This paper proposes a method to safely adjust exploration in RL to satisfy constraints.
problem Unsafe exploration in reinforcement learning violates constraints on controlled object states.
method Automatic adjustment of exploration inputs and variance-covariance matrix for safety.
result The method guarantees satisfaction of joint chance constraints with specified probability.
CPP solves chance constrained optimization problems with a framework that combines samples and quantile lemma.
problem Chance constrained optimization problems with constraints on random variables.
method CPP framework using samples and quantile lemma to transform into deterministic problem.
result CPP provides a posteriori guarantees on constraint satisfaction and can handle different types of chance constraints.
A new RL method handles uncertainty and constraints in real-time optimization.
problem Real-time optimization under process uncertainty and constraints.
method Chance-constrained reinforcement learning to handle probabilistic state constraints.
result Satisfies process constraints with high probability in real-time.
Study scaling of optimal solutions for reliability constraints in resource provisioning.
problem Achieving high reliability in resource provisioning under stringent requirements.
method Chance-constrained optimization, distributionally robust optimization, f-divergence balls, line search.
result Correct scaling properties of optimal decisions are preserved by using appropriate f-divergence balls, leading to conservative yet near-optimal solutions.
This work proposes an online learning approach to tighten constraints in stochastic control problems.
problem Solving chance-constrained stochastic optimal control problems is computationally challenging.
method Reformulate chance constraints as a binary regression problem and use a GP model to learn constraint-tightening parameters online.
result The approach tightens constraints more effectively, leading to lower costs in numerical experiments.
Chance-constrained ActInf allows for small violations of constraints to drive goal-directed behavior.
problem Goal-directed behavior constrained by prior beliefs.
method Introducing chance constraints to ActInf, allowing for small violations of constraints.
result Chance-constrained ActInf allows for a trade-off between robust control and chance constraint violation.
Develops a new method for optimizing with uncertain data.
problem Uncertainty in real-world optimization problems.
method Combines chance constraints and constraint learning for mixed-integer linear optimization.
result Data-driven solution for setting probabilistic bounds on learned constraints.
A scalable method for deep metric learning using chance constraints.
problem Improving deep metric learning by addressing feasibility issues.
method Relating DML to chance constraints, reformulating as a feasibility problem, and iteratively training proxies.
result The method effectively improves deep metric learning performance across multiple benchmarks.
The paper tackles online resource allocation with uncertain coefficients and chance constraints.
problem Online stochastic resource allocation problem with chance constraints.
method Linearization and primal-dual algorithms with heuristic corrections.
result Optimality gap and constraint violation are on the order of √n.
We discuss the role of integrated chance constraints (ICC) as quantitative risk constraints in asset and liability management (ALM) for pension funds. We define two types of ICC: the one period integrated chance constraint (OICC) and the multiperiod integrated chance constraint (MICC). As their names suggest, the OICC …
Voltage control plays an important role in the operation of electricity distribution networks, especially with high penetration of distributed energy resources. These resources introduce significant and fast varying uncertainties. In this paper, we focus on reactive power compensation to control voltage in the presence…
We propose a stochastic approximation method for approximating the efficient frontier of chance-constrained nonlinear programs. Our approach is based on a bi-objective viewpoint of chance-constrained programs that seeks solutions on the efficient frontier of optimal objective value versus risk of constraint violation. …
Bayesian method optimizes uncertain constraints in black-box function optimization.
problem Optimizing black-box functions with uncertain environmental variables.
method Distributionally robust chance-constrained Bayesian optimization.
result The method can find accurate solutions with high probability in a finite number of trials.
This paper provides a non-robust interpretation of the distributionally robust optimization (DRO) problem by relating the distributional uncertainties to the chance probabilities. Our analysis allows a decision-maker to interpret the size of the ambiguity set, which is often lack of business meaning, through the chance…
Paper tackles SMPC for linear systems with unknown noise distribution.
problem Stochastic MPC for linear systems with chance state constraints and unknown noise distribution.
method Reformulate chance constraints, design robust benchmark SMPC, and develop adaptive SMPC with online noise statistics learning.
result Adaptive SMPC guarantees time-uniform satisfaction of unknown reformulated state constraints with high probability.
Improves logistic regression performance with nonconvex programming.
problem Stochastic generalized linear regression with chance constraints.
method Nonconvex programming techniques, clustering, quantile estimation.
result Over 1 to 2 percent improvement in model performance.
A new Bayesian optimization method tackles constrained optimization with uncertainties.
problem Optimizing functions with uncertain constraints.
method Bayesian optimization with a new acquisition criterion.
result The new criterion optimizes both objective function improvement and constraint reliability.
Develops a machine learning approach for solving AC-OPF problems.
problem Nonlinear and computationally demanding AC chance-constrained OPF problem.
method Uses Gaussian process regression to approximate AC power flow equations.
result Demonstrates competitive and promising results compared to state-of-the-art approaches.
Paper develops robust OPF method using contextual information.
problem Optimal Power Flow problem under incomplete uncertainty knowledge.
method Distributionally robust chance-constrained formulation with probability trimmings and optimal transport.
result Distributional robustness improves expected cost and system reliability.
Optimizes power systems with energy storage under uncertainty using scenario-based method.
problem Optimizing power systems with energy storage, intermittent renewable generation, and uncontrollable loads under uncertainty.
method Developed a novel solution method based on scenario optimization and strategic sampling to solve the chance-constrained optimal power system operation problem.
result The strategic sampling method significantly improves computational efficiency and data-driven convex approximation of power flow.
A new model of learning corrects for chance to improve learning outcomes.
problem The importance of chance-corrected measures in learning.
method Developed two models: Informatron and AdaBook, based on empirical psychological results.
result Chance correction facilitates learning, as shown by computational results.
New algorithms improve boosting by optimizing chance-corrected measures.
problem Improving boosting algorithms to use chance-corrected measures effectively.
method Developed new algorithms (AdaBook and Multibook) that optimize chance-corrected measures.
result AdaBook and Multibook outperform standard Multiboost or AdaBoost in multiclass situations.
Robust MCVaR portfolio optimization using RKHS for risk management.
problem Minimizing portfolio risk while achieving higher returns under uncertainty.
method Introduces a robust MCVaR model with ellipsoidal support and RKHS uncertainty set for chance constraint.
result Robust model outperforms nominal and market portfolios in various market conditions.
The objective in a traditional reinforcement learning (RL) problem is to find a policy that optimizes the expected value of a performance metric such as the infinite-horizon cumulative discounted or long-run average cost/reward. In practice, optimizing the expected value alone may not be satisfactory, in that it may be…
Motivated by problems of anomaly detection, this paper implements the Neyman-Pearson paradigm to deal with asymmetric errors in binary classification with a convex loss. Given a finite collection of classifiers, we combine them and obtain a new classifier that satisfies simultaneously the two following properties with …
The logic of uncertainty is not the logic of experience and as well as it is not the logic of chance. It is the logic of experience and chance. Experience and chance are two inseparable poles. These are two dual reflections of one essence, which is called co~event. The theory of experience and chance is the theory of c…
Estimates multiple linear systems on a graph with smoothness constraints.
problem Joint estimation of multiple linear systems under graph smoothness constraints.
method Proposes estimators for joint estimation of system matrices with error bounds.
result MSE converges to zero as m increases, typically polynomially fast w.r.t m. NMF with specific constraints is equivalent to LDA.
problem Dimensionality reduction of non-negative data.
method NMF with ℓ1 normalization constraints and Dirichlet prior. result NMF with these constraints is equivalent to LDA.
Paper uses Gaussian processes to solve AC-OPF with renewable uncertainty.
problem Optimizing power grids with fluctuating renewable sources.
method Data-driven approach using Gaussian processes.
result Efficiently solves chance-constrained AC-OPF with uncertainty.
We study system design problems stated as parameterized stochastic programs with a chance-constraint set. We adopt a Bayesian approach that requires the computation of a posterior predictive integral which is usually intractable. In addition, for the problem to be a well-defined convex program, we must retain the conve…
New method for distributed online learning with communication constraints reduces joint regret.
problem Joint regret minimization in a distributed online learning setting with communication constraints.
method Adaptive graph partitioning and comparator-adaptive online convex optimization with delayed gradient information.
result Optimal graph partition selection for adversarial activations and gradients reduces joint regret.
Study on women entrepreneurs' access to finance in France.
problem Inequalities in accessing external finance for women entrepreneurs in France.
method Quantitative approach using data from a representative sample of women entrepreneurs.
result Founder status affects access to external finance; increases success in fundraising but reduces bank finance.
Chances of a gambler are always lower than chances of a casino in the case of an ideal, mathematically perfect roulette, if the capital of the gambler is limited and the minimum and maximum allowed bets are limited by the casino. However, a realistic roulette is not ideal: the probabilities of realisation of different …
The paper analyzes regret in online recommendation systems with constraints.
problem Analyzing regret in online recommendation systems with user-item constraints.
method Theoretical analysis and algorithm design considering user-item constraints and unknown probabilities.
result Derives regret lower bounds and algorithms achieving these limits for various structural assumptions.
New method certifies neural network robustness under random input noise.
problem Certifying neural network robustness against random input noise.
method Chance-constrained optimization problem reformulated with input-output samples, convex conditions developed.
result Proposed method certifies robustness against various input noise regimes over larger uncertainty regions.
A new method uses GANs for robust optimization under uncertain data.
problem Optimizing supply chains under demand uncertainty with ambiguous distributions.
method Generative adversarial networks (GANs) for data-driven distributionally robust chance constrained programming.
result The approach effectively handles uncertain data distributions and improves supply chain optimization.
Statistical models of economic distributions lead to Boltzmann distributions rather than a Pareto power law. This result is supported by two facts: 1. the distributions of income, car sales, marriages or jobs are a matter of chances and luck and not of reason! 2. Data for property, automobile sales, marriages and job m…
Combines Gaussian processes and polynomial chaos for stochastic control.
problem Uncertainties in dynamic models lead to performance issues in predictive control.
method Combines Gaussian processes with polynomial chaos expansions to estimate probability distributions of nonlinear functions.
result Demonstrates accurate approximation and closed-loop performance in stochastic nonlinear model predictive control.
We provide analytical results for a static portfolio optimization problem with two coherent risk measures. The use of two risk measures is motivated by joint decision-making for portfolio selection where the risk perception of the portfolio manager is of primary concern, hence, it appears in the objective function, and…
The concepts of risk-aversion, chance-constrained optimization, and robust optimization have developed significantly over the last decade. Statistical learning community has also witnessed a rapid theoretical and applied growth by relying on these concepts. A modeling framework, called distributionally robust optimizat…
USS fund risk assessment shows low default chance but high overfunding.
problem Risk assessment of Universities Superannuation Scheme (USS) fund.
method Estimates risk of default and overfunding using a cautious model.
result Fund has less than 7% chance of defaulting but overfunding by at least £100bn.
Generalizes information theory for hierarchical partitions.
problem Understanding hierarchical decomposition of complex systems.
method Introducing a generalization of information theory for hierarchical partitions, revisiting Hierarchical Mutual Information (HMI), and proving its bounds and transformations.
result Derives hierarchical generalizations of information-theoretic quantities, including a non-metric variation of information.
FastAMI efficiently approximates AMI and SMI for large datasets.
problem Computational difficulty in comparing clusterings with an adjustment for chance.
method Monte Carlo-based approach to approximate AMI and SMI.
result FastAMI provides accurate results for large datasets.
Improved text generation with constraints using discrete auto-regressive biasing.
problem Balancing fluency and constraint satisfaction in LLM outputs.
method Discrete Auto-regressive Biasing, leveraging gradients in discrete text space.
result Significantly improved constraint satisfaction with comparable fluency.
GP CC-OPF solves uncertain power grid optimization with Gaussian Process.
problem Uncertainty in power grid operations due to high renewables integration.
method Data-driven Gaussian Process regression for solving non-convex CC-OPF problem.
result Effective economic dispatch optimization in uncertain power grids.
Paper proposes a fast data-driven AC-OPF method using sparse hybrid Gaussian processes.
problem Optimizing electricity generation and delivery under generation uncertainty in modern power grids.
method Data-driven approach using sparse hybrid Gaussian processes to model power flow equations.
result Shows up to two times faster and more accurate solutions compared to state-of-the-art methods.
Risk-controlled post-processing optimizes decision policies under risk constraints.
problem Optimizing decision policies with risk constraints for better outcomes.
method Developed a post-processing algorithm that selects a threshold based on fitted fallback policy and score, leveraging tools from algorithmic stability and stochastic processes.
result The post-processed policy achieves precise expected risk control under exchangeability and meets or nearly meets risk budgets while preserving more agreement with the baseline.
The paper critiques and expands on common evaluation metrics in machine learning.
problem The common evaluation metrics like Precision, Recall, F-Measure, and Rand Accuracy are biased and misleading.
method The paper introduces new measures like Informedness, Markedness, and Correlation to better reflect the quality of predictions.
result A system that performs worse in terms of Informedness can appear better using common measures like Precision and Recall.