English
Related papers

Related papers: Policy Gradients for CVaR-Constrained MDPs

200 papers

In this paper, we develop a new accelerated stochastic gradient method for efficiently solving the convex regularized empirical risk minimization problem in mini-batch settings. The use of mini-batches is becoming a golden standard in the…

Optimization and Control · Mathematics 2017-09-20 Tomoya Murata , Taiji Suzuki

Conditional Value at Risk (CVaR) is widely used to account for the preferences of a risk-averse agent in the extreme loss scenarios. To study the effectiveness of randomization in interdiction games with an interdictor that is both risk and…

Computer Science and Game Theory · Computer Science 2020-03-19 Utsav Sadana , Erick Delage

A new approach in stochastic optimization via the use of stochastic gradient Langevin dynamics (SGLD) algorithms, which is a variant of stochastic gradient decent (SGD) methods, allows us to efficiently approximate global minimizers of…

Portfolio Management · Quantitative Finance 2020-07-06 Sotirios Sabanis , Ying Zhang

Among the very first variance reduced stochastic methods for solving the empirical risk minimization problem was the SVRG method (Johnson & Zhang 2013). SVRG is an inner-outer loop based method, where in the outer loop a reference full…

Optimization and Control · Mathematics 2021-07-05 Othmane Sebbouh , Nidham Gazagnadou , Samy Jelassi , Francis Bach , Robert M. Gower

The paper deals with finite-state Markov decision processes (MDPs) with integer weights assigned to each state-action pair. New algorithms are presented to classify end components according to their limiting behavior with respect to the…

Logic in Computer Science · Computer Science 2018-05-01 Christel Baier , Nathalie Bertrand , Clemens Dubslaff , Daniel Gburek , Ocan Sankur

We study a linear-quadratic, optimal control problem on a discrete, finite time horizon with distributional ambiguity, in which the cost is assessed via Conditional Value-at-Risk (CVaR). We take steps toward deriving a scalable dynamic…

Systems and Control · Electrical Eng. & Systems 2022-06-28 Margaret P. Chapman , Laurent Lessard

Conditional value at risk (CVaR) is a popular measure for quantifying portfolio risk. Sensitivity analysis of CVaR is very useful in risk management and gradient-based optimization algorithms. In this paper, we study the infinitesimal…

Numerical Analysis · Mathematics 2020-09-22 Zhijian He

We study a class of stochastic optimal design problems for elliptic partial differential equations in divergence form, where the coefficients represent mixtures of two conducting materials. The objective is to minimize a generalized risk…

Optimization and Control · Mathematics 2026-02-24 Amal Alphonse , Petar Kunštek , Marko Vrdoljak

We propose policy gradient algorithms which learn risk-sensitive policies in a reinforcement learning (RL) framework. Our proposed algorithms maximize the distortion risk measure (DRM) of the cumulative reward in an episodic Markov decision…

Machine Learning · Computer Science 2024-02-06 Nithia Vijayan , Prashanth L. A

We study the Stochastic Shortest Path (SSP) problem for autonomous systems with mixed max-sum cost aggregations under Linear Temporal Logic constraints. Classical SSP formulations rely on sum-aggregated costs, which are suitable for…

Systems and Control · Electrical Eng. & Systems 2025-12-16 Zhiquan Zhang , Omar Muhammetkulyyev , Tichakorn Wongpiromsarn , Melkior Ornik

Constrained Markov decision processes (CMDPs) are used as a decision-making framework to study the long-run performance of a stochastic system. It is well-known that a stationary optimal policy of a CMDP problem under discounted cost…

Optimization and Control · Mathematics 2025-06-02 V Varagapriya , Vikas Vikram Singh , Abdel Lisser

The low-rank stochastic semidefinite optimization has attracted rising attention due to its wide range of applications. The nonconvex reformulation based on the low-rank factorization, significantly improves the computational efficiency but…

Optimization and Control · Mathematics 2021-01-05 Jinshan Zeng , Yixuan Zha , Ke Ma , Yuan Yao

Stochastic gradient descent is the method of choice for large-scale machine learning problems, by virtue of its light complexity per iteration. However, it lags behind its non-stochastic counterparts with respect to the convergence rate,…

Machine Learning · Statistics 2016-03-23 Vatsal Shah , Megasthenis Asteris , Anastasios Kyrillidis , Sujay Sanghavi

We consider stochastic strongly-convex-strongly-concave (SCSC) saddle point (SP) problems which frequently arise in applications ranging from distributionally robust learning to game theory and fairness in machine learning. We focus on the…

Optimization and Control · Mathematics 2023-07-17 Yassine Laguel , Necdet Serhat Aybat , Mert Gürbüzbalaban

We propose a new stochastic optimization framework for empirical risk minimization problems such as those that arise in machine learning. The traditional approaches, such as (mini-batch) stochastic gradient descent (SGD), utilize an…

Machine Learning · Statistics 2020-02-04 Kenji Kawaguchi , Haihao Lu

Although well-established in general reinforcement learning (RL), value-based methods are rarely explored in constrained RL (CRL) for their incapability of finding policies that can randomize among multiple actions. To apply value-based…

Machine Learning · Computer Science 2022-06-28 Tianchi Cai , Wenpeng Zhang , Lihong Gu , Xiaodong Zeng , Jinjie Gu

In this paper we provide faster algorithms for approximately solving discounted Markov Decision Processes in multiple parameter regimes. Given a discounted Markov Decision Process (DMDP) with $|S|$ states, $|A|$ actions, discount factor…

Data Structures and Algorithms · Computer Science 2020-12-24 Aaron Sidford , Mengdi Wang , Xian Wu , Yinyu Ye

We propose a novel algorithm, TR-SVR, for solving unconstrained stochastic optimization problems. This method builds on the trust-region framework, which effectively balances local and global exploration in optimization tasks. TR-SVR…

Optimization and Control · Mathematics 2024-12-03 Xinshou Zheng

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…

Machine Learning · Computer Science 2017-06-12 Simon S. Du , Jianshu Chen , Lihong Li , Lin Xiao , Dengyong Zhou

We consider a composite convex minimization problem associated with regularized empirical risk minimization, which often arises in machine learning. We propose two new stochastic gradient methods that are based on stochastic dual averaging…

Optimization and Control · Mathematics 2016-03-09 Tomoya Murata , Taiji Suzuki