61 citations · 319 across the 56 of their papers we have counts for
58 papers
Multi-Objective Multi-Fidelity Bayesian Optimization with Causal Priors
Md Abir Hossen, Mohammad Ali Javidian, Vignesh Narayanan +2
Multi-fidelity Bayesian optimization (MFBO) accelerates the search for the global optimum of black-box functions by integrating inexpensive, low-fidelity approximations. The centra…
Hardness, Structural Knowledge, and Opportunity: An Analytical Framework for Modular Performance Modeling
Omid Gheibi, Christian Kästner, Pooyan Jamshidi
Performance-influence models are beneficial for understanding how configurations affect system performance, but their creation is challenging due to the exponential growth of confi…
An Empirical Study of Accuracy-Robustness Tradeoff and Training Efficiency in Self-Supervised Learning
Fatemeh Ghofrani, Pooyan Jamshidi
Self-supervised learning (SSL) has significantly advanced image representation learning, yet efficiency challenges persist, particularly with adversarial training. Many SSL methods…
Sponge: Inference Serving with Dynamic SLOs Using In-Place Vertical Scaling
Kamran Razavi, Saeid Ghafouri, Max Mühlhäuser +2
Mobile and IoT applications increasingly adopt deep learning inference to provide intelligence. Inference requests are typically sent to a cloud infrastructure over a wireless netw…
CURE: Simulation-Augmented Auto-Tuning in Robotics
Md Abir Hossen, Sonam Kharade, Jason M. O'Kane +3
Robotic systems are typically composed of various subsystems, such as localization and navigation, each encompassing numerous configurable components (e.g., selecting different pla…
Software Engineering for Robotics: Future Research Directions; Report from the 2023 Workshop on Software Engineering for Robotics
Claire Le Goues, Sebastian Elbaum, David Anthony +7
Robots are experiencing a revolution as they permeate many aspects of our daily lives, from performing house maintenance to infrastructure inspection, from efficiently warehousing…
HEET: A Heterogeneity Measure to Quantify the Difference across Distributed Computing Systems
Ali Mokhtari, Saeid Ghafouri, Pooyan Jamshidi +1
Although system heterogeneity has been extensively studied in the past, there is yet to be a study on measuring the impact of heterogeneity on system performance. For this purpose,…
Introducing Interactions in Multi-Objective Optimization of Software Architectures
Vittorio Cortellessa, J. Andres Diaz-Pace, Daniele Di Pompeo +4
Software architecture optimization aims to enhance non-functional attributes like performance and reliability while meeting functional requirements. Multi-objective optimization em…
Independent Modular Networks
Hamed Damirchi, Forest Agostinelli, Pooyan Jamshidi
Monolithic neural networks that make use of a single set of weights to learn useful representations for downstream tasks explicitly dismiss the compositional nature of data generat…
CAMEO: A Causal Transfer Learning Approach for Performance Optimization of Configurable Computer Systems
Md Shahriar Iqbal, Ziyuan Zhong, Iftakhar Ahmad +2
Modern computer systems are highly configurable, with hundreds of configuration options that interact, resulting in an enormous configuration space. As a result, optimizing perform…
Reconciling High Accuracy, Cost-Efficiency, and Low Latency of Inference Serving Systems
Mehran Salmani, Saeid Ghafouri, Alireza Sanaee +5
The use of machine learning (ML) inference for various applications is growing drastically. ML inference services engage with users directly, requiring fast and accurate responses.…
Rethinking Robust Contrastive Learning from the Adversarial Perspective
Fatemeh Ghofrani, Mehdi Yaghouti, Pooyan Jamshidi
To advance the understanding of robust deep learning, we delve into the effects of adversarial training on self-supervised and supervised contrastive learning alongside supervised…
CaRE: Finding Root Causes of Configuration Issues in Highly-Configurable Robots
Md Abir Hossen, Sonam Kharade, Bradley Schmerl +6
Robotic systems have subsystems with a combinatorially large configuration space and hundreds or thousands of possible software and hardware configuration options interacting non-t…
Improving the Performance of DNN-based Software Services using Automated Layer Caching
Mohammadamin Abedi, Yanni Iouannou, Pooyan Jamshidi +1
Deep Neural Networks (DNNs) have become an essential component in many application domains including web-based services. A variety of these services require high throughput and (cl…
FELARE: Fair Scheduling of Machine Learning Tasks on Heterogeneous Edge Systems
Ali Mokhtari, Md Abir Hossen, Pooyan Jamshidi +1
Edge computing enables smart IoT-based systems via concurrent and continuous execution of latency-sensitive machine learning (ML) applications. These edge-based machine learning sy…
Guidelines for Artifacts to Support Industry-Relevant Research on Self-Adaptation
Danny Weyns, Ilias Gerostathopoulos, Barbora Buhnova +16
Artifacts support evaluating new research results and help comparing them with the state of the art in a field of interest. Over the past years, several artifacts have been introdu…
On Debugging the Performance of Configurable Software Systems: Developer Needs and Tailored Tool Support
Miguel Velez, Pooyan Jamshidi, Norbert Siegmund +2
Determining whether a configurable software system has a performance bug or it was misconfigured is often challenging. While there are numerous debugging techniques that can suppor…
Pre-Trained Language Transformers are Universal Image Classifiers
Rahul Goel, Modar Sulaiman, Kimia Noorbakhsh +4
Facial images disclose many hidden personal traits such as age, gender, race, health, emotion, and psychology. Understanding these traits will help to classify the people in differ…
Unicorn: Reasoning about Configurable System Performance through the lens of Causality
Md Shahriar Iqbal, Rahul Krishna, Mohammad Ali Javidian +2
Modern computer systems are highly configurable, with the total variability space sometimes larger than the number of atoms in the universe. Understanding and reasoning about the p…
Pretrained Language Models are Symbolic Mathematics Solvers too!
Kimia Noorbakhsh, Modar Sulaiman, Mahdi Sharifi +2
Solving symbolic mathematics has always been of in the arena of human ingenuity that needs compositional reasoning and recurrence. However, recent studies have shown that large-sca…
Scalable Causal Domain Adaptation
Mohammad Ali Javidian, Om Pandey, Pooyan Jamshidi
One of the most critical problems in transfer learning is the task of domain adaptation, where the goal is to apply an algorithm trained in one or more source domains to a differen…
Accelerating Recursive Partition-Based Causal Structure Learning
Md. Musfiqur Rahman, Ayman Rasheed, Md. Mosaddek Khan +3
Causal structure discovery from observational data is fundamental to the causal understanding of autonomous systems such as medical decision support systems, advertising campaigns…
White-Box Analysis over Machine Learning: Modeling Performance of Configurable Systems
Miguel Velez, Pooyan Jamshidi, Norbert Siegmund +2
Performance-influence models can help stakeholders understand how and where configuration options and their interactions influence the performance of a system. With this understand…
Kuksa*: Self-Adaptive Microservices in Automotive Systems
Ahmad Banijamali, Pasi Kuvaja, Markku Oivo +1
In pervasive dynamic environments, vehicles connect to other objects to send operational data and receive updates so that vehicular applications can provide services to users on de…