Tootfinder

Graph-based Gossiping for Communication Efficiency in Decentralized Federated Learning
Huong Nguyen, Hong-Tri Nguyen, Praveen Kumar Donta, Susanna Pirttikangas, Lauri Lov\'en
https://arxiv.org/abs/2506.10607

Graph-based Gossiping for Communication Efficiency in Decentralized Federated Learning
Federated learning has emerged as a privacy-preserving technique for collaborative model training across heterogeneously distributed silos. Yet, its reliance on a single central server introduces potential bottlenecks and risks of single-point failure. Decentralizing the server, often referred to as decentralized learning, addresses this problem by distributing the server role across nodes within the network. One drawback regarding this pure decentralization is it introduces communication ineff…

FLoRIST: Singular Value Thresholding for Efficient and Accurate Federated Fine-Tuning of Large Language Models
Hariharan Ramesh, Jyotikrishna Dass
https://arxiv.org/abs/2506.09199

FLoRIST: Singular Value Thresholding for Efficient and Accurate Federated Fine-Tuning of Large Language Models
Integrating Low-Rank Adaptation (LoRA) into federated learning offers a promising solution for parameter-efficient fine-tuning of Large Language Models (LLMs) without sharing local data. However, several methods designed for federated LoRA present significant challenges in balancing communication efficiency, model accuracy, and computational cost, particularly among heterogeneous clients. These methods either rely on simplistic averaging of local adapters, which introduces aggregation noise, re…

Physical Layer-Based Device Fingerprinting for Wireless Security: From Theory to Practice
Junqing Zhang, Francesco Ardizzon, Mattia Piana, Guanxiong Shen, Stefano Tomasin
https://arxiv.org/abs/2506.09807

Physical Layer-Based Device Fingerprinting for Wireless Security: From Theory to Practice
The identification of the devices from which a message is received is part of security mechanisms to ensure authentication in wireless communications. Conventional authentication approaches are cryptography-based, which, however, are usually computationally expensive and not adequate in the Internet of Things (IoT), where devices tend to be low-cost and with limited resources. This paper provides a comprehensive survey of physical layer-based device fingerprinting, which is an emerging device a…

This https://arxiv.org/abs/2505.16457 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

Maximum Separation of Quantum Communication Complexity With and Without Shared Entanglement
We present relation problems whose input size is $n$ such that they can be solved with no communication for entanglement-assisted quantum communication models, but require $Ω(n)$ qubit communication for $2$-way quantum communication models without prior shared entanglement. This is the maximum separation of quantum communication complexity with and without shared entanglement. To our knowledge, our result even shows the first lower bound on quantum communication complexity without shared entan…

Gradient flow in the kernel learning problem
Yang Li, Feng Ruan
https://arxiv.org/abs/2506.08550 https://arxiv.org/pdf/2506.08550

Gradient flow in the kernel learning problem
This is a sequel to our paper `On the kernel learning problem'. We identify a canonical choice of Riemannian gradient flow, to find the stationary points in the kernel learning problem. In the presence of Gaussian noise variables, this flow enjoys the remarkable property of having a continuous family of Lyapunov functionals, and the interpretation is the automatic reduction of noise. PS. We include an extensive discussion in the postcript explaining the comparison with the 2-layer neural netw…

An Effective Equivalence Model of Analyzing PLS of Multiple Eavesdroppers Facing Low-altitude Communication Systems
Yujia Zhao, Zhiyong Feng, Kan Yu, Qixun Zhang, Dong Li
https://arxiv.org/abs/2507.05878

An Effective Equivalence Model of Analyzing PLS of Multiple Eavesdroppers Facing Low-altitude Communication Systems
In low-altitude wireless communications, the increased complexity of wireless channels and the uncertainty of eavesdroppers (Eves)--caused by diverse altitudes, speeds, and obstacles--pose significant challenges to physical layer security (PLS) technologies based on fixed-position antennas (FPAs), particularly in terms of beamforming capabilities and spatial efficiency. In contrast, movable antennas (MAs) offer a flexible solution by enabling channel reconstruction through antenna movement, eff…

Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs
Ziyue Li, Yang Li, Tianyi Zhou
https://arxiv.org/abs/2507.07996 https://arxiv.org/pdf/2507.07996 https://arxiv.org/html/2507.07996
arXiv:2507.07996v1 Announce Type: new
Abstract: Can a pretrained neural network adapt its architecture to different inputs without any finetuning? Do we need all layers for simple tasks, and are they adequate for challenging tasks? We found that the layers of a pretrained large language model (LLM) can be manipulated as separate modules to build a better and even shallower model customized for each test sample. In particular, each layer from the pretrained model can be skipped/pruned or repeated multiple times as recurrent neural networks (RNN), and stacked with others in arbitrary orders, yielding a chain-of-layers (CoLa) per sample. This compositional space greatly expands the scope of existing works on looped/recurrent pretrained modules, layer pruning, or early-exit networks. We develop a Monte Carlo Tree Search (MCTS) protocol to explore and identify the optimal CoLa for each sample from math and commonsense reasoning benchmarks. Compared to a static model of a fixed depth, CoLa allows shortcut paths (fast thinking), recurrence of the same layer(s) (slow thinking), and combining both, offering more flexible, dynamic architectures for different inputs. We conduct an extensive analysis of the MCTS-optimized CoLa, which leads to two key findings: (1) For >75% of samples with correct predictions by the original LLM, we can find shorter CoLa, suggesting a large space for improving inference efficiency; (2) For >60% of samples with originally incorrect predictions, we can identify CoLa achieving correct predictions, suggesting a large space of performance enhancement. Our results highlight the shortcomings of using a fixed architecture of pre-trained LLMs for inference on different samples and pave the way to unlock the generalization power of test-time depth adaptation.
toXiv_bot_toot

A Survey on Artificial Noise for Physical Layer Security: Opportunities, Technologies, Guidelines, Advances, and Trends
Hong Niu, Yue Xiao, Xia Lei, Jiangong Chen, Zhihan Xiao, Mao Li, Chau Yuen
https://arxiv.org/abs/2507.06500

A Survey on Artificial Noise for Physical Layer Security: Opportunities, Technologies, Guidelines, Advances, and Trends
Due to the broadcast nature of wireless communications, physical-layer security has attracted increasing concerns from both academia and industry. Artificial noise (AN), as one of the promising physical-layer security techniques, is capable of utilizing the spatial degree-of-freedom of channels to effectively enhance the security of wireless communications. In contrast to other physicallayer security techniques, the key distinguishing feature of AN is to generate specific interfering signals ac…

Does Movable Antenna Present A Dual-edged Nature? From the Perspective of Physical Layer Security: A Joint Design of Fixed-position Antenna and Movable Antenna
Kan Yu, Wenxu Wang, Xiaowu Liu, Yujia Zhao, Qixun Zhang, Zhiyong Feng, Dong Li
https://arxiv.org/abs/2507.05784

Does Movable Antenna Present A Dual-edged Nature? From the Perspective of Physical Layer Security: A Joint Design of Fixed-position Antenna and Movable Antenna
In conventional artificial noise (AN)-aided physical-layer security systems, fixed-position antenna (FPA) arrays exhibit inherent vulnerability to coverage gaps due to their static spatial configuration. Adversarial eavesdroppers can strategically exploit their mobility to infiltrate these spatial nulls of AN radiation patterns, thereby evading interference suppression and successfully intercepting the confidential communication. To overcome this limitation, in this paper, we investigate a hybr…

Demystifying NCCL: An In-depth Analysis of GPU Communication Protocols and Algorithms
Zhiyi Hu, Siyuan Shen, Tommaso Bonato, Sylvain Jeaugey, Cedell Alexander, Eric Spada, Jeff Hammond, Torsten Hoefler
https://arxiv.org/abs/2507.04786

Demystifying NCCL: An In-depth Analysis of GPU Communication Protocols and Algorithms
The NVIDIA Collective Communication Library (NCCL) is a critical software layer enabling high-performance collectives on large-scale GPU clusters. Despite being open source with a documented API, its internal design remains largely opaque. The orchestration of communication channels, selection of protocols, and handling of memory movement across devices and nodes are not well understood, making it difficult to analyze performance or identify bottlenecks. This paper presents a comprehensive anal…