[Submitted on 10 Feb 2025 ( v1 ), last revised 19 Dec 2025 (this version, v3)] Title:Generating Samples to Probe Trained Models View a PDF of the paper titled Generating Samples to Probe Trained Models, by Eren Mehmet K{\i}ral and 2 other authors View PDF HTML (experimental) Abstract:There is a growing need for investigating how machine learning models operate. With this work, we aim to understand trained machine learning models by questioning their data preferences.
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Ş. Ilker
[2502.04840] Coherent Local Explanations for Mathematical Optimization
arXiv:2502.04840 (math) View PDF HTML (experimental) Subjects: Optimization and Control (math.OC); Machine Learning (cs.LG) Cite as: arXiv:2502.04840 [math.OC] (or arXiv:2502.04840v1 [math.OC] for this version) https://doi.org/10.48550/arXiv.2502.04840 Submission history From: Ilker Birbil [ view email] [v1] Fri, 7 Feb 2025 11:18:04 UTC (6,813 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic Explorer () Connected Papers Toggle Connected Papers (What is Connected Papers?)...
[2405.15314] Output-Constrained Decision Trees
arXiv:2405.15314 (cs) View PDF HTML (experimental) Comments: Subjects: Machine Learning (cs.LG) Cite as: arXiv:2405.15314 [cs.LG] (or arXiv:2405.15314v1 [cs.LG] for this version) Submission history From: Ilker Birbil [ view email] [v1] Fri, 24 May 2024 07:54:44 UTC (1,895 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic Explorer () Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Links to Code...
[2405.15431] Counterfactual Explanations for Linear Optimization
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
[2307.00897] Fixing confirmation bias in feature attribution methods via semantic match
[Submitted on 3 Jul 2023 ( v1 ), last revised 26 Feb 2024 (this version, v3)] Title:Fixing confirmation bias in feature attribution methods via semantic match Download a PDF of the paper titled Fixing confirmation bias in feature attribution methods via semantic match, by Giovanni Cin\`a and 8 other authors Download PDF HTML (experimental) Abstract:Feature attribution methods have become a staple method to disentangle the complex behavior of black box models.
[2301.11113] Finding Regions of Counterfactual Explanations via Robust Optimization
[Submitted on 26 Jan 2023 ( v1 ), last revised 16 May 2023 (this version, v2)] Title:Finding Regions of Counterfactual Explanations via Robust Optimization Download a PDF of the paper titled Finding Regions of Counterfactual Explanations via Robust Optimization, by Donato Maragno and 5 other authors Download PDF Abstract: Counterfactual explanations play an important role in detecting bias and improving the explainability of data-driven classification models.
[2111.07058] Bolstering Stochastic Gradient Descent with Model Building
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
[2110.10498] Differentially Private Linear Optimization for Multi-Party Resource Sharing
[Submitted on 20 Oct 2021 ( v1 ), last revised 4 Jan 2024 (this version, v3)] Title:Differentially Private Linear Optimization for Multi-Party Resource Sharing Download a PDF of the paper titled Differentially Private Linear Optimization for Multi-Party Resource Sharing, by Utku Karaca and 3 other authors Download PDF HTML (experimental) Abstract:This study examines a resource-sharing problem involving multiple parties that agree to use a set of capacities together.
Rule Generation for Classification: Scalability, Interpretability, and Fairness
[Submitted on 21 Apr 2021 ( v1 ), last revised 6 Feb 2025 (this version, v5)] Title:Rule Generation for Classification: Scalability, Interpretability, and Fairness View a PDF of the paper titled Rule Generation for Classification: Scalability, Interpretability, and Fairness, by Tabea E. R\"ober and 3 other authors View PDF HTML (experimental) Abstract:We introduce a new rule-based optimization method for classification with constraints.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Ş.
Contact Ş., search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack