English
Related papers

Related papers: Deep Reinforcement Learning via L-BFGS Optimizatio…

200 papers

Many recent successes of machine learning went hand in hand with advances in optimization. The exchange of ideas between these fields has worked both ways, with machine learning building on standard optimization procedures such as gradient…

Optimization and Control · Mathematics 2021-10-26 Konstantin Mishchenko

While large language models (LLMs) are increasingly used as automated heuristic designers for vehicle routing problems (VRPs), current state-of-the-art methods predominantly rely on prompting massive, general-purpose models like GPT-4. This…

Machine Learning · Computer Science 2025-10-14 Rongjie Zhu , Cong Zhang , Zhiguang Cao

We propose a new stochastic L-BFGS algorithm and prove a linear convergence rate for strongly convex and smooth functions. Our algorithm draws heavily from a recent stochastic variant of L-BFGS proposed in Byrd et al. (2014) as well as a…

Optimization and Control · Mathematics 2016-04-15 Philipp Moritz , Robert Nishihara , Michael I. Jordan

Reinforcement learning (RL) is a branch of machine learning which is employed to solve various sequential decision making problems without proper supervision. Due to the recent advancement of deep learning, the newly proposed Deep-RL…

Artificial Intelligence · Computer Science 2019-04-17 Dhruv Ramani

We propose a novel limited-memory stochastic block BFGS update for incorporating enriched curvature information in stochastic approximation methods. In our method, the estimate of the inverse Hessian matrix that is maintained by it, is…

Optimization and Control · Mathematics 2016-04-01 Robert M. Gower , Donald Goldfarb , Peter Richtárik

In this paper, we show that simple {Stochastic} subGradient Decent methods with multiple Restarting, named {\bf RSGD}, can achieve a \textit{linear convergence rate} for a class of non-smooth and non-strongly convex optimization problems…

Machine Learning · Computer Science 2016-04-01 Tianbao Yang , Qihang Lin

Bayesian Reinforcement Learning (RL) is capable of not only incorporating domain knowledge, but also solving the exploration-exploitation dilemma in a natural way. As Bayesian RL is intractable except for special cases, previous work has…

Artificial Intelligence · Computer Science 2013-06-14 Kenji Kawaguchi , Mauricio Araya

The classical line search for learning rate (LR) tuning in the stochastic gradient descent (SGD) algorithm can tame the convergence slowdown due to data-sampling noise. In a federated setting, wherein the client heterogeneity introduces a…

Machine Learning · Computer Science 2025-10-28 Geetika , Somya Tyagi , Bapi Chatterjee

We propose a trust region method for policy optimization that employs Quasi-Newton approximation for the Hessian, called Quasi-Newton Trust Region Policy Optimization QNTRPO. Gradient descent is the de facto algorithm for reinforcement…

Machine Learning · Computer Science 2019-12-30 Devesh Jha , Arvind Raghunathan , Diego Romeres

In this paper, we study and prove the non-asymptotic superlinear convergence rate of the Broyden class of quasi-Newton algorithms which includes the Davidon--Fletcher--Powell (DFP) method and the Broyden--Fletcher--Goldfarb--Shanno (BFGS)…

Optimization and Control · Mathematics 2021-12-02 Qiujiang Jin , Aryan Mokhtari

Mean Field Control Games (MFCGs) provide a powerful theoretical framework for analyzing systems of infinitely many interacting agents, blending elements from Mean Field Games (MFGs) and Mean Field Control (MFC). However, solving the coupled…

Machine Learning · Computer Science 2025-01-03 Nianli Peng , Yilin Wang

Recent development of Deep Reinforcement Learning (DRL) has demonstrated superior performance of neural networks in solving challenging problems with large or even continuous state spaces. One specific approach is to deploy neural networks…

Machine Learning · Computer Science 2022-03-15 Martin Gottwald , Sven Gronauer , Hao Shen , Klaus Diepold

Quasi-Newton methods refer to a class of algorithms at the interface between first and second order methods. They aim to progress as substantially as second order methods per iteration, while maintaining the computational complexity of…

Optimization and Control · Mathematics 2024-05-14 Shida Wang , Jalal Fadili , Peter Ochs

Backpropagation is driving today's artificial neural networks (ANNs). However, despite extensive research, it remains unclear if the brain implements this algorithm. Among neuroscientists, reinforcement learning (RL) algorithms are often…

Neurons and Cognition · Quantitative Biology 2020-04-24 Benjamin James Lansdell , Prashanth Ravi Prakash , Konrad Paul Kording

Thompson sampling (TS) is one of the most popular exploration techniques in reinforcement learning (RL). However, most TS algorithms with theoretical guarantees are difficult to implement and not generalizable to Deep RL. While the emerging…

Machine Learning · Computer Science 2024-06-19 Haque Ishfaq , Yixin Tan , Yu Yang , Qingfeng Lan , Jianfeng Lu , A. Rupam Mahmood , Doina Precup , Pan Xu

The classical theory of reinforcement learning (RL) has focused on tabular and linear representations of value functions. Further progress hinges on combining RL with modern function approximators such as kernel functions and deep neural…

Machine Learning · Computer Science 2021-01-01 Zhuoran Yang , Chi Jin , Zhaoran Wang , Mengdi Wang , Michael I. Jordan

Stochastic gradient descent (SGD) has achieved great success in training deep neural network, where the gradient is computed through back-propagation. However, the back-propagated values of different layers vary dramatically. This…

Machine Learning · Statistics 2018-02-28 Huishuai Zhang , Wei Chen , Tie-Yan Liu

The Robbins-Monro stochastic approximation algorithm is a foundation of many algorithmic frameworks for reinforcement learning (RL), and often an efficient approach to solving (or approximating the solution to) complex optimal control…

Optimization and Control · Mathematics 2019-03-19 Andrey Bernstein , Yue Chen , Marcello Colombino , Emiliano Dall'Anese , Prashant Mehta , Sean Meyn

Accelerating the convergence of second-order optimization, particularly Newton-type methods, remains a pivotal challenge in algorithmic research. In this paper, we extend previous work on the \textbf{Quadratic Gradient (QG)} and rigorously…

Optimization and Control · Mathematics 2026-04-01 John Chiang

Deep Q-learning method is one of the most popularly used deep reinforcement learning algorithms which uses deep neural networks to approximate the estimation of the action-value function. Training of the deep Q-network (DQN) is usually…

Machine Learning · Computer Science 2020-10-20 S. Indrapriyadarsini , Shahrzad Mahboubi , Hiroshi Ninomiya , Takeshi Kamio , Hideki Asai