio theory deals with finding the optimal proportion in which an agent invests a wealth in a risk-free asset and a probabilistic risky asset. Formulating and solving the problem depend on how the risk is represented and how, combined with the utility function defines a notion of expected utility. In t…
We construct a time-consistent sublinear expectation in the setting of volatility uncertainty. This mapping extends Peng's G-expectation by allowing the range of the volatility uncertainty to be stochastic. Our construction is purely probabilistic and based on an optimal control formulation with path-dependent control …
New method optimizes costly functions with unknown costs and budget constraints.
problem Optimizing functions with unknown and heterogeneous evaluation costs under a budget constraint.
method Budgeted multi-step expected improvement acquisition function.
result Our method outperforms existing approaches in various synthetic and real problems.
Optimal transport framework for density estimation with constraints.
problem Density estimation under expectation constraints.
method Minimizes Wasserstein distance subject to expected value constraints and regularization.
result Framework effectively addresses non-smooth constraints through annealing-like algorithm.
A non-Euclidean generalization of conditional expectation is introduced and characterized as the minimizer of expected intrinsic squared-distance from a manifold-valued target. The computational tractable formulation expresses the non-convex optimization problem as transformations of Euclidean conditional expectation. …
Study preferences over uncertain time payments, finds growth-optimality better than expected utility theory.
problem Understanding how people make decisions with uncertain timing of payments.
method Normative model of growth-optimality, revisiting experimental evidence on time lotteries.
result Growth-optimality better explains experimental data on time lotteries than expected discounted utility theory.
In recent years, the evaluation of the minimal investment risk of the quenched disordered system of a portfolio optimization problem and the investment concentration of the optimal portfolio has been actively investigated using the analysis methods of statistical mechanical informatics. However, the work to date has no…
A new method for high-dimensional Bayesian optimization.
problem Challenges in extending BO to high dimensions.
method Expected Coordinate Improvement (ECI) criterion for high-dimensional Bayesian optimization.
result Significantly better results than standard BO and competitive results with state-of-the-art methods.
Investigates risk measures for DC pension decumulation.
problem Develop optimal decumulation strategies for DC plan holders.
method Formulates decumulation as a control problem, studies risk measures (expected shortfall, linear shortfall, probability of shortfall).
result Optimal controls for expected reward and expected shortfall are identical to those for expected reward and linear shortfall.
Posterior sampling-based EI achieves sublinear regret bounds for expensive function optimization.
problem Theoretical analysis of expected improvement (EI) in Bayesian optimization.
method Randomized posterior sampling of EI.
result Achieves sublinear Bayesian cumulative regret bounds.
We propose a flexible framework for hedging a contingent claim by holding static positions in vanilla European calls, puts, bonds, and forwards. A model-free expression is derived for the optimal static hedging strategy that minimizes the expected squared hedging error subject to a cost constraint. The optimal hedge in…
LogEI improves Bayesian optimization by simplifying numerical computation of EI and related functions.
problem Numerical pathologies in optimizing EI and related acquisition functions.
method Proposes LogEI, a family of acquisition functions that simplify numerical optimization.
result LogEI members improve optimization performance and match or exceed state-of-the-art methods.
GBC methods compute expected utility without needing the model's density.
problem Computing expected utility in complex models.
method Density-free generative method using quantile neural estimator.
result Efficient estimation of expected utility from simulated data.
Optimal portfolios are found for a wide range of utility functions under hyperbolic returns.
problem Portfolio optimization under expected utility criterion for large portfolios.
method Analytical expressions for optimal portfolios under hyperbolic return distributions and various utility functions.
result The two-fund separation holds true for a broad class of utility functions.
Paper analyzes convergence rate of noisy Bayesian Optimization with Expected Improvement.
problem Theoretical convergence behaviors and rates of Expected Improvement (EI) in Bayesian optimization.
method Analyzes Expected Improvement (EI) under Gaussian process (GP) prior assumption, considering noisy observations.
result Established asymptotic error bound and rate for GP-EI with noisy observations.
A new parallel BO method with exact gradients for multi-objective optimization.
problem Efficiently optimizing multiple objectives in a sample-efficient manner.
method Derive q-Expected Hypervolume Improvement (qEHVI) for parallel, constrained evaluation.
result qEHVI is computationally tractable and outperforms state-of-the-art methods.
Stochastic gradient methods can converge in expectation under heavy-tailed noise.
problem Convergence of stochastic gradient methods under heavy-tailed noise.
method Comprehensive study of stochastic optimization under heavy-tailed noise for extsfSGD, extsfSMD, extsfASMD, extsfSGDM in convex and nonconvex optimization. result Established in-expectation convergence results for various stochastic gradient methods.
The paper explores optimal insurance contracts using various deviation measures.
problem Optimal insurance contracts with mean-deviation measures.
method Study of convex signed Choquet integrals and standard deviation as deviation measures, analyzing premium principles like expected value, Value-at-Risk, and Expected Shortfall.
result Characterization of optimal indemnities and deductibles under different premium principles.
New method optimizes risk estimation for financial losses.
problem Estimating expected shortfall risk for heavy-tailed distributions.
method Proposes a novel estimator for expected shortfall robust to data corruption.
result Demonstrates superior performance and robustness compared to classical methods.
We propose an extension of the concept of Expected Improvement criterion commonly used in Kriging based optimization. We extend it for more complex Kriging models, e.g. models using derivatives. The target field of application are CFD problems, where objective function are extremely expensive to evaluate, but the theor…