English
Related papers

Related papers: Leaderless State-Machine Replication: Specificatio…

200 papers

The Continual Learning (CL) problem involves performing well on a sequence of tasks under limited compute. Current algorithms in the domain are either slow, offline or sensitive to hyper-parameters. La-MAML, an optimization-based…

Machine Learning · Computer Science 2021-05-21 Joel Joseph , Alex Gu

Supporting ultra-reliable low-latency communications (URLLC) is a major challenge of 5G wireless networks. Stringent delay and reliability requirements need to be satisfied for both scheduled and non-scheduled URLLC traffic to enable a…

Networking and Internet Architecture · Computer Science 2019-01-15 Amin Azari , Mustafa Ozger , Cicek Cavdar

While reinforcement learning has been increasingly applied to stochastic control, few studies have systematically examined policy-based methods in queuing environments modeled as a semi-Markov decision process (SMDP). To address this gap,…

Optimization and Control · Mathematics 2026-04-28 Joseph Walton , Gabriel Nicolosi

Decentralized machine learning (DML) supports collaborative training in large-scale networks with no central server. It is sensitive to the quality and reliability of inter-device communications that result in time-varying and stochastic…

Signal Processing · Electrical Eng. & Systems 2025-11-06 Zhiyuan Zhai , Shuyan Hu , Wei Ni , Xiaojun Yuan , Xin Wang

Multi-Objective Reinforcement Learning (MORL) is a generalization of traditional Reinforcement Learning (RL) that aims to optimize multiple, often conflicting objectives simultaneously rather than focusing on a single reward. This approach…

Machine Learning · Computer Science 2025-08-15 Davide Guidobene , Lorenzo Benedetti , Diego Arapovic

This paper proposes a new approach to analyze and design distributed robust consensus control protocols for general linear leaderless multi-agent systems (MASs) in presence of relative-state constraints or uncertainties. First, we show that…

Optimization and Control · Mathematics 2016-05-13 Dinh Hoa Nguyen , Tatsuo Narikiyo , Michihiro Kawanishi

The goal of this work is to propose an extension of the popular leader-follower framework for multi-agent collective tracking and formation maintenance in presence of a time- varying leader. In particular, the leader is persistently…

Systems and Control · Computer Science 2017-12-20 Antonio Franchi , Paolo Robuffo Giordano

Large Language Models (LLMs) increasingly rely on reinforcement learning with verifiable rewards (RLVR) to elicit reliable chain-of-thought reasoning. However, the training process remains bottlenecked by the computationally expensive…

Machine Learning · Computer Science 2026-01-13 Bingshuai Liu , Ante Wang , Zijun Min , Liang Yao , Haibo Zhang , Yang Liu , Xu Han , Peng Li , Anxiang Zeng , Jinsong Su

We propose a new meta learning based framework for low resource speech recognition that improves the previous model agnostic meta learning (MAML) approach. The MAML is a simple yet powerful meta learning approach. However, the MAML presents…

Computation and Language · Computer Science 2022-05-13 Satwinder Singh , Ruili Wang , Feng Hou

We present the notion of stateful priorities for imposing precise restrictions on system actions, in order to meet safety constraints. By using stateful priorities we are able to exclusively restrict erroneous system behavior as specified…

Logic in Computer Science · Computer Science 2020-02-21 Christian Herrera

Collaborative working is increasingly popular, but it presents challenges due to the need for high responsiveness and disconnected work support. To address these challenges the data is optimistically replicated at the edges of the network,…

Databases · Computer Science 2012-12-12 Stéphane Martin , Mehdi Ahmed-Nacer , Pascal Urso

Model-based reinforcement learning promises to learn an optimal policy from fewer interactions with the environment compared to model-free reinforcement learning by learning an intermediate model of the environment in order to predict…

Machine Learning · Computer Science 2022-06-08 Abhinav Bhatia , Philip S. Thomas , Shlomo Zilberstein

In this paper, we propose a fast reinforcement learning (RL) control algorithm that enables online control of large-scale networked dynamic systems. RL is an effective way of designing model-free linear quadratic regulator (LQR) controllers…

Systems and Control · Electrical Eng. & Systems 2020-09-16 Tomonori Sadamoto , Aranya Chakrabortty , Jun-ichi Imura

The application of machine learning (ML) in computer systems introduces not only many benefits but also risks to society. In this paper, we develop the concept of ML governance to balance such benefits and risks, with the aim of achieving…

Cryptography and Security · Computer Science 2021-09-23 Varun Chandrasekaran , Hengrui Jia , Anvith Thudi , Adelin Travers , Mohammad Yaghini , Nicolas Papernot

Machine learning (ML) training algorithms often possess an inherent self-correcting behavior due to their iterative-convergent nature. Recent systems exploit this property to achieve adaptability and efficiency in unreliable computing…

Machine Learning · Computer Science 2018-10-18 Aurick Qiao , Bryon Aragam , Bingjing Zhang , Eric P. Xing

Building consensus sequences based on distributed, fault-tolerant consensus, as used for replicated state machines, typically requires a separate distributed state for every new consensus instance. Allocating and maintaining this state…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-04-02 Jan Skrzypczak , Florian Schintke , Thorsten Schütt

We present a set of model-free, reduced-dimensional reinforcement learning (RL) based optimal control designs for linear time-invariant singularly perturbed (SP) systems. We first present a state-feedback and output-feedback based RL…

Systems and Control · Electrical Eng. & Systems 2021-02-08 Sayak Mukherjee , He Bai , Aranya Chakrabortty

Deploying massive large language models (LLMs) as continuous cognitive engines for robotics is bottlenecked by the time-to-first-token (TTFT) latency required to process extensive state histories. Existing solutions like RAG or sliding…

Robotics · Computer Science 2026-05-11 Robin Karlsson , Go Suzui

Deep reinforcement learning (DRL) frameworks are increasingly used to solve high-dimensional continuous control tasks in robotics. However, due to the lack of sample efficiency, applying DRL for online learning is still practically…

Robotics · Computer Science 2024-04-30 Yu Tang Liu , Aamir Ahmad

Latency and efficiency issues are often overlooked when evaluating IR models based on Pretrained Language Models (PLMs) in reason of multiple hardware and software testing scenarios. Nevertheless, efficiency is an important part of such…

Information Retrieval · Computer Science 2022-07-11 Carlos Lassance , Stéphane Clinchant