arXiv subjects

Mats Brorsson

Publications and source records attributed to Mats Brorsson.

13 recordsLinked to original sources

arXiv2026

Rethinking Scale: Deployment Trade-offs of Small Language Models under Agent Paradigms

Despite the impressive capabilities of large language models, their substantial computational costs, latency, and privacy risks hinder their widespread deployment in real-world applications. Small Language Models (SLMs) with fewer than 10 billion parameters present a promising alternative; however, their inherent limitations in knowledge and reasoning curtail their effectiveness. Existing research primarily focuses on enhancing SLMs through scaling laws or fine-tuning strategies while overlooking the potential of using agent paradigms, such as tool use and multi-agent collaboration, to systematically compensate for the inherent weaknesses of small models. To address this gap, this paper presents the first large-scale, comprehensive study of <10B open-source models under three paradigms: (1) the base model, (2) a single agent equipped with tools, and (3) a multi-agent system with collaborative capabilities. Our results show that single-agent systems achieve the best balance between performance and cost, while multi-agent setups add overhead with limited gains. Our findings highlight the importance of agent-centric design for efficient and trustworthy deployment in resource-constrained settings.

cs.CL↗

arXiv2025

Which Company Adjustment Matter? Insights from Uplift Modeling on Financial Health

Uplift modeling has achieved significant success in various fields, particularly in online marketing. It is a method that primarily utilizes machine learning and deep learning to estimate individual treatment effects. This paper we apply uplift modeling to analyze the effect of company adjustment on their financial status, and we treat these adjustment as treatments or interventions in this study. Although there have been extensive studies and application regarding binary treatments, multiple treatments, and continuous treatments, company adjustment are often more complex than these scenarios, as they constitute a series of multiple time-dependent actions. The effect estimation of company adjustment needs to take into account not only individual treatment traits but also the temporal order of this series of treatments. This study collects a real-world data set about company financial statements and reported behavior in Luxembourg for the experiments. First, we use two meta-learners and three other well-known uplift models to analyze different company adjustment by simplifying the adjustment as binary treatments. Furthermore, we propose a new uplift modeling framework (MTDnet) to address the time-dependent nature of these adjustment, and the experimental result shows the necessity of considering the timing of these adjustment.

cs.CE↗

arXiv2024

Datasets for Advanced Bankruptcy Prediction: A survey and Taxonomy

Bankruptcy prediction is an important research area that heavily relies on data science. It aims to help investors, managers, and regulators better understand the operational status of corporations and predict potential financial risks in advance. To improve prediction, researchers and practitioners have begun to utilize a variety of different types of data, ranging from traditional financial indicators to unstructured data, to aid in the construction and optimization of bankruptcy forecasting models. Over time, not only instrumentalized data improved, but also instrumentalized methodology for data structuring, cleaning, and analysis. With the aid of advanced analytical techniques that deploy machine learning and deep learning algorithms, bankruptcy assessment became more accurate over time. However, due to the sensitivity of financial data, the scarcity of valid public datasets remains a key bottleneck for the rapid modeling and evaluation of machine learning algorithms for targeted tasks. This study therefore introduces a taxonomy of datasets for bankruptcy research, and summarizes their characteristics. This paper also proposes a set of metrics to measure the quality and the informativeness of public datasets The taxonomy, coupled with the informativeness measure, thus aims at providing valuable insights to better assist researchers and practitioners in developing potential applications for various aspects of credit assessment and decision making by pointing at appropriate datasets for their studies.

cs.CE↗

arXiv2024

Augmenting Bankruptcy Prediction using Reported Behavior of Corporate Restructuring

Credit risk assessment of a company is commonly conducted by utilizing financial ratios that are derived from its financial statements. However, this approach may not fully encompass other significant aspects of a company. We propose the utilization of a hybrid dataset that combines financial statements with information about corporate restructuring behavior in order to construct diverse machine learning models to predict bankruptcy. Utilizing a hybrid data set provides a more comprehensive and holistic perspective on a company's financial position and the dynamics of its business operations. The experiments were carried out using publicly available records of all the files submitted by small and medium-sized enterprises to Luxembourg Business Registers. We conduct a comparative analysis of bankruptcy prediction using six machine learning models. Furthermore, we validate the effectiveness of the hybrid dataset. In addition to the conventional testing set, we deliberately chose the timeframe encompassing the years of the Covid-19 pandemic as an additional testing set in order to evaluate the robustness of the models. The experimental results demonstrate that the hybrid data set can improve the performance of the model by 4%-13% compared to a single source data set. We also identify suitable models for predicting bankruptcy.

cs.CE↗

arXiv2023

DIPPM: a Deep Learning Inference Performance Predictive Model using Graph Neural Networks

Deep Learning (DL) has developed to become a corner-stone in many everyday applications that we are now relying on. However, making sure that the DL model uses the underlying hardware efficiently takes a lot of effort. Knowledge about inference characteristics can help to find the right match so that enough resources are given to the model, but not too much. We have developed a DL Inference Performance Predictive Model (DIPPM) that predicts the inference latency, energy, and memory usage of a given input DL model on the NVIDIA A100 GPU. We also devised an algorithm to suggest the appropriate A100 Multi-Instance GPU profile from the output of DIPPM. We developed a methodology to convert DL models expressed in multiple frameworks to a generalized graph structure that is used in DIPPM. It means DIPPM can parse input DL models from various frameworks. Our DIPPM can be used not only helps to find suitable hardware configurations but also helps to perform rapid design-space exploration for the inference performance of a model. We constructed a graph multi-regression dataset consisting of 10,508 different DL models to train and evaluate the performance of DIPPM, and reached a resulting Mean Absolute Percentage Error (MAPE) as low as 1.9%.

cs.PF↗

arXiv2023

A Cloud-Edge Continuum Experimental Methodology Applied to a 5G Core Study

There is an increasing interest in extending traditional cloud-native technologies, such as Kubernetes, outside the data center to build a continuum towards the edge and between. However, traditional resource orchestration algorithms do not work well in this case, and it is also difficult to test applications for a heterogeneous cloud infrastructure without actually building it. To address these challenges, we propose a new methodology to aid in deploying, testing, and analyzing the effects of microservice placement and scheduling in a heterogeneous Cloud environment. With this methodology, we can investigate any combination of deployment scenarios and monitor metrics in accordance with the placement of microservices in the cloud-edge continuum. Edge devices may be simulated, but as we use Kubernetes, any device which can be attached to a Kubernetes cluster could be used. In order to demonstrate our methodology, we have applied it to the problem of network function placement of an open-source 5G core implementation.

cs.DC↗

arXiv2021

At the Edge of a Seamless Cloud Experience

There is a growing need for low latency for many devices and users. The traditional cloud computing paradigm can not meet this requirement, legitimizing the need for a new paradigm. Edge computing proposes to move computing capacities to the edge of the network, closer to where data is produced and consumed. However, edge computing raises new challenges. At the edge, devices are more heterogeneous than in the data centre, where everything is optimized to achieve economies of scale. Edge devices can be mobile, like a car, which complicates architecture with dynamic topologies. IoT devices produce a considerable amount of data that can be processed at the Edge. In this paper, we discuss the main challenges to be met in edge computing and solutions to achieve a seamless cloud experience. We propose to use technologies like containers and WebAssembly to manage applications' execution on heterogeneous devices.

cs.DC↗

arXiv2021

An ASIC Implementation and Evaluation of a Profiled Low-Energy Instruction Set Architecture Extension

This paper presents an extension to an existing instruction set architecture, which gains considerable reduction in power consumption. The reduction in power consumption is achieved through coding of the most commonly executed instructions in a short format done by the compiler based on a profile of previous executions. This leads to fewer accesses to the instruction cache and that more instructions can fit in the cache. As a secondary effect, this turned out to be very beneficial in terms of power. Another major advantage, which is the main concern of this paper is the reduction in the number of instruction fetch cycles which will also contribute significantly towards reduction in power consumption. The work involves implementing the new processor architecture in ASIC and estimation of power-consumption compared to the normal architecture.

cs.AR↗

arXiv2019

Infer Your Enemies and Know Yourself, Learning in Real-Time Bidding with Partially Observable Opponents

Real-time bidding, as one of the most popular mechanisms for selling online ad slots, facilitates advertisers to reach their potential customers. The goal of bidding optimization is to maximize the advertisers' return on investment (ROI) under a certain budget setting. A straightforward solution is to model the bidding function in an explicit form. However, the static functional solutions lack generality in practice and are insensitive to the stochastic behaviour of other bidders in the environment. In this paper, we propose a general multi-agent framework with actor-critic solutions facing against playing imperfect information games. We firstly introduce a novel Deep Attentive Survival Analysis (DASA) model to infer the censored data in the second price auctions which outperforms start-of-the-art survival analysis. Furthermore, our approach introduces the DASA model as the opponent model into the policy learning process for each agent and develop a mean field equilibrium analysis of the second price auctions. The experiments have shown that with the inference of the market, the market converges to the equilibrium much faster while playing against both fixed strategy agents and dynamic learning agents.

cs.GT↗

arXiv2017

Identifying the potential of Near Data Computing for Apache Spark

cs.DC↗

arXiv2016

Architectural Impact on Performance of In-memory Data Analytics: Apache Spark Case Study

While cluster computing frameworks are continuously evolving to provide real-time data analysis capabilities, Apache Spark has managed to be at the forefront of big data analytics for being a unified framework for both, batch and stream data processing. However, recent studies on micro-architectural characterization of in-memory data analytics are limited to only batch processing workloads. We compare micro-architectural performance of batch processing and stream processing workloads in Apache Spark using hardware performance counters on a dual socket server. In our evaluation experiments, we have found that batch processing are stream processing workloads have similar micro-architectural characteristics and are bounded by the latency of frequent data access to DRAM. For data accesses we have found that simultaneous multi-threading is effective in hiding the data latencies. We have also observed that (i) data locality on NUMA nodes can improve the performance by 10% on average and(ii) disabling next-line L1-D prefetchers can reduce the execution time by up-to 14\% and (iii) multiple small executors can provide up-to 36\% speedup over single large executor.

cs.DC↗

arXiv2015

How Data Volume Affects Spark Based Data Analytics on a Scale-up Server

Sheer increase in volume of data over the last decade has triggered research in cluster computing frameworks that enable web enterprises to extract big insights from big data. While Apache Spark is gaining popularity for exhibiting superior scale-out performance on the commodity machines, the impact of data volume on the performance of Spark based data analytics in scale-up configuration is not well understood. We present a deep-dive analysis of Spark based applications on a large scale-up server machine. Our analysis reveals that Spark based data analytics are DRAM bound and do not benefit by using more than 12 cores for an executor. By enlarging input data size, application performance degrades significantly due to substantial increase in wait time during I/O operations and garbage collection, despite 10\% better instruction retirement rate (due to lower L1 cache misses and higher core utilization). We match memory behaviour with the garbage collector to improve performance of applications between 1.6x to 3x.

cs.DC↗

arXiv2015

Performance Characterization of In-Memory Data Analytics on a Modern Cloud Server

In last decade, data analytics have rapidly progressed from traditional disk-based processing to modern in-memory processing. However, little effort has been devoted at enhancing performance at micro-architecture level. This paper characterizes the performance of in-memory data analytics using Apache Spark framework. We use a single node NUMA machine and identify the bottlenecks hampering the scalability of workloads. We also quantify the inefficiencies at micro-architecture level for various data analysis workloads. Through empirical evaluation, we show that spark workloads do not scale linearly beyond twelve threads, due to work time inflation and thread level load imbalance. Further, at the micro-architecture level, we observe memory bound latency to be the major cause of work time inflation.

cs.DC↗