2024-04-29 07:10:50
Online Policy Learning and Inference by Matrix Completion
Congyuan Duan, Jingyang Li, Dong Xia
https://arxiv.org/abs/2404.17398 https://
Online Policy Learning and Inference by Matrix Completion
Congyuan Duan, Jingyang Li, Dong Xia
https://arxiv.org/abs/2404.17398 https://
Sound Concurrent Traces for Online Monitoring Technical Report
Chukri Soueidi, Ylies Falcone
https://arxiv.org/abs/2402.18391 https://
This https://arxiv.org/abs/2311.00656 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…
This https://arxiv.org/abs/2005.01867 has been replaced.
link: https://scholar.google.com/scholar?q=a
This https://arxiv.org/abs/2403.07728 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…
This https://arxiv.org/abs/2211.14361 has been replaced.
link: https://scholar.google.com/scholar?q=a
Efficient Online Learning for Networks of Two-Compartment Spiking Neurons
Yujia Yin, Xinyi Chen, Chenxiang Ma, Jibin Wu, Kay Chen Tan
https://arxiv.org/abs/2402.15969 https://arxiv.org/pdf/2402.15969
arXiv:2402.15969v1 Announce Type: new
Abstract: The brain-inspired Spiking Neural Networks (SNNs) have garnered considerable research interest due to their superior performance and energy efficiency in processing temporal signals. Recently, a novel multi-compartment spiking neuron model, namely the Two-Compartment LIF (TC-LIF) model, has been proposed and exhibited a remarkable capacity for sequential modelling. However, training the TC-LIF model presents challenges stemming from the large memory consumption and the issue of gradient vanishing associated with the Backpropagation Through Time (BPTT) algorithm. To address these challenges, online learning methodologies emerge as a promising solution. Yet, to date, the application of online learning methods in SNNs has been predominantly confined to simplified Leaky Integrate-and-Fire (LIF) neuron models. In this paper, we present a novel online learning method specifically tailored for networks of TC-LIF neurons. Additionally, we propose a refined TC-LIF neuron model called Adaptive TC-LIF, which is carefully designed to enhance temporal information integration in online learning scenarios. Extensive experiments, conducted on various sequential benchmarks, demonstrate that our approach successfully preserves the superior sequential modeling capabilities of the TC-LIF neuron while incorporating the training efficiency and hardware friendliness of online learning. As a result, it offers a multitude of opportunities to leverage neuromorphic solutions for processing temporal signals.
> She worries the negative effects will spread as the technology does. "One biased human hiring manager can harm a lot of people in a year, and that's not great," she says. "But an algorithm that is maybe used in all incoming applications at a large company… that could harm hundreds of thousands of applicants."
This https://arxiv.org/abs/2302.01421 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…
Online Submodular Welfare Maximization Meets Post-Allocation Stochasticity and Reusability
Rajan Udwani
https://arxiv.org/abs/2403.18059 https://
This https://arxiv.org/abs/2302.01421 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…
This https://arxiv.org/abs/2304.06565 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDS_…
This https://arxiv.org/abs/2201.10017 has been replaced.
link: https://scholar.google.com/scholar?q=a
Has anybody written about the near-ubiquitous online trend of bowdlerizing text, either to avoid being penalized by the algorithm (real or imagined) or to avoid content being searchable by others? We have people who communicate about "s*x" instead of "sex" and... that's probably a very bad thing.
Subgame Optimal and Prior-Independent Online Algorithms
Jason Hartline, Aleck Johnsen, Anant Shah
https://arxiv.org/abs/2403.10451 https://
This https://arxiv.org/abs/2402.09824 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…
From Batch to Stream: Automatic Generation of Online Algorithms
Ziteng Wang, Shankara Pailoor, Aaryan Prakash, Yuepeng Wang, Isil Dillig
https://arxiv.org/abs/2404.04743
"So, what’s the fun of writing on the internet anymore? Well, if your aim is to be respected as an author, there’s probably not much fun to be had here at all. Don’t write online for fame & glory. Write here because ideas matter, not authorship. Write here because the more robots, pirates…the more we need independent writing in order to think new thoughts in the future—even if your words are getting dished up and plated by an algorithm."
Unraveling Contagion Origins: Optimal Estimation through Maximum-Likelihood and Starlike Tree Approximation in Markovian Spreading Models
Pei-Duo Yu, Chee Wei Tan, Liang Zheng, Chao Zhao
https://arxiv.org/abs/2403.14890
This https://arxiv.org/abs/2402.12734 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDS_…
This https://arxiv.org/abs/2308.08138 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…
This https://arxiv.org/abs/2402.12734 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDS_…
Online Differentially Private Synthetic Data Generation
Yiyun He, Roman Vershynin, Yizhe Zhu
https://arxiv.org/abs/2402.08012 https://
(a) If you think "reply guys" are a problem, count yourself lucky that they can at least read for meaning
(b) Israel-Palestine makes some people completely lose their minds; don't take the crazies seriously
(c) It is not some evil algorithm or the mechanism of quote tweets (alone) that poison online discourse
(d) In my job, we've known for many decades that the letter-writers aren't reflective of the audience. Never mistake them for real life.
Action Model Learning with Guarantees
Diego Aineto, Enrico Scala
https://arxiv.org/abs/2404.09631 https://arxiv.org/pdf/2404.09631
Towards Robotised Palpation for Cancer Detection through Online Tissue Viscoelastic Characterisation with a Collaborative Robotic Arm
Luca Beber, Edoardo Lamon, Giacomo Moretti, Daniele Fontanelli, Matteo Saveriano, Luigi Palopoli
https://arxiv.org/abs/2404.09542
Scene: A Google conference room.
Project manager: OK, we need something new here. What are we thinking?
Developer 1: How about glasses that …
Manager: No.
Developer 2: What if we make phones that drive cars?
Manager: Oh we’re coming back to that, but what can we do right now?
Developer3: (Nervously) You know how we’re the best in the world at searching things?
Manager: Yeah?
Developer3: Let’s ruin it.
Manager: Up top!
Online Policy Optimization in Unknown Nonlinear Systems
Yiheng Lin, James A. Preiss, Fengze Xie, Emile Anand, Soon-Jo Chung, Yisong Yue, Adam Wierman
https://arxiv.org/abs/2404.13009
Online Identification of Stochastic Continuous-Time Wiener Models Using Sampled Data
Mohamed Abdalmoaty, Efe C. Balta, John Lygeros, Roy S. Smith
https://arxiv.org/abs/2403.05899 …
Numerical complexity of helix unraveling algorithm for charged particle tracking
Kacper Topolnicki, Tomasz Bold
https://arxiv.org/abs/2402.07142 https://…
A Novel Approach to Industrial Defect Generation through Blended Latent Diffusion Model with Online Adaptation
Hanxi Li, Zhengxun Zhang, Hao Chen, Lin Wu, Bo Li, Deyin Liu, Mingwen Wang
https://arxiv.org/abs/2402.19330
CAS: A General Algorithm for Online Selective Conformal Prediction with FCR Control
Yajie Bao, Yuyang Huo, Haojie Ren, Changliang Zou
https://arxiv.org/abs/2403.07728
The Competition Complexity of Prophet Inequalities
Johannes Brustle, Jos\'e Correa, Paul D\"utting, Tomer Ezra, Michal Feldman, Victor Verdugo
https://arxiv.org/abs/2402.11084
Stop Relying on No-Choice and Do not Repeat the Moves: Optimal, Efficient and Practical Algorithms for Assortment Optimization
Aadirupa Saha, Pierre Gaillard
https://arxiv.org/abs/2402.18917
Error Checking for Sparse Systolic Tensor Arrays
Christodoulos Peltekis, Dionysios Filippas, Giorgos Dimitrakopoulos
https://arxiv.org/abs/2402.10850 https…
This https://arxiv.org/abs/2310.02195 has been replaced.
link: https://scholar.google.com/scholar?q=a
This https://arxiv.org/abs/2404.06834 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…
Forward Direct Feedback Alignment for Online Gradient Estimates of Spiking Neural Networks
Florian Bacho, Dminique Chu
https://arxiv.org/abs/2403.08804 htt…
Cost-Driven Data Replication with Predictions
Tianyu Zuo, Xueyan Tang, Bu Sung Lee
https://arxiv.org/abs/2404.16489 https://arxiv.org…
Dynamic Q-planning for Online UAV Path Planning in Unknown and Complex Environments
Lidia Gianne Souza da Rocha, Kenny Anderson Queiroz Caldas, Marco Henrique Terra, Fabio Ramos, Kelen Cristiane Teixeira Vivaldini
https://arxiv.org/abs/2402.06297
This https://arxiv.org/abs/2312.01996 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…
Cost-Driven Data Replication with Predictions
Tianyu Zuo, Xueyan Tang, Bu Sung Lee
https://arxiv.org/abs/2404.16489 https://arxiv.org…
Online Flexible Busy Time Scheduling on Heterogeneous Machines
Gruia Calinescu, Sami Davies, Samir Khuller, Shirley Zhang
https://arxiv.org/abs/2402.11109 …
This https://arxiv.org/abs/2309.15498 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…
This https://arxiv.org/abs/2402.09495 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qfi…
Numerical complexity of helix unraveling algorithm for charged particle tracking
Kacper Topolnicki, Tomasz Bold
https://arxiv.org/abs/2402.07142 https://…
Learning from Offline and Online Experiences: A Hybrid Adaptive Operator Selection Framework
Jiyuan Pei, Jialin Liu, Yi Mei
https://arxiv.org/abs/2404.10252
This https://arxiv.org/abs/2304.00707 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…
This https://arxiv.org/abs/2303.00047 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…
Nonlinear identification algorithm for online and offline study of pulmonary mechanical ventilation
Diego A. Riva, Carolina A. Evangelista, Paul F. Puleston, Luis Corsiglia, Nahuel Dargains
https://arxiv.org/abs/2402.18709
This https://arxiv.org/abs/2305.07164 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDS_…
This https://arxiv.org/abs/2309.15498 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…
Population-aware Online Mirror Descent for Mean-Field Games by Deep Reinforcement Learning
Zida Wu, Mathieu Lauriere, Samuel Jia Cong Chua, Matthieu Geist, Olivier Pietquin, Ankur Mehta
https://arxiv.org/abs/2403.03552
This https://arxiv.org/abs/2305.07164 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDS_…
This https://arxiv.org/abs/2303.00047 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…
Time Efficient Implementation for Online $k$-server Problem on Trees
Kamil Khadiev, Maxim Yagafarov
https://arxiv.org/abs/2402.14633 https://
Solving Parametric PDEs with Radial Basis Functions and Deep Neural Networks
Guanhang Lei, Zhen Lei, Lei Shi, Chenyu Zeng
https://arxiv.org/abs/2404.06834 …
Real-Time Adaptive Safety-Critical Control with Gaussian Processes in High-Order Uncertain Models
Yu Zhang, Long Wen, Xiangtong Yao, Zhenshan Bing, Linghuan Kong, Wei He, Alois Knoll
https://arxiv.org/abs/2402.18946
Population-aware Online Mirror Descent for Mean-Field Games by Deep Reinforcement Learning
Zida Wu, Mathieu Lauriere, Samuel Jia Cong Chua, Matthieu Geist, Olivier Pietquin, Ankur Mehta
https://arxiv.org/abs/2403.03552
Tightly-Coupled LiDAR-IMU-Wheel Odometry with Online Calibration of a Kinematic Model for Skid-Steering Robots
Taku Okawara, Kenji Koide, Shuji Oishi, Masashi Yokozuka, Atsuhiko Banno, Kentaro Uno, Kazuya Yoshida
https://arxiv.org/abs/2404.02515
Unweighted Layered Graph Traversal
Xingjian Bai, Christian Coester, Romain Cosson
https://arxiv.org/abs/2404.16176 https://arxiv.org/…
This https://arxiv.org/abs/2210.08886 has been replaced.
link: https://scholar.google.com/scholar?q=a
Unweighted Layered Graph Traversal
Xingjian Bai, Christian Coester, Romain Cosson
https://arxiv.org/abs/2404.16176 https://arxiv.org/…
This https://arxiv.org/abs/2210.08886 has been replaced.
link: https://scholar.google.com/scholar?q=a
This https://arxiv.org/abs/2304.01901 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…
This https://arxiv.org/abs/2305.01420 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDS_…
Body Schema Acquisition through Active Learning
Ruben Martinez-Cantin, Manuel Lopes, Luis Montesano
https://arxiv.org/abs/2402.06067 https://
Random-Order Online Interval Scheduling and Geometric Generalizations
Mohit Garg, Debajyoti Kar, Arindam Khan
https://arxiv.org/abs/2402.14201 https://
An Online Algorithm for Solving Feedback Optimal Control Problems with Partial Observations
Siming Liang, Ruoyu Hu, Feng Bao, Richard Archibald, Guannan Zhang
https://arxiv.org/abs/2404.05734
This https://arxiv.org/abs/2304.01901 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…
This https://arxiv.org/abs/2303.02407 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…
Advanced-Step Real-time Iterations with Four Levels -- New Error Bounds and Fast Implementation in acados
Jonathan Frey, Armin Nurkanovic, Moritz Diehl
https://arxiv.org/abs/2403.07101
This https://arxiv.org/abs/2306.16674 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…
This https://arxiv.org/abs/2208.03367 has been replaced.
link: https://scholar.google.com/scholar?q=a
Advanced-Step Real-time Iterations with Four Levels -- New Error Bounds and Fast Implementation in acados
Jonathan Frey, Armin Nurkanovic, Moritz Diehl
https://arxiv.org/abs/2403.07101
This https://arxiv.org/abs/2208.03367 has been replaced.
link: https://scholar.google.com/scholar?q=a
Learning-augmented Online Algorithm for Two-level Ski-rental Problem
Keyuan Zhang, Zhongdong Liu, Nakjung Choi, Bo Ji
https://arxiv.org/abs/2402.06715 http…
This https://arxiv.org/abs/2309.14737 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…
Learning-augmented Online Algorithm for Two-level Ski-rental Problem
Keyuan Zhang, Zhongdong Liu, Nakjung Choi, Bo Ji
https://arxiv.org/abs/2402.06715 http…
This https://arxiv.org/abs/2205.02160 has been replaced.
link: https://scholar.google.com/scholar?q=a
Safe Returning FaSTrack with Robust Control Lyapunov-Value Functions
Zheng Gong, Boyang Li, Sylvia Herbert
https://arxiv.org/abs/2404.02472 https://…
On Approximate Fully-Dynamic Matching and Online Matrix-Vector Multiplication
Yang P. Liu
https://arxiv.org/abs/2403.02582 https://ar…
Optimizing Inventory Placement for a Downstream Online Matching Problem
Boris EpsteinColumbia University, Will MaColumbia University
https://arxiv.org/abs/2403.04598
This https://arxiv.org/abs/2404.05271 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDS_…
Scheduling Multi-Server Jobs is Not Easy
Rahul Vaze
https://arxiv.org/abs/2404.05271 https://arxiv.org/pdf/2404.05271
Scheduling Multi-Server Jobs is Not Easy
Rahul Vaze
https://arxiv.org/abs/2404.05271 https://arxiv.org/pdf/2404.05271
This https://arxiv.org/abs/2311.09408 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…
This https://arxiv.org/abs/2404.01613 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_mat…
This https://arxiv.org/abs/2305.08353 has been replaced.
link: https://scholar.google.com/scholar?q=a