English
Related papers

Related papers: n-Step Temporal Difference Learning with Optimal n

200 papers

We consider $d$-dimensional linear stochastic approximation algorithms (LSAs) with a constant step-size and the so called Polyak-Ruppert (PR) averaging of iterates. LSAs are widely applied in machine learning and reinforcement learning…

Machine Learning · Computer Science 2017-09-14 Chandrashekar Lakshminarayanan , Csaba Szepesvári

We present a method for Temporal Difference (TD) learning that addresses several challenges faced by robots learning to navigate in a marine environment. For improved data efficiency, our method reduces TD updates to Gaussian Process…

Machine Learning · Computer Science 2018-10-03 John Martin , Jinkun Wang , Brendan Englot

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

Temporal-difference learning is a popular algorithm for policy evaluation. In this paper, we study the convergence of the regularized non-parametric TD(0) algorithm, in both the independent and Markovian observation settings. In particular,…

Optimization and Control · Mathematics 2022-05-25 Eloïse Berthier , Ziad Kobeissi , Francis Bach

Stochastic Gradient Descent (SGD) has played a central role in machine learning. However, it requires a carefully hand-picked stepsize for fast convergence, which is notoriously tedious and time-consuming to tune. Over the last several…

Machine Learning · Computer Science 2019-06-10 Zhenxun Zhuang , Ashok Cutkosky , Francesco Orabona

We study differentially private (DP) algorithms for stochastic convex optimization: the problem of minimizing the population loss given i.i.d. samples from a distribution over convex loss functions. A recent work of Bassily et al. (2019)…

Machine Learning · Computer Science 2020-05-12 Vitaly Feldman , Tomer Koren , Kunal Talwar

This paper considers convex optimization problems where nodes of a network have access to summands of a global objective. Each of these local objectives is further assumed to be an average of a finite set of functions. The motivation for…

Optimization and Control · Mathematics 2015-06-16 Aryan Mokhtari , Alejandro Ribeiro

Training neural networks on image datasets generally require extensive experimentation to find the optimal learning rate regime. Especially, for the cases of adversarial training or for training a newly synthesized model, one would not know…

Machine Learning · Computer Science 2019-10-28 Koyel Mukherjee , Alind Khare , Ashish Verma

Recently, a new multi-step temporal learning algorithm, called $Q(\sigma)$, unifies $n$-step Tree-Backup (when $\sigma=0$) and $n$-step Sarsa (when $\sigma=1$) by introducing a sampling parameter $\sigma$. However, similar to other…

Artificial Intelligence · Computer Science 2018-02-12 Long Yang , Minhao Shi , Qian Zheng , Wenjia Meng , Gang Pan

In this work, we consider solving optimization problems with a stochastic objective and deterministic equality constraints. We propose a Trust-Region Sequential Quadratic Programming method to find both first- and second-order stationary…

Optimization and Control · Mathematics 2024-09-27 Yuchen Fang , Sen Na , Michael W. Mahoney , Mladen Kolar

Simultaneous perturbation stochastic approximation (SPSA) is widely used in stochastic optimization due to its high efficiency, asymptotic stability, and reduced number of required loss function measurements. However, the standard SPSA…

Optimization and Control · Mathematics 2023-02-07 Zhichao Jia , Ziyi Wei , James C. Spall

In this work, we conduct the first systematic study of stochastic variational inequality (SVI) and stochastic saddle point (SSP) problems under the constraint of differential privacy (DP). We propose two algorithms: Noisy Stochastic…

Optimization and Control · Mathematics 2022-04-04 Digvijay Boob , Cristóbal Guzmán

We propose a stochastic approximation (SA) based method with randomization of samples for policy evaluation using the least squares temporal difference (LSTD) algorithm. Our proposed scheme is equivalent to running regular temporal…

Machine Learning · Computer Science 2020-01-27 L. A. Prashanth , Nathaniel Korda , Rémi Munos

Acceleration is an increasingly common theme in the stochastic optimization literature. The two most common examples are Nesterov's method, and Polyak's momentum technique. In this paper two new algorithms are introduced for root finding…

Optimization and Control · Mathematics 2019-02-07 Adithya M. Devraj , Ana Bušić , Sean Meyn

Recently, the decentralized optimization problem is attracting growing attention. Most existing methods are deterministic with high per-iteration cost and have a convergence rate quadratically depending on the problem condition number.…

Machine Learning · Statistics 2018-05-28 Zebang Shen , Aryan Mokhtari , Tengfei Zhou , Peilin Zhao , Hui Qian

Value functions arise as a component of algorithms as well as performance metrics in statistics and engineering applications. Computation of the associated Bellman equations is numerically challenging in all but a few special cases. A…

Systems and Control · Computer Science 2018-12-27 Adithya M. Devraj , Sean P. Meyn

Gradient temporal difference (Gradient TD) algorithms are a popular class of stochastic approximation (SA) algorithms used for policy evaluation in reinforcement learning. Here, we consider Gradient TD algorithms with an additional heavy…

Machine Learning · Computer Science 2021-11-23 Rohan Deb , Shalabh Bhatnagar

We propose a statistical adaptive procedure called SALSA for automatically scheduling the learning rate (step size) in stochastic gradient methods. SALSA first uses a smoothed stochastic line-search procedure to gradually increase the…

Machine Learning · Statistics 2020-02-26 Pengchuan Zhang , Hunter Lang , Qiang Liu , Lin Xiao

The DTW Barycenter Averaging (DBA) algorithm is a widely used algorithm for estimating the mean of a given set of point sequences. In this context, the mean is defined as a point sequence that minimises the sum of dynamic time warping…

Computational Geometry · Computer Science 2024-01-12 Frederik Brüning , Anne Driemel , Alperen Ergür , Heiko Röglin

We study differentially private (DP) algorithms for stochastic non-convex optimization. In this problem, the goal is to minimize the population loss over a $p$-dimensional space given $n$ i.i.d. samples drawn from a distribution. We improve…

Machine Learning · Computer Science 2020-08-12 Yingxue Zhou , Xiangyi Chen , Mingyi Hong , Zhiwei Steven Wu , Arindam Banerjee