English
Related papers

Related papers: Policy Gradient Optimal Correlation Search for Var…

200 papers

Simplicity is a powerful inductive bias. In reinforcement learning, regularization is used for simpler policies, data augmentation for simpler representations, and sparse reward functions for simpler objectives, all that, with the…

Machine Learning · Computer Science 2025-05-23 Bang You , Puze Liu , Huaping Liu , Jan Peters , Oleg Arenz

We develop a new primitive for stochastic optimization: a low-bias, low-cost estimator of the minimizer $x_\star$ of any Lipschitz strongly-convex function. In particular, we use a multilevel Monte-Carlo approach due to Blanchet and Glynn…

Optimization and Control · Mathematics 2021-10-29 Hilal Asi , Yair Carmon , Arun Jambulapati , Yujia Jin , Aaron Sidford

Control variates are a well-established tool to reduce the variance of Monte Carlo estimators. However, for large-scale problems including high-dimensional and large-sample settings, their advantages can be outweighed by a substantial…

Machine Learning · Statistics 2021-07-22 Shijing Si , Chris. J. Oates , Andrew B. Duncan , Lawrence Carin , François-Xavier Briol

In this work, we provide faster algorithms for approximating the optimal transport distance, e.g. earth mover's distance, between two discrete probability distributions $\mu, \nu \in \Delta^n$. Given a cost function $C : [n] \times [n] \to…

Data Structures and Algorithms · Computer Science 2020-01-29 Jose Blanchet , Arun Jambulapati , Carson Kent , Aaron Sidford

Mobility service route design requires demand information to operate in a service region. Transit planners and operators can access various data sources including household travel survey data and mobile device location logs. However, when…

Artificial Intelligence · Computer Science 2024-09-04 Gyugeun Yoon , Joseph Y. J. Chow

In this work we present a novel approach to hierarchical reinforcement learning for linearly-solvable Markov decision processes. Our approach assumes that the state space is partitioned, and the subtasks consist in moving between the…

Machine Learning · Computer Science 2024-06-04 Guillermo Infante , Anders Jonsson , Vicenç Gómez

Many reinforcement learning algorithms, particularly those that rely on return estimates for policy improvement, can suffer from poor sample efficiency and training instability due to high-variance return estimates. In this paper we…

Machine Learning · Computer Science 2026-01-06 Alexander W. Goodall , Edwin Hamel-De le Court , Francesco Belardinelli

In this work, we consider solving a distributed optimization problem in a multi-agent network with multiple clusters. In each cluster, the involved agents cooperatively optimize a separable composite function with a common decision…

Optimization and Control · Mathematics 2022-03-03 Jianzheng Wang , Guoqiang Hu

Can Monte Carlo (MC) solvers be directly used in gradient-based methods for PDE-constrained optimization problems? In these problems, a gradient of the loss function is typically presented as a product of two PDE solutions, one for the…

Numerical Analysis · Mathematics 2022-09-27 Qin Li , Li Wang , Yunan Yang

Importance sampling has been known as a powerful tool to reduce the variance of Monte Carlo estimator for rare event simulation. Based on the criterion of minimizing the variance of Monte Carlo estimator within a parametric family, we…

Methodology · Statistics 2013-02-11 Cheng-Der Fuh , Huei-Wen Teng , Ren-Her Wang

We develop an efficient stochastic variance reduced gradient descent algorithm to solve the affine rank minimization problem consists of finding a matrix of minimum rank from linear measurements. The proposed algorithm as a stochastic…

Optimization and Control · Mathematics 2022-11-08 Ningning Han , Juan Nie , Jian Lu , Michael K. Ng

Sparse high dimensional graphical model selection is a popular topic in contemporary machine learning. To this end, various useful approaches have been proposed in the context of $\ell_1$-penalized estimation in the Gaussian framework.…

Computation · Statistics 2022-02-04 Sang-Yun Oh , Onkar Dalal , Kshitij Khare , Bala Rajaratnam

Policy networks are a central feature of deep reinforcement learning (RL) algorithms for continuous control, enabling the estimation and sampling of high-value actions. From the variational inference perspective on RL, policy networks, when…

Machine Learning · Computer Science 2021-10-26 Joseph Marino , Alexandre Piché , Alessandro Davide Ialongo , Yisong Yue

In this article, we discuss the optimal allocation problem in an experiment when a regression model is used for statistical analysis. Monotonic convergence for a general class of multiplicative algorithms for $D$-optimality has been…

Computation · Statistics 2013-10-28 Wei Gao , Ping Shing Chan , Hon Keung Tony Ng , Xiaolei Lu

This paper investigates the problem of tracking solutions of stochastic optimization problems with time-varying costs that depend on random variables with decision-dependent distributions. In this context, we propose the use of an online…

Optimization and Control · Mathematics 2021-10-29 Killian Wood , Gianluca Bianchin , Emiliano Dall'Anese

The objective in statistical Optimal Transport (OT) is to consistently estimate the optimal transport plan/map solely using samples from the given source and target marginal distributions. This work takes the novel approach of posing…

Machine Learning · Computer Science 2020-11-11 J. Saketha Nath , Pratik Jawanpuria

We consider the core reinforcement-learning problem of on-policy value function approximation from a batch of trajectory data, and focus on various issues of Temporal Difference (TD) learning and Monte Carlo (MC) policy evaluation. The two…

We propose a new framework for generative modeling based on a discrete-time stochastic control formulation of measure transport. Adapting classic results from control theory, we formulate our problem as a linear program whose dual variables…

Machine Learning · Computer Science 2026-05-22 Pablo Moreno-Muñoz , Adrian Müller , Gergely Neu

We propose a numerical algorithm for the computation of multi-marginal optimal transport (MMOT) problems involving general probability measures that are not necessarily discrete. By developing a relaxation scheme in which marginal…

Optimization and Control · Mathematics 2025-12-29 Ariel Neufeld , Qikun Xiang

Optimal transport is a framework that facilitates the most efficient allocation of a limited amount of resources. However, the most efficient allocation scheme does not necessarily preserve the most fairness. In this paper, we establish a…

Optimization and Control · Mathematics 2021-04-01 Jason Hughes , Juntao Chen