61 citations · 319 across the 56 of their papers we have counts for
13 papers · 1 filter
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…
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…
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…
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…
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…
Learning LWF Chain Graphs: A Markov Blanket Discovery Approach
Mohammad Ali Javidian, Marco Valtorta, Pooyan Jamshidi
This paper provides a graphical characterization of Markov blankets in chain graphs (CGs) under the Lauritzen-Wermuth-Frydenberg (LWF) interpretation. The characterization is diffe…
Understanding the Nature of System-Related Issues in Machine Learning Frameworks: An Exploratory Study
Yang Ren, Gregory Gay, Christian Kästner +1
Modern systems are built using development frameworks. These frameworks have a major impact on how the resulting system executes, how configurations are managed, how it is tested,…
FlexiBO: A Decoupled Cost-Aware Multi-Objective Optimization Approach for Deep Neural Networks
Md Shahriar Iqbal, Jianhai Su, Lars Kotthoff +1
The design of machine learning systems often requires trading off different objectives, for example, prediction error and energy consumption for deep neural networks (DNNs). Typica…
ATHENA: A Framework based on Diverse Weak Defenses for Building Adversarial Defense
Ying Meng, Jianhai Su, Jason O'Kane +1
There has been extensive research on developing defense techniques against adversarial attacks; however, they have been mainly designed for specific model families or application d…
Conservative Q-Improvement: Reinforcement Learning for an Interpretable Decision-Tree Policy
Aaron M. Roth, Nicholay Topin, Pooyan Jamshidi +1
There is a growing desire in the field of reinforcement learning (and machine learning in general) to move from black-box models toward more "interpretable AI." We improve interpre…
Transfer Learning for Performance Modeling of Deep Neural Network Systems
Md Shahriar Iqbal, Lars Kotthoff, Pooyan Jamshidi
Modern deep neural network (DNN) systems are highly configurable with large a number of options that significantly affect their non-functional behavior, for example inference time…