English
Related papers

Related papers: A New Optimal Stepsize For Approximate Dynamic Pro…

200 papers

We prove the first, even super-polynomial, lower bounds on the size of tropical (min,+) and (max,+) circuits approximating given optimization problems. Many classical dynamic programming (DP) algorithms for optimization problems are pure in…

Computational Complexity · Computer Science 2020-12-24 Stasys Jukna , Hannes Seiwert

Markov decision processes (MDPs) with large number of states are of high practical interest. However, conventional algorithms to solve MDP are computationally infeasible in this scenario. Approximate dynamic programming (ADP) methods tackle…

Systems and Control · Computer Science 2014-11-19 Chandrashekar Lakshminarayanan , Shalabh Bhatnagar

Let $P=(P_1, P_2, \ldots, P_n)$, $P_i \in \field{R}$ for all $i$, be a signal and let $C$ be a constant. In this work our goal is to find a function $F:[n]\rightarrow \field{R}$ which optimizes the following objective function: $$ \min_{F}…

Data Structures and Algorithms · Computer Science 2015-03-13 Gary L. Miller , Richard Peng , Russell Schwartz , Charalampos E. Tsourakakis

Approximate computing is a computation domain which can be used to trade time and energy with quality and therefore is useful in embedded systems. Energy is the prime resource in battery-driven embedded systems, like robots. Approximate…

Robotics · Computer Science 2021-08-30 Hrishav Bakul Barua

Recently, convergence as well as convergence rate analyses of deep learning optimizers for nonconvex optimization have been widely studied. Meanwhile, numerical evaluations for the optimizers have precisely clarified the relationship…

Optimization and Control · Mathematics 2021-08-27 Hideaki Iiduka

The training of deep neural networks is inherently a nonconvex optimization problem, yet standard approaches such as stochastic gradient descent (SGD) require simultaneous updates to all parameters, often leading to unstable convergence and…

Machine Learning · Computer Science 2025-08-07 Chengcheng Yan , Jiawei Xu , Zheng Peng , Qingsong Wang

Real Time Dynamic Programming (RTDP) is an online algorithm based on Dynamic Programming (DP) that acts by 1-step greedy planning. Unlike DP, RTDP does not require access to the entire state space, i.e., it explicitly handles the…

Machine Learning · Computer Science 2020-10-13 Yonathan Efroni , Mohammad Ghavamzadeh , Shie Mannor

We revisit adaptive time stepping, one of the classical topics of numerical analysis and computational engineering. While widely used in application and subject of many theoretical works, a complete understanding is still missing. Apart…

Numerical Analysis · Mathematics 2025-06-24 Michael Feischl , David Niederkofler

We consider approximate dynamic programming in $\gamma$-discounted Markov decision processes and apply it to approximate planning with linear value-function approximation. Our first contribution is a new variant of Approximate Policy…

Machine Learning · Computer Science 2022-10-31 Gellért Weisz , András György , Tadashi Kozuno , Csaba Szepesvári

Gradient descent is slow to converge for ill-conditioned problems and non-convex problems. An important technique for acceleration is step-size adaptation. The first part of this paper contains a detailed review of step-size adaptation…

Machine Learning · Computer Science 2022-05-27 Hengshuai Yao

Neuro-dynamic programming is a class of powerful techniques for approximating the solution to dynamic programming equations. In their most computationally attractive formulations, these techniques provide the approximate solution only…

Machine Learning · Computer Science 2016-04-18 Wei Chen , Dayu Huang , Ankur A. Kulkarni , Jayakrishnan Unnikrishnan , Quanyan Zhu , Prashant Mehta , Sean Meyn , Adam Wierman

On-demand ride-pooling (e.g., UberPool) has recently become popular because of its ability to lower costs for passengers while simultaneously increasing revenue for drivers and aggregation companies. Unlike in Taxi on Demand (ToD) services…

Computers and Society · Computer Science 2019-11-21 Sanket Shah , Meghna Lowalekar , Pradeep Varakantham

We introduce a new method, stepwise method for solving optimal con- trol problems. Our first motivation for new approach emanate from limi- tations on continuous time control functions in PMP. Practically in most of the real world models,…

Optimization and Control · Mathematics 2015-06-26 Mehdi Afshar , Farshad Merrikhbayat , Mohammad Reza Razvan

While evolutionary algorithms are known to be very successful for a broad range of applications, the algorithm designer is often left with many algorithmic choices, for example, the size of the population, the mutation rates, and the…

Neural and Evolutionary Computing · Computer Science 2015-04-14 Benjamin Doerr , Carola Doerr

We develop a method for obtaining safe initial policies for reinforcement learning via approximate dynamic programming (ADP) techniques for uncertain systems evolving with discrete-time dynamics. We employ kernelized Lipschitz estimation…

Systems and Control · Electrical Eng. & Systems 2019-07-05 Ankush Chakrabarty , Devesh K. Jha , Gregery T. Buzzard , Yebin Wang , Kyriakos Vamvoudakis

Recently, Stochastic Gradient Descent (SGD) and its variants have become the dominant methods in the large-scale optimization of machine learning (ML) problems. A variety of strategies have been proposed for tuning the step sizes, ranging…

Machine Learning · Computer Science 2022-08-02 Xiaoyu Li

Differential Dynamic Programming (DDP) has become a well established method for unconstrained trajectory optimization. Despite its several applications in robotics and controls however, a widely successful constrained version of the…

Optimization and Control · Mathematics 2020-05-05 Yuichiro Aoyama , George Boutselis , Akash Patel , Evangelos A. Theodorou

The principle of optimality is a fundamental aspect of dynamic programming, which states that the optimal solution to a dynamic optimization problem can be found by combining the optimal solutions to its sub-problems. While this principle…

Optimization and Control · Mathematics 2024-08-14 Bar Light

With the advent of the era of big data, deep learning has become a prevalent building block in a variety of machine learning or data mining tasks, such as signal processing, network modeling and traffic analysis, to name a few. The massive…

Cryptography and Security · Computer Science 2019-12-20 Zhiying Xu , Shuyu Shi , Alex X. Liu , Jun Zhao , Lin Chen

Adaptive optimizers, most notably Adam, have become the default standard for training large-scale neural networks such as Transformers. These methods maintain running estimates of gradient first and second moments, incurring substantial…

Machine Learning · Computer Science 2026-05-12 Yao Lu , Dengdong Fan , Shixun Zhang , Yonghong Tian
‹ Prev 1 8 9 10 Next ›