English
Related papers

Related papers: Expected Sarsa($\lambda$) with Control Variate for…

200 papers

Optimal Transport (OT) based distances are powerful tools for machine learning to compare probability measures and manipulate them using OT maps. In this field, a setting of interest is semi-discrete OT, where the source measure $\mu$ is…

Modern machine learning uses more and more advanced optimization techniques to find optimal hyper parameters. Whenever the objective function is non-convex, non continuous and with potentially multiple local minima, standard gradient…

Machine Learning · Computer Science 2019-02-13 Eric Benhamou , Jamal Atif , Rida Laraki

Selecting key variables from high-dimensional data is increasingly important in the era of big data. Sparse regression serves as a powerful tool for this purpose by promoting model simplicity and explainability. In this work, we revisit a…

Machine Learning · Computer Science 2025-09-09 Hyungjoon Soh , Dongha Lee , Vipul Periwal , Junghyo Jo

Direct policy gradient methods for reinforcement learning and continuous control problems are a popular approach for a variety of reasons: 1) they are easy to implement without explicit knowledge of the underlying model 2) they are an…

Machine Learning · Computer Science 2019-03-26 Maryam Fazel , Rong Ge , Sham M. Kakade , Mehran Mesbahi

Stochastic gradient descent (SGD), which dates back to the 1950s, is one of the most popular and effective approaches for performing stochastic optimization. Research on SGD resurged recently in machine learning for optimizing convex loss…

Machine Learning · Computer Science 2019-12-24 Jie Chen , Ronny Luss

We consider the off-policy estimation problem of estimating the expected reward of a target policy using samples collected by a different behavior policy. Importance sampling (IS) has been a key technique to derive (nearly) unbiased…

Machine Learning · Computer Science 2018-10-31 Qiang Liu , Lihong Li , Ziyang Tang , Dengyong Zhou

Stochastic approximation (SA) is a classical approach for stochastic convex optimization. Previous studies have demonstrated that the convergence rate of SA can be improved by introducing either smoothness or strong convexity condition. In…

Machine Learning · Computer Science 2019-01-29 Lijun Zhang , Zhi-Hua Zhou

Reinforcement learning (RL) is increasingly used to align large language models (LLMs). Off-policy methods offer greater implementation simplicity and data efficiency than on-policy techniques, but often result in suboptimal performance. In…

Machine Learning · Computer Science 2025-12-01 Charles Arnal , Gaëtan Narozniak , Vivien Cabannes , Yunhao Tang , Julia Kempe , Remi Munos

Several useful variance-reduced stochastic gradient algorithms, such as SVRG, SAGA, Finito, and SAG, have been proposed to minimize empirical risks with linear convergence properties to the exact minimizer. The existing convergence results…

Machine Learning · Computer Science 2018-02-19 Bicheng Ying , Kun Yuan , Ali H. Sayed

In this paper, we analyze the convergence rate of the gradient temporal difference learning (GTD) family of algorithms. Previous analyses of this class of algorithms use ODE techniques to prove asymptotic convergence, and to the best of our…

Machine Learning · Computer Science 2020-07-06 Bo Liu , Ji Liu , Mohammad Ghavamzadeh , Sridhar Mahadevan , Marek Petrik

We consider off-policy temporal-difference (TD) learning methods for policy evaluation in Markov decision processes with finite spaces and discounted reward criteria, and we present a collection of convergence results for several…

Machine Learning · Computer Science 2018-03-30 Huizhen Yu

We consider saddle point problems which objective functions are the average of $n$ strongly convex-concave individual components. Recently, researchers exploit variance reduction methods to solve such problems and achieve linear-convergence…

Machine Learning · Computer Science 2019-09-17 Luo Luo , Cheng Chen , Yujun Li , Guangzeng Xie , Zhihua Zhang

The control variates method is a classical variance reduction technique for Monte Carlo estimators that exploits correlated auxiliary variables without introducing bias. In many applications, the quantity of interest can be expressed as a…

Statistics Theory · Mathematics 2025-11-10 Louison Bocquet-Nouaille , Jérôme Morio , Benjamin Bobbia

This paper studies the convergence of clipped stochastic gradient descent (SGD) algorithms with decision-dependent data distribution. Our setting is motivated by privacy preserving optimization algorithms that interact with performative…

Optimization and Control · Mathematics 2025-01-31 Qiang Li , Michal Yemini , Hoi-To Wai

Although with progress in introducing auxiliary amortized inference models, learning discrete latent variable models is still challenging. In this paper, we show that the annoying difficulty of obtaining reliable stochastic gradients for…

Machine Learning · Statistics 2020-05-29 Zhijian Ou , Yunfu Song

Reinforcement learning (RL) algorithms are often categorized as either on-policy or off-policy depending on whether they use data from a target policy of interest or from a different behavior policy. In this paper, we study a subtle…

Machine Learning · Computer Science 2022-10-12 Rujie Zhong , Duohan Zhang , Lukas Schäfer , Stefano V. Albrecht , Josiah P. Hanna

Several authors have recently developed risk-sensitive policy gradient methods that augment the standard expected cost minimization problem with a measure of variability in cost. These studies have focused on specific risk-measures, such as…

Artificial Intelligence · Computer Science 2015-06-09 Aviv Tamar , Yinlam Chow , Mohammad Ghavamzadeh , Shie Mannor

Unbiased and consistent variance estimators generally do not exist for design-based treatment effect estimators because experimenters never observe more than one potential outcome for any unit. The problem is exacerbated by interference and…

Methodology · Statistics 2024-07-04 Christopher Harshaw , Joel A. Middleton , Fredrik Sävje

The learning and evaluation of energy-based latent variable models (EBLVMs) without any structural assumptions are highly challenging, because the true posteriors and the partition functions in such models are generally intractable. This…

Machine Learning · Computer Science 2021-06-08 Fan Bao , Kun Xu , Chongxuan Li , Lanqing Hong , Jun Zhu , Bo Zhang

Learning high-performance control policies that remain consistent with expert behavior is a fundamental challenge in robotics. Reinforcement learning can discover high-performing strategies but often departs from desirable human behavior,…

Robotics · Computer Science 2026-04-06 Siwei Ju , Jan Tauberschmidt , Oleg Arenz , Peter van Vliet , Jan Peters
‹ Prev 1 8 9 10 Next ›