The growing use of large machine learning models highlights concerns about their increasing computational demands. While the energy consumption of their training phase has received attention, fewer works have considered the inference phase. For ML inference, the binding of ML models to the ML system for user access, known as ML serving, is a critical yet understudied step for achieving efficiency in ML applications. We examine the literature in ML architectural design decisions and Green AI, with a special focus on ML serving. The aim is to analyze ML serving architectural design decisions for the purpose of understanding and identifying them with respect to quality characteristics from the point of view of researchers and practitioners in the context of ML serving literature. Our results (i) identify ML serving architectural design decisions along with their corresponding components and associated technological stack, and (ii) provide an overview of the quality characteristics studied in the literature, including energy efficiency. This preliminary study is the first step in our goal to achieve green ML serving. Our analysis may aid ML researchers and practitioners in making green-aware architecture design decisions when serving their models.
相關內容
This paper studies the truncation method from Alquier [1] to derive high-probability PAC-Bayes bounds for unbounded losses with heavy tails. Assuming that the $p$-th moment is bounded, the resulting bounds interpolate between a slow rate $1 / \sqrt{n}$ when $p=2$, and a fast rate $1 / n$ when $p \to \infty$ and the loss is essentially bounded. Moreover, the paper derives a high-probability PAC-Bayes bound for losses with a bounded variance. This bound has an exponentially better dependence on the confidence parameter and the dependency measure than previous bounds in the literature. Finally, the paper extends all results to guarantees in expectation and single-draw PAC-Bayes. In order to so, it obtains analogues of the PAC-Bayes fast rate bound for bounded losses from [2] in these settings.
We introduce Multi-view Ancestral Sampling (MAS), a method for 3D motion generation, using 2D diffusion models that were trained on motions obtained from in-the-wild videos. As such, MAS opens opportunities to exciting and diverse fields of motion previously under-explored as 3D data is scarce and hard to collect. MAS works by simultaneously denoising multiple 2D motion sequences representing different views of the same 3D motion. It ensures consistency across all views at each diffusion step by combining the individual generations into a unified 3D sequence, and projecting it back to the original views. We demonstrate MAS on 2D pose data acquired from videos depicting professional basketball maneuvers, rhythmic gymnastic performances featuring a ball apparatus, and horse races. In each of these domains, 3D motion capture is arduous, and yet, MAS generates diverse and realistic 3D sequences. Unlike the Score Distillation approach, which optimizes each sample by repeatedly applying small fixes, our method uses a sampling process that was constructed for the diffusion framework. As we demonstrate, MAS avoids common issues such as out-of-domain sampling and mode-collapse. //guytevet.github.io/mas-page/
HRI research using autonomous robots in real-world settings can produce results with the highest ecological validity of any study modality, but many difficulties limit such studies' feasibility and effectiveness. We propose Vid2Real HRI, a research framework to maximize real-world insights offered by video-based studies. The Vid2Real HRI framework was used to design an online study using first-person videos of robots as real-world encounter surrogates. The online study ($n = 385$) distinguished the within-subjects effects of four robot behavioral conditions on perceived social intelligence and human willingness to help the robot enter an exterior door. A real-world, between-subjects replication ($n = 26$) using two conditions confirmed the validity of the online study's findings and the sufficiency of the participant recruitment target ($22$) based on a power analysis of online study results. The Vid2Real HRI framework offers HRI researchers a principled way to take advantage of the efficiency of video-based study modalities while generating directly transferable knowledge of real-world HRI. Code and data from the study are provided at //vid2real.github.io/vid2realHRI
Placing applications in mobile edge computing servers presents a complex challenge involving many servers, users, and their requests. Existing algorithms take a long time to solve high-dimensional problems with significant uncertainty scenarios. Therefore, an efficient approach is required to maximize the quality of service while considering all technical constraints. One of these approaches is machine learning, which emulates optimal solutions for application placement in edge servers. Machine learning models are expected to learn how to allocate user requests to servers based on the spatial positions of users and servers. In this study, the problem is formulated as a two-stage stochastic programming. A sufficient amount of training records is generated by varying parameters such as user locations, their request rates, and solving the optimization model. Then, based on the distance features of each user from the available servers and their request rates, machine learning models generate decision variables for the first stage of the stochastic optimization model, which is the user-to-server request allocation, and are employed as independent decision agents that reliably mimic the optimization model. Support Vector Machines (SVM) and Multi-layer Perceptron (MLP) are used in this research to achieve practical decisions from the stochastic optimization models. The performance of each model has shown an execution effectiveness of over 80%. This research aims to provide a more efficient approach for tackling high-dimensional problems and scenarios with uncertainties in mobile edge computing by leveraging machine learning models for optimal decision-making in request allocation to edge servers. These results suggest that machine-learning models can significantly improve solution times compared to conventional approaches.
For multivariate data, tandem clustering is a well-known technique aiming to improve cluster identification through initial dimension reduction. Nevertheless, the usual approach using principal component analysis (PCA) has been criticized for focusing solely on inertia so that the first components do not necessarily retain the structure of interest for clustering. To address this limitation, a new tandem clustering approach based on invariant coordinate selection (ICS) is proposed. By jointly diagonalizing two scatter matrices, ICS is designed to find structure in the data while providing affine invariant components. Certain theoretical results have been previously derived and guarantee that under some elliptical mixture models, the group structure can be highlighted on a subset of the first and/or last components. However, ICS has garnered minimal attention within the context of clustering. Two challenges associated with ICS include choosing the pair of scatter matrices and selecting the components to retain. For effective clustering purposes, it is demonstrated that the best scatter pairs consist of one scatter matrix capturing the within-cluster structure and another capturing the global structure. For the former, local shape or pairwise scatters are of great interest, as is the minimum covariance determinant (MCD) estimator based on a carefully chosen subset size that is smaller than usual. The performance of ICS as a dimension reduction method is evaluated in terms of preserving the cluster structure in the data. In an extensive simulation study and empirical applications with benchmark data sets, various combinations of scatter matrices as well as component selection criteria are compared in situations with and without outliers. Overall, the new approach of tandem clustering with ICS shows promising results and clearly outperforms the PCA-based approach.
Text clustering is an important approach for organising the growing amount of digital content, helping to structure and find hidden patterns in uncategorised data. In this research, we investigated how different textual embeddings - particularly those used in large language models (LLMs) - and clustering algorithms affect how text datasets are clustered. A series of experiments were conducted to assess how embeddings influence clustering results, the role played by dimensionality reduction through summarisation, and embedding size adjustment. Results reveal that LLM embeddings excel at capturing the nuances of structured language, while BERT leads the lightweight options in performance. In addition, we find that increasing embedding dimensionality and summarisation techniques do not uniformly improve clustering efficiency, suggesting that these strategies require careful analysis to use in real-life models. These results highlight a complex balance between the need for nuanced text representation and computational feasibility in text clustering applications. This study extends traditional text clustering frameworks by incorporating embeddings from LLMs, thereby paving the way for improved methodologies and opening new avenues for future research in various types of textual analysis.
This paper presents a method for future motion prediction of multi-agent systems by including group formation information and future intent. Formation of groups depends on a physics-based clustering method that follows the agglomerative hierarchical clustering algorithm. We identify clusters that incorporate the minimum cost-to-go function of a relevant optimal control problem as a metric for clustering between the groups among agents, where groups with similar associated costs are assumed to be likely to move together. The cost metric accounts for proximity to other agents as well as the intended goal of each agent. An unscented Kalman filter based approach is used to update the established clusters as well as add new clusters when new information is obtained. Our approach is verified through non-trivial numerical simulations implementing the proposed algorithm on different datasets pertaining to a variety of scenarios and agents.
This paper presents GeoFlood, a new open-source software package for solving shallow water equations (SWE) on a quadtree hierarchy of mapped, logically Cartesian grids managed by the parallel, adaptive library ForestClaw (Calhoun and Burstedde, 2017). The GeoFlood model is validated using standard benchmark tests from Neelz and Pender (2013) and against George (2011) results obtained from the GeoClaw software (Clawpack Development Team, 2020) for the historical Malpasset dam failure problem. The benchmark test results are compared against GeoClaw and software package HEC-RAS (Hydraulic Engineering Center - River Analysis System, Army Corp of Engineers) results (Brunner, 2018). This comparison demonstrates the capability of GeoFlood to accurately and efficiently predict flood wave propagation on complex terrain. The results from comparisons with the Malpasset dam break show good agreement with the GeoClaw results and are consistent with the historical records of the event.
In the past few years, the emergence of pre-training models has brought uni-modal fields such as computer vision (CV) and natural language processing (NLP) to a new era. Substantial works have shown they are beneficial for downstream uni-modal tasks and avoid training a new model from scratch. So can such pre-trained models be applied to multi-modal tasks? Researchers have explored this problem and made significant progress. This paper surveys recent advances and new frontiers in vision-language pre-training (VLP), including image-text and video-text pre-training. To give readers a better overall grasp of VLP, we first review its recent advances from five aspects: feature extraction, model architecture, pre-training objectives, pre-training datasets, and downstream tasks. Then, we summarize the specific VLP models in detail. Finally, we discuss the new frontiers in VLP. To the best of our knowledge, this is the first survey on VLP. We hope that this survey can shed light on future research in the VLP field.
We present ResMLP, an architecture built entirely upon multi-layer perceptrons for image classification. It is a simple residual network that alternates (i) a linear layer in which image patches interact, independently and identically across channels, and (ii) a two-layer feed-forward network in which channels interact independently per patch. When trained with a modern training strategy using heavy data-augmentation and optionally distillation, it attains surprisingly good accuracy/complexity trade-offs on ImageNet. We will share our code based on the Timm library and pre-trained models.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191