Current state-of-the-art systems for hybrid memory management are enriched with machine intelligence. To enable the practical use of Machine Learning (ML), system-level page schedulers focus the ML model training over a small subset of the applications’ memory footprint. At the same time, they use existing lightweight historical information to predict the access behavior of majority of the pages. To maximize application performance improvements, the pages selected for machine learning-based management are identified with elaborate page selection methods. These methods involve the calculation of detailed performance estimates depending on the configuration of the hybrid memory platform. This paper explores the opportunities to reduce such operational overheads of machine learning-based hybrid memory page schedulers via use of visualization techniques to depict memory access patterns, and reveal spatial and temporal correlations among the selected pages, that current methods fail to leverage. We propose an initial version of a visualization pipeline for prioritizing pages for machine learning, that is independent of the hybrid memory configuration. Our approach selects pages whose ML-based management delivers, on average, performance levels within 5% of current solutions, while reducing by 75 × the page selection time. We discuss future directions and make a case that visualization and computer vision methods can unlock new insights and reduce the operational complexity of emerging systems solutions.
more »
« less
This content will become publicly available on June 27, 2024
Learning-Assisted Algorithm Unrolling for Online Optimization with Budget Constraints
Online optimization with multiple budget constraints is challenging since the online decisions over a short time horizon are coupled together by strict inventory constraints. The existing manually-designed algorithms cannot achieve satisfactory average performance for this setting because they often need a large number of time steps for convergence and/or may violate the inventory constraints. In this paper, we propose a new machine learning (ML) assisted unrolling approach, called LAAU (Learning-Assisted Algorithm Unrolling), which unrolls the agent’s online decision pipeline and leverages an ML model for updating the Lagrangian multiplier online. For efficient training via backpropagation, we derive gradients of the decision pipeline over time. We also provide the average cost bounds for two cases when training data is available offline and collected online, respectively. Finally, we present numerical results to highlight that LAAU can outperform the existing baselines.
more »
« less
- Award ID(s):
- 1910208
- NSF-PAR ID:
- 10466187
- Date Published:
- Journal Name:
- Proceedings of the AAAI Conference on Artificial Intelligence
- Volume:
- 37
- Issue:
- 9
- ISSN:
- 2159-5399
- Page Range / eLocation ID:
- 10771 to 10779
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The increasing ubiquity of network traffic and the new online applications’ deployment has increased traffic analysis complexity. Traditionally, network administrators rely on recognizing well-known static ports for classifying the traffic flowing their networks. However, modern network traffic uses dynamic ports and is transported over secure application-layer protocols (e.g., HTTPS, SSL, and SSH). This makes it a challenging task for network administrators to identify online applications using traditional port-based approaches. One way for classifying the modern network traffic is to use machine learning (ML) to distinguish between the different traffic attributes such as packet count and size, packet inter-arrival time, packet send–receive ratio, etc. This paper presents the design and implementation of NetScrapper, a flow-based network traffic classifier for online applications. NetScrapper uses three ML models, namely K-Nearest Neighbors (KNN), Random Forest (RF), and Artificial Neural Network (ANN), for classifying the most popular 53 online applications, including Amazon, Youtube, Google, Twitter, and many others. We collected a network traffic dataset containing 3,577,296 packet flows with different 87 features for training, validating, and testing the ML models. A web-based user-friendly interface is developed to enable users to either upload a snapshot of their network traffic to NetScrapper or sniff the network traffic directly from the network interface card in real time. Additionally, we created a middleware pipeline for interfacing the three models with the Flask GUI. Finally, we evaluated NetScrapper using various performance metrics such as classification accuracy and prediction time. Most notably, we found that our ANN model achieves an overall classification accuracy of 99.86% in recognizing the online applications in our dataset.more » « less
-
more » « less
Machine learning (ML) has become increasingly prevalent in various domains. However, ML algorithms sometimes give unfair outcomes and discrimination against certain groups. Thereby, bias occurs when our results produce a decision that is systematically incorrect. At various phases of the ML pipeline, such as data collection, pre-processing, model selection, and evaluation, these biases appear. Bias reduction methods for ML have been suggested using a variety of techniques. By changing the data or the model itself, adding more fairness constraints, or both, these methods try to lessen bias. The best technique relies on the particular context and application because each technique has advantages and disadvantages. Therefore, in this paper, we present a comprehensive survey of bias mitigation techniques in machine learning (ML) with a focus on in-depth exploration of methods, including adversarial training. We examine the diverse types of bias that can afflict ML systems, elucidate current research trends, and address future challenges. Our discussion encompasses a detailed analysis of pre-processing, in-processing, and post-processing methods, including their respective pros and cons. Moreover, we go beyond qualitative assessments by quantifying the strategies for bias reduction and providing empirical evidence and performance metrics. This paper serves as an invaluable resource for researchers, practitioners, and policymakers seeking to navigate the intricate landscape of bias in ML, offering both a profound understanding of the issue and actionable insights for responsible and effective bias mitigation.
-
more » « less
The use of audio and video modalities for Human Activity Recognition (HAR) is common, given the richness of the data and the availability of pre-trained ML models using a large corpus of labeled training data. However, audio and video sensors also lead to significant consumer privacy concerns. Researchers have thus explored alternate modalities that are less privacy-invasive such as mmWave doppler radars, IMUs, motion sensors. However, the key limitation of these approaches is that most of them do not readily generalize across environments and require significant in-situ training data. Recent work has proposed cross-modality transfer learning approaches to alleviate the lack of trained labeled data with some success. In this paper, we generalize this concept to create a novel system called VAX (Video/Audio to 'X'), where training labels acquired from existing Video/Audio ML models are used to train ML models for a wide range of 'X' privacy-sensitive sensors. Notably, in VAX, once the ML models for the privacy-sensitive sensors are trained, with little to no user involvement, the Audio/Video sensors can be removed altogether to protect the user's privacy better. We built and deployed VAX in ten participants' homes while they performed 17 common activities of daily living. Our evaluation results show that after training, VAX can use its onboard camera and microphone to detect approximately 15 out of 17 activities with an average accuracy of 90%. For these activities that can be detected using a camera and a microphone, VAX trains a per-home model for the privacy-preserving sensors. These models (average accuracy = 84%) require no in-situ user input. In addition, when VAX is augmented with just one labeled instance for the activities not detected by the VAX A/V pipeline (~2 out of 17), it can detect all 17 activities with an average accuracy of 84%. Our results show that VAX is significantly better than a baseline supervised-learning approach of using one labeled instance per activity in each home (average accuracy of 79%) since VAX reduces the user burden of providing activity labels by 8x (~2 labels vs. 17 labels).
-
more » « less
For energy-assisted compression ignition (EACI) engine propulsion at high-altitude operating conditions using sustainable jet fuels with varying cetane numbers, it is essential to develop an efficient engine control system for robust and optimal operation. Control systems are typically trained using experimental data, which can be costly and time consuming to generate due to setup time of experiments, unforeseen delays/issues with manufacturing, mishaps/engine failures and the consequent repairs (which can take weeks), and errors in measurements. Computational fluid dynamics (CFD) simulations can overcome such burdens by complementing experiments with simulated data for control system training. Such simulations, however, can be computationally expensive. Existing data-driven machine learning (ML) models have shown promise for emulating the expensive CFD simulator, but encounter key limitations here due to the expensive nature of the training data and the range of differing combustion behaviors (e.g. misfires and partial/delayed ignition) observed at such broad operating conditions. We thus develop a novel physics-integrated emulator, called the Misfire-Integrated GP (MInt-GP), which integrates important auxiliary information on engine misfires within a Gaussian process surrogate model. With limited CFD training data, we show the MInt-GP model can yield reliable predictions of in-cylinder pressure evolution profiles and subsequent heat release profiles and engine CA50 predictions at a broad range of input conditions. We further demonstrate much better prediction capabilities of the MInt-GP at different combustion behaviors compared to existing data-driven ML models such as kriging and neural networks, while also observing up to 80 times computational speed-up over CFD, thus establishing its effectiveness as a tool to assist CFD for fast data generation in control system training.
