中文
相关论文

相关论文: QUIVER: A Formal Framework for Quantifying Perturb…

200 篇论文

Systems for serving inference requests on graph neural networks (GNN) must combine low latency with high throughout, but they face irregular computation due to skew in the number of sampled graph nodes and aggregated GNN features. This…

分布式、并行与集群计算 · 计算机科学 2023-05-19 Zeyuan Tan , Xiulong Yuan , Congjie He , Man-Kit Sit , Guo Li , Xiaoze Liu , Baole Ai , Kai Zeng , Peter Pietzuch , Luo Mai

We introduce a novel mathematical framework for analyzing neural networks using tools from quiver representation theory. This framework enables us to quantify the similarity between a new data sample and the training data, as perceived by…

机器学习 · 计算机科学 2024-09-23 Samuel Leblanc , Aiky Rasolomanana , Marco Armenta

In this paper we state the basics for a signal processing framework on quiver representations. A quiver is a directed graph and a quiver representation is an assignment of vector spaces to the nodes of the graph and of linear maps between…

信号处理 · 电气工程与系统科学 2020-10-24 Alejandro Parada-Mayorga , Hans Riess , Alejandro Ribeiro , Robert Ghrist

A fundamental challenge in multiparameter persistent homology is the absence of a complete and discrete invariant. To address this issue, we propose an enhanced framework that realizes a holistic understanding of a fully commutative…

代数拓扑 · 数学 2023-11-14 Yasuaki Hiraoka , Ken Nakashima , Ippei Obayashi , Chenguang Xu

Understanding how LLMs reason is hindered by a practical asymmetry: while their generated outputs are observable, the underlying reasoning patterns remain opaque. Relying on single probes, such as Mutual Information Peak (MIP) or…

计算与语言 · 计算机科学 2026-05-28 Leonardo Matthew Yauw , Wei-Bin Kou , Yujiu Yang

We introduce a framework for linear precoder design over a massive multiple-input multiple-output downlink system in the presence of nonlinear power amplifiers (PAs). By studying the spatial characteristics of the distortion, we demonstrate…

This work presents novel extensions for combining two frameworks for quantifying both aleatoric (i.e., irreducible) and epistemic (i.e., reducible) sources of uncertainties in the modeling of engineered systems. The data-consistent (DC)…

机器学习 · 统计学 2024-03-07 Taylor Roper , Harri Hakula , Troy Butler

The growth of large-scale AI systems is increasingly constrained by infrastructure limits: power availability, thermal and water constraints, interconnect scaling, memory pressure, data-pipeline throughput, and rapidly escalating lifecycle…

综合经济学 · 经济学 2026-01-21 Qi He

Integrating quantum circuits into deep learning pipelines remains challenging due to heuristic design limitations. We propose Q-DIVER, a hybrid framework combining a large-scale pretrained EEG encoder (DIVER-1) with a differentiable quantum…

量子物理 · 物理学 2026-03-31 Junghoon Justin Park , Yeonghyeon Park , Jiook Cha

Just as humans can become disoriented in featureless deserts or thick fogs, not all environments are conducive to the Localization Accuracy and Stability (LAS) of autonomous robots. This paper introduces an efficient framework designed to…

机器人学 · 计算机科学 2024-08-06 Kaixin Chai , Long Xu , Qianhao Wang , Chao Xu , Peng Yin , Fei Gao

Time series generation is critical for a wide range of applications, which greatly supports downstream analytical and decision-making tasks. However, the inherent temporal heterogeneous induced by localized perturbations present significant…

机器学习 · 计算机科学 2025-11-19 Jintao Zhang , Mingyue Cheng , Zirui Liu , Xianquan Wang , Yitong Zhou , Qi Liu

The adoption of high-performance multi-core platforms in avionics and automotive systems introduces significant challenges in ensuring predictable execution, primarily due to shared resource interferences. Many existing approaches study…

Recent literature has shown how linear time-invariant (LTI) systems can be represented by trajectories features, that is relying on a single input-output (IO) data dictionary to span all possible system trajectories, as long as the input is…

系统与控制 · 电气工程与系统科学 2023-09-18 Marcelo Menezes Morato , Julio Elias Normey-Rico , Olivier Sename

The increasing complexity of AI workloads, especially distributed Large Language Model (LLM) training, places significant strain on the networking infrastructure of parallel data centers and supercomputing systems. While Equal-Cost Multi-…

网络与互联网体系结构 · 计算机科学 2024-10-25 Hasibul Jamil , Abdul Alim , Laurent Schares , Pavlos Maniotis , Liran Schour , Ali Sydney , Abdullah Kayi , Tevfik Kosar , Bengi Karacali

Computer architecture design space is vast and complex. Tools are needed to explore new ideas and gain insights quickly, with low efforts and at a desired accuracy. We propose Calipers, a criticality-based framework to model key…

性能 · 计算机科学 2022-01-19 Hossein Golestani , Rathijit Sen , Vinson Young , Gagan Gupta

Fidelity estimation is a critical yet resource-intensive step in testing quantum programs on noisy intermediate-scale quantum (NISQ) devices, where the required number of measurements is difficult to predefine due to hardware noise, device…

量子物理 · 物理学 2026-01-22 Tingting Li , Ziming Zhao , Jianwei Yin

The deployment of large language models (LLMs) in production environments has created an urgent need for observability systems that span the full stack -- from model internals to GPU kernels. Yet existing monitoring approaches address…

软件工程 · 计算机科学 2026-04-30 Twinkll Sisodia

Running a quantum circuit on current hardware involves a sequence of engineering decisions, each with tunable parameters and distinct error characteristics. Existing tools optimize each decision in isolation, leaving practitioners unable to…

量子物理 · 物理学 2026-05-13 Kisho Sotokawa , Hideaki Kawaguchi , Shin Nishio , Takahiko Satoh

Early detection and resolution of duplicate and conflicting requirements can significantly enhance project efficiency and overall software quality. Researchers have developed various computational predictors by leveraging Artificial…

软件工程 · 计算机科学 2024-12-03 Summra Saleem , Muhammad Nabeel Asim , Andreas Dengel

Mechanistic interpretability aims to reverse-engineer the internal computations of Large Language Models (LLMs), yet separating sparse semantic signals from high-dimensional polysemantic noise remains a significant challenge. This paper…

量子物理 · 物理学 2026-02-09 Jonathan Pan
‹ 上一页 1 2 3 10 下一页 ›