Search Results for author: Pooyan Jamshidi

Found 19 papers, 15 papers with code

Pretrained Language Models are Symbolic Mathematics Solvers too!

1 code implementation7 Oct 2021 Kimia Noorbakhsh, Modar Sulaiman, Mahdi Sharifi, Kallol Roy, Pooyan Jamshidi

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.

Fine-tuning

Scalable Causal Transfer Learning

no code implementations27 Feb 2021 Mohammad Ali Javidian, Om Pandey, Pooyan Jamshidi

To overcome this difficulty, we propose SCTL, an algorithm that avoids an exhaustive search and identifies invariant causal features across the source and target domains based on Markov blanket discovery.

Causal Discovery Causal Inference +2

Accelerating Recursive Partition-Based Causal Structure Learning

no code implementations23 Feb 2021 Md. Musfiqur Rahman, Ayman Rasheed, Md. Mosaddek Khan, Mohammad Ali Javidian, Pooyan Jamshidi, Md. Mamun-or-Rashid

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.

Causal Discovery Decision Making +1

Learning LWF Chain Graphs: A Markov Blanket Discovery Approach

1 code implementation29 May 2020 Mohammad Ali Javidian, Marco Valtorta, Pooyan Jamshidi

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

1 code implementation27 May 2020 Mohammad Ali Javidian, Marco Valtorta, Pooyan Jamshidi

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

no code implementations13 May 2020 Yang Ren, Gregory Gay, Christian Kästner, Pooyan Jamshidi

Machine learning (ML) frameworks and the systems developed using them differ greatly from traditional frameworks.

AMP Chain Graphs: Minimal Separators and Structure Learning Algorithms

1 code implementation24 Feb 2020 Mohammad Ali Javidian, Marco Valtorta, Pooyan Jamshidi

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: Cost-Aware Multi-Objective Optimization of Deep Neural Networks

1 code implementation18 Jan 2020 Md Shahriar Iqbal, Jianhai Su, Lars Kotthoff, Pooyan Jamshidi

This is particularly important for optimizing DNNs: the cost arising on account of assessing the accuracy of DNNs is orders of magnitude higher than that of measuring the energy consumption of pre-trained DNNs.

Object Detection Speech Recognition

ATHENA: A Framework based on Diverse Weak Defenses for Building Adversarial Defense

3 code implementations2 Jan 2020 Ying Meng, Jianhai Su, Jason O'Kane, Pooyan Jamshidi

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.

Adversarial Defense Denoising

Whence to Learn? Transferring Knowledge in Configurable Systems using BEETLE

2 code implementations1 Nov 2019 Rahul Krishna, Vivek Nair, Pooyan Jamshidi, Tim Menzies

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

1 code implementation1 Oct 2019 Mohammad Ali Javidian, Marco Valtorta, Pooyan Jamshidi

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

1 code implementation2 Jul 2019 Aaron M. Roth, Nicholay Topin, Pooyan Jamshidi, Manuela Veloso

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

1 code implementation4 Apr 2019 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 and energy consumption.

Transfer Learning

Machine Learning Meets Quantitative Planning: Enabling Self-Adaptation in Autonomous Robots

1 code implementation10 Mar 2019 Pooyan Jamshidi, Javier Cámara, Bradley Schmerl, Christian Kästner, David Garlan

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

1 code implementation26 Feb 2019 Mohammad Ali Javidian, Pooyan Jamshidi, Marco Valtorta

We expect that the ability to carry over causal relations will enable effective performance analysis of highly-configurable systems.

Transfer Learning

Transfer Learning with Bellwethers to find Good Configurations

3 code implementations11 Mar 2018 Vivek Nair, Rahul Krishna, Tim Menzies, Pooyan Jamshidi

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

A Comparison of Reinforcement Learning Techniques for Fuzzy Cloud Auto-Scaling

no code implementations19 May 2017 Hamid Arabnejad, Claus Pahl, Pooyan Jamshidi, Giovani Estrada

A goal of cloud service management is to design self-adaptable auto-scaler to react to workload fluctuations and changing the resources assigned.

Q-Learning

Self-Learning Cloud Controllers: Fuzzy Q-Learning for Knowledge Evolution

1 code implementation2 Jul 2015 Pooyan Jamshidi, Amir Sharifloo, Claus Pahl, Andreas Metzger, Giovani Estrada

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.

Q-Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.