Search Results for author:
Found 29 papers, 22 papers with code
CURE: Simulation-Augmented Auto-Tuning in Robotics
This paper proposes CURE -- a method that identifies causally relevant configuration options, enabling the optimization process to operate in a reduced search space, thereby enabling faster optimization of robot performance.
IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency
Model variants are different versions of pre-trained models for the same deep learning task with variations in resource requirements, latency, and accuracy.
Independent Modular Networks
However, a lack of structure in each module's role, and modular network-specific issues such as module collapse have restricted their usability.
Reconciling High Accuracy, Cost-Efficiency, and Low Latency of Inference Serving Systems
Adapting to dynamic workloads considering all the pillars of accuracy, latency, and resource cost is challenging.
Rethinking Robust Contrastive Learning from the Adversarial Perspective
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 learning.
CaRE: Finding Root Causes of Configuration Issues in Highly-Configurable Robots
Finding the root cause of such faults is challenging due to the exponentially large configuration space and the dependencies between the robot's configuration settings and performance.
Improving the Performance of DNN-based Software Services using Automated Layer Caching
The proposed solution is an automated online layer caching mechanism that allows early exiting of a large model during inference time if the cache model in one of the early exits is confident enough for final prediction.
FELARE: Fair Scheduling of Machine Learning Tasks on Heterogeneous Edge Systems
The challenge is to allocate user requests for different ML applications on the Heterogeneous Edge Computing Systems (HEC) with respect to both the energy and latency constraints of these systems.
Pre-Trained Language Transformers are Universal Image Classifiers
The pretrained transformer of GPT-2 is trained to generate text and then fine-tuned to classify facial images.
Unicorn: Reasoning about Configurable System Performance through the lens of Causality
Understanding and reasoning about the performance behavior of highly configurable systems, over a vast and variable space, is challenging.
Pretrained Language Models are Symbolic Mathematics Solvers too!
In this paper, we present a sample efficient way of solving the symbolic tasks by first pretraining the transformer model with language translation and then fine-tuning the pretrained transformer model to solve the downstream task of symbolic mathematics.
Scalable Causal Domain Adaptation
To overcome this difficulty, we propose SCTL, an algorithm that avoids an exhaustive search and identifies invariant causal features across source and target domains based on Markov blanket discovery.
Accelerating Recursive Partition-Based Causal Structure Learning
This paper proposes a generic causal structure refinement strategy that can locate the undesired relations with a small number of CI-tests, thus speeding up the algorithm for large and complex problems.
Learning LWF Chain Graphs: A Markov Blanket Discovery Approach
We provide a novel scalable and sound algorithm for Markov blanket discovery in LWF CGs and prove that the Grow-Shrink algorithm, the IAMB algorithm, and its variants are still correct for Markov blanket discovery in LWF CGs under the same assumptions as for Bayesian networks.
Learning LWF Chain Graphs: an Order Independent Algorithm
We present a PC-like algorithm that finds the structure of chain graphs under the faithfulness assumption to resolve the problem of scalability of the proposed algorithm by Studeny (1997).
Understanding the Nature of System-Related Issues in Machine Learning Frameworks: An Exploratory Study
Machine learning (ML) frameworks and the systems developed using them differ greatly from traditional frameworks.
AMP Chain Graphs: Minimal Separators and Structure Learning Algorithms
To address the problem of learning the structure of AMP CGs from data, we show that the PC-like algorithm (Pena, 2012) is order-dependent, in the sense that the output can depend on the order in which the variables are given.
FlexiBO: A Decoupled Cost-Aware Multi-Objective Optimization Approach for Deep Neural Networks
FlexiBO weights the improvement of the hypervolume of the Pareto region by the measurement cost of each objective to balance the expense of collecting new information with the knowledge gained through objective evaluations, preventing us from performing expensive measurements for little to no gain.
ATHENA: A Framework based on Diverse Weak Defenses for Building Adversarial Defense
There has been extensive research on developing defense techniques against adversarial attacks; however, they have been mainly designed for specific model families or application domains, therefore, they cannot be easily extended.
Whence to Learn? Transferring Knowledge in Configurable Systems using BEETLE
To resolve these problems, we propose a novel transfer learning framework called BEETLE, which is a "bellwether"-based transfer learner that focuses on identifying and learning from the most relevant source from amongst the old data.
Software Engineering
Order-Independent Structure Learning of Multivariate Regression Chain Graphs
We consider the PC-like algorithm for structure learning of MVR CGs, which is a constraint-based method proposed by Sonntag and Pe\~{n}a in [18].
Conservative Q-Improvement: Reinforcement Learning for an Interpretable Decision-Tree Policy
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."
Transfer Learning for Performance Modeling of Deep Neural Network Systems
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 and energy consumption.
Machine Learning Meets Quantitative Planning: Enabling Self-Adaptation in Autonomous Robots
Modern cyber-physical systems (e. g., robotics systems) are typically composed of physical and software components, the characteristics of which are likely to change over time.
Transfer Learning for Performance Modeling of Configurable Systems: A Causal Analysis
We expect that the ability to carry over causal relations will enable effective performance analysis of highly-configurable systems.
Transfer Learning with Bellwethers to find Good Configurations
Using this insight, this paper proposes BEETLE, a novel bellwether based transfer learning scheme, which can identify a suitable source and use it to find near-optimal configurations of a software system.
Software Engineering
Transfer Learning for Performance Modeling of Configurable Systems: An Exploratory Analysis
Modern software systems provide many configuration options which significantly influence their non-functional properties.
A Comparison of Reinforcement Learning Techniques for Fuzzy Cloud Auto-Scaling
A goal of cloud service management is to design self-adaptable auto-scaler to react to workload fluctuations and changing the resources assigned.
Self-Learning Cloud Controllers: Fuzzy Q-Learning for Knowledge Evolution
The benefit is that for designing cloud controllers, we do not have to rely solely on precise design-time knowledge, which may be difficult to acquire.
