Mansard Roofline Model: Reinforcing the Accuracy of the Roofs

Continuous enhancements and diversity in modern multi-core hardware, such as wider and deeper core pipelines and memory subsystems, bring to practice a set of hard-to-solve challenges when modeling their upper-bound capabilities and identifying the main application bottlenecks. Insightful roofline models are widely used for this purpose, but the existing approaches overly abstract the micro-architecture complexity, thus providing unrealistic performance bounds that lead to a misleading characterization of real-world applications. To address this problem, the Mansard Roofline Model (MaRM), proposed in this work, uncovers a minimum set of architectural features that must be considered to provide insightful, but yet accurate and realistic, modeling of performance upper bounds for modern processors. By encapsulating the retirement constraints due to the amount of retirement slots, Reorder-Buffer and Physical Register File sizes, the proposed model accurately models the capabilities of a real platform (average rRMSE of 5.4%) and characterizes 12 application kernels from standard benchmark suites. By following a herein proposed MaRM interpretation methodology and guidelines, speed-ups of up to 5× are obtained when optimizing real-world bioinformatic application, as well as a super-linear speedup of 18.5× when parallelized.

Download Full-text

Sliding-Window Thompson Sampling for Non-Stationary Settings

Journal of Artificial Intelligence Research ◽

10.1613/jair.1.11407 ◽

2020 ◽

Vol 68 ◽

pp. 311-364

Author(s):

Francesco Trovo ◽

Stefano Paladino ◽

Marcello Restelli ◽

Nicola Gatti

Keyword(s):

Real World ◽

State Of The Art ◽

Sliding Window ◽

Upper Bounds ◽

Decision Problems ◽

Sequential Decision ◽

Thompson Sampling ◽

The Past ◽

Real World Applications ◽

Window Approach

Multi-Armed Bandit (MAB) techniques have been successfully applied to many classes of sequential decision problems in the past decades. However, non-stationary settings -- very common in real-world applications -- received little attention so far, and theoretical guarantees on the regret are known only for some frequentist algorithms. In this paper, we propose an algorithm, namely Sliding-Window Thompson Sampling (SW-TS), for nonstationary stochastic MAB settings. Our algorithm is based on Thompson Sampling and exploits a sliding-window approach to tackle, in a unified fashion, two different forms of non-stationarity studied separately so far: abruptly changing and smoothly changing. In the former, the reward distributions are constant during sequences of rounds, and their change may be arbitrary and happen at unknown rounds, while, in the latter, the reward distributions smoothly evolve over rounds according to unknown dynamics. Under mild assumptions, we provide regret upper bounds on the dynamic pseudo-regret of SW-TS for the abruptly changing environment, for the smoothly changing one, and for the setting in which both the non-stationarity forms are present. Furthermore, we empirically show that SW-TS dramatically outperforms state-of-the-art algorithms even when the forms of non-stationarity are taken separately, as previously studied in the literature.

Download Full-text

Fair Pairwise Exchange among Groups

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2021/59 ◽

2021 ◽

Author(s):

Zhaohong Sun ◽

Taiki Todo ◽

Toby Walsh

Keyword(s):

Polynomial Time ◽

Real World ◽

Research Question ◽

Polynomial Time Algorithm ◽

Time Algorithm ◽

Upper Bounds ◽

Individual Rationality ◽

Running Time ◽

Graph Structures ◽

Real World Applications

We study the pairwise organ exchange problem among groups motivated by real-world applications and consider two types of group formulations. Each group represents either a certain type of patient-donor pairs who are compatible with the same set of organs, or a set of patient-donor pairs who reside in the same region. We address a natural research question, which asks how to match a maximum number of pairwise compatible patient-donor pairs in a fair and individually rational way. We first propose a natural fairness concept that is applicable to both types of group formulations and design a polynomial-time algorithm that checks whether a matching exists that satisfies optimality, individual rationality, and fairness. We also present several running time upper bounds for computing such matchings for different graph structures.

Download Full-text

ANALYSIS OF THE 2-SUM PROBLEM AND THE SPECTRAL ALGORITHM

International Journal of Computing ◽

10.47839/ijc.8.2.676 ◽

2014 ◽

pp. 139-148

Author(s):

Alexander Kolomiychuk

Keyword(s):

Real World ◽

Assignment Problem ◽

Quadratic Assignment Problem ◽

Sparse Matrices ◽

Approximate Solutions ◽

Upper Bounds ◽

Quadratic Assignment ◽

Euclidian Space ◽

Real World Applications ◽

Spectral Algorithm

This paper presents the analysis of the 2-sum problem and the spectral algorithm. The spectral algorithm was proposed by Barnard, Pothen and Simon in [1]; its heuristic properties have been advocated by George and Pothen in [4] by formulation of the 2-sum problem as a Quadratic Assignment Problem. In contrast to that analysis another approach is proposed: permutations are considered as vectors of Euclidian space. This approach enables one to prove the bound results originally obtained in [4] in an easier way. The geometry of permutations is considered in order to explain what are ‘good’ and ‘pathological’ situations for the spectral algorithm. Upper bounds for approximate solutions generated by the spectral algorithm are proved. The results of numerical computations on (graphs of) large sparse matrices from real-world applications are presented to support the obtained results and illustrate considerations related to the ‘pathological’ cases.

Download Full-text

Entropy-based Variational Learning of Finite Inverted Beta-Liouville Mixture Model

The International FLAIRS Conference Proceedings ◽

10.32473/flairs.v34i1.128379 ◽

2021 ◽

Vol 34 (1) ◽

Author(s):

Narges Manouchehri ◽

Mohammad Sadegh Ahmadzadeh ◽

Hafsa Ennajari ◽

Nizar Bouguila ◽

Manar Amayri ◽

...

Keyword(s):

Mixture Models ◽

Mixture Model ◽

Activity Recognition ◽

Real World ◽

Variational Inference ◽

Inference Algorithm ◽

Image Categorization ◽

Proposed Model ◽

Learning Technique ◽

Real World Applications

Mixture models are a common unsupervised learning technique that have been widely used to statistically approximate and analyse heterogenous data. In this paper, an effective mixture model-based approach for positive vectors clustering and modeling is proposed. Our mixture model is based on the inverted Beta-Liouville (IBL) distribution. To deploy the proposed model, we introduce an entropy-based variational inference algorithm. The performance of the proposed model is evaluated on two real-world applications, namely, human activity recognition and image categorization.

Download Full-text