English
Related papers

Related papers: Outer-Momentum Restarting in High-Dimensional Two-…

200 papers

A common optimization tool used in deep reinforcement learning is momentum, which consists in accumulating and discounting past gradients, reapplying them at each iteration. We argue that, unlike in supervised learning, momentum in Temporal…

Machine Learning · Computer Science 2021-06-09 Emmanuel Bengio , Joelle Pineau , Doina Precup

As we scale to more massive machine learning models, the frequent synchronization demands inherent in data-parallel approaches create significant slowdowns, posing a critical challenge to further scaling. Recent work develops an approach…

Machine Learning · Computer Science 2025-03-14 Zachary Charles , Gabriel Teston , Lucio Dery , Keith Rush , Nova Fallen , Zachary Garrett , Arthur Szlam , Arthur Douillard

This paper considers a class of convex optimization problems where both, the objective function and the constraints, have a continuously varying dependence on time. Our goal is to develop an algorithm to track the optimal solution as it…

Optimization and Control · Mathematics 2015-10-07 Mahyar Fazlyab , Santiago Paternain , Victor M. Preciado , Alejandro Ribeiro

Momentum SGD (MSGD) serves as a foundational optimizer in training deep models due to momentum's key role in accelerating convergence and enhancing generalization. Meanwhile, asynchronous distributed learning is crucial for training…

Machine Learning · Computer Science 2026-01-21 Chang-Wei Shi , Shi-Shang Wang , Wu-Jun Li

This paper presents a distributed continuous-time optimization framework aimed at overcoming the challenges posed by time-varying cost functions and constraints in multi-agent systems, particularly those subject to disturbances. By…

Systems and Control · Electrical Eng. & Systems 2024-09-10 Zeinab Ebrahimi , Mohammad Deghat

Recent work in continual learning has highlighted the stability gap -- a temporary performance drop on previously learned tasks when new ones are introduced. This phenomenon reflects a mismatch between rapid adaptation and strong retention…

Machine Learning · Computer Science 2026-01-28 Alejandro Rodriguez-Garcia , Anindya Ghosh , Srikanth Ramaswamy

The application of distributed model predictive controllers (DMPC) for multi-agent systems (MASs) necessitates communication between agents, yet the consequence of communication data rates is typically overlooked. This work focuses on…

Systems and Control · Electrical Eng. & Systems 2023-08-08 Yujia Yang , Ye Wang , Chris Manzie , Ye Pu

Proximal policy optimization (PPO) is a widely-used algorithm for on-policy reinforcement learning. This work offers an alternative perspective of PPO, in which it is decomposed into the inner-loop estimation of update vectors, and the…

Machine Learning · Computer Science 2024-11-04 Charlie B. Tan , Edan Toledo , Benjamin Ellis , Jakob N. Foerster , Ferenc Huszár

Continual learning algorithms strive to acquire new knowledge while preserving prior information. Often, these algorithms emphasise stability and restrict network updates upon learning new tasks. In many cases, such restrictions come at a…

Machine Learning · Computer Science 2024-06-21 Daniel Anthes , Sushrut Thorat , Peter König , Tim C. Kietzmann

In this overview article we will consider the deliberate restarting of algorithms, a meta technique, in order to improve the algorithm's performance, e.g., convergence rates or approximation guarantees. One of the major advantages is that…

Optimization and Control · Mathematics 2020-06-29 Sebastian Pokutta

This paper discusses an outer-approximation guided optimization method for constrained neural network inverse problems with rectified linear units. The constrained neural network inverse problems refer to an optimization problem to find the…

Optimization and Control · Mathematics 2020-02-25 Myun-Seok Cheon

Time distributed optimization is an implementation strategy that can significantly reduce the computational burden of model predictive control by exploiting its robustness to incomplete optimization. When using this strategy, optimization…

Optimization and Control · Mathematics 2020-04-14 Dominic Liao-McPherson , Marco Nicotra , Ilya Kolmanovsky

Edge robotics involves frequent exchanges of large-volume multi-modal data. Existing methods ignore the interdependency between robotic functionalities and communication conditions, leading to excessive communication overhead. This paper…

Robotics · Computer Science 2025-10-21 Dan Guo , Xibin Jin , Shuai Wang , Zhigang Wen , Miaowen Wen , Chengzhong Xu

Learning to Optimize (L2O) enhances optimization efficiency with integrated neural networks. L2O paradigms achieve great outcomes, e.g., refitting optimizer, generating unseen solutions iteratively or directly. However, conventional L2O…

Machine Learning · Computer Science 2025-03-17 Mingjia Shi , Ruihan Lin , Xuxi Chen , Yuhao Zhou , Zezhen Ding , Pingzhi Li , Tong Wang , Kai Wang , Zhangyang Wang , Jiheng Zhang , Tianlong Chen

This paper considers a nested stochastic distributed optimization problem. In it, approximate solutions to realizations of the inner-problem are leveraged to obtain a Distributed Stochastic Cubic Regularized Newton (DiSCRN) update to the…

Optimization and Control · Mathematics 2021-08-06 Tor Anderson , Sonia Martinez

In this paper we consider a network of processors aiming at cooperatively solving linear programming problems subject to uncertainty. Each node only knows a common cost function and its local uncertain constraint set. We propose a…

Optimization and Control · Mathematics 2019-08-27 Mohammadreza Chamanbaz , Giuseppe Notarstefano , Roland Bouffanais

We propose a generalization of modern representation learning objectives by reframing them as recursive divergence alignment processes over localized conditional distributions While recent frameworks like Information Contrastive Learning…

Machine Learning · Computer Science 2025-05-02 Anthony D Martin

We consider a decentralized learning problem, where a set of computing nodes aim at solving a non-convex optimization problem collaboratively. It is well-known that decentralized optimization schemes face two major system bottlenecks:…

Machine Learning · Computer Science 2019-11-04 Amirhossein Reisizadeh , Hossein Taheri , Aryan Mokhtari , Hamed Hassani , Ramtin Pedarsani

Multidimensional Retiming is one of the most important optimization techniques to improve timing parameters of nested loops. It consists in exploring the iterative and recursive structures of loops to redistribute computation nodes on cycle…

Programming Languages · Computer Science 2012-05-22 Yaroub Elloumi , Mohamed Akil , Mohamed Hedi Bedoui

Distributed optimization requires nodes to coordinate, yet full synchronization scales poorly. When $n$ nodes collaborate through $m$ pairwise regularizers, standard methods demand $\mathcal{O}(m)$ communications per iteration. This paper…

Machine Learning · Computer Science 2025-09-19 Ying Lin , Yao Kuang , Ahmet Alacaoglu , Michael P. Friedlander