Zobrazeno 1 - 10
of 3 960
pro vyhledávání: '"Kadioğlu A"'
Mixed-Integer Programming (MIP) is a powerful paradigm for modeling and solving various important combinatorial optimization problems. Recently, learning-based approaches have shown potential to speed up MIP solving via offline training that then gui
Externí odkaz:
http://arxiv.org/abs/2412.14382
Autor:
Rosenberg, Gili, Brubaker, J. Kyle, Schuetz, Martin J. A., Zhu, Elton Yechao, Kadıoğlu, Serdar, Borujeni, Sima E., Katzgraber, Helmut G.
Pruning neural networks, which involves removing a fraction of their weights, can often maintain high accuracy while significantly reducing model complexity, at least up to a certain limit. We present a neural network pruning technique that builds up
Externí odkaz:
http://arxiv.org/abs/2411.17796
Autor:
Kadioglu, Serdar, Michalsky, Filip
The acceleration in the adoption of AI-based automated decision-making systems poses a challenge for evaluating the fairness of algorithmic decisions, especially in the absence of ground truth. When designing interventions, uplift modeling is used ex
Externí odkaz:
http://arxiv.org/abs/2403.12069
Autor:
Kadıoğlu, Serdar, Kleynhans, Bernard
The goal of this paper is to share our experience in designing and organizing educational competitions with anonymous and (near) real-time leaderboards in both academic and industrial settings. While such competitions serve as a great educational too
Externí odkaz:
http://arxiv.org/abs/2402.07936
This study presents a deep learning-based approach to seismic velocity inversion problem, focusing on both noisy and noiseless training datasets of varying sizes. Our Seismic Velocity Inversion Network (SVInvNet) introduces a novel architecture that
Externí odkaz:
http://arxiv.org/abs/2312.08194
Twenty-seven years ago, E. Freuder highlighted that "Constraint programming represents one of the closest approaches computer science has yet made to the Holy Grail of programming: the user states the problem, the computer solves it". Nowadays, CP us
Externí odkaz:
http://arxiv.org/abs/2308.01589
Publikováno v:
New J. Phys. 25 113014 (2023)
We investigate the energetic advantage of accelerating a quantum harmonic oscillator Otto engine by use of shortcuts to adiabaticity (for the expansion and compression strokes) and to equilibrium (for the hot isochore), by means of counter-diabatic (
Externí odkaz:
http://arxiv.org/abs/2306.14847
Autor:
Tuncer, Aslı, Kadıoğlu, Serhat C.
We propose that spin glasses can exist in equally probable superposition states (SSs) comprising potential configurations. Employing the Edward-Anderson (EA) order parameter and magnetization, we establish a classification scheme for these SSs based
Externí odkaz:
http://arxiv.org/abs/2306.10571
Autor:
Rosenberg, Gili, Brubaker, J. Kyle, Schuetz, Martin J. A., Salton, Grant, Zhu, Zhihuai, Zhu, Elton Yechao, Kadıoğlu, Serdar, Borujeni, Sima E., Katzgraber, Helmut G.
We propose and implement an interpretable machine learning classification model for Explainable AI (XAI) based on expressive Boolean formulas. Potential applications include credit scoring and diagnosis of medical conditions. The Boolean formula defi
Externí odkaz:
http://arxiv.org/abs/2306.03976
Autor:
Tuncer, Aslı, Kadıoğlu, Serhat C.
Spin-glass (SG) is a fascinating system that has garnered significant attention due to its intriguing properties and implications for various research fields. One of the key characteristics of spin glasses is that they contain random disorder, which
Externí odkaz:
http://arxiv.org/abs/2304.09782