Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Samet Oymak

Samet Oymak

Certainty Equivalent Quadratic Control for Markov Jump Systems


May 26, 2021
Zhe Du, Yahya Sattar, Davoud Ataee Tarzanagh, Laura Balzano, Samet Oymak, Necmiye Ozay

Figure 1 for Certainty Equivalent Quadratic Control for Markov Jump Systems
Figure 2 for Certainty Equivalent Quadratic Control for Markov Jump Systems
* 17 pages, 8 figures 
  Access Paper or Ask Questions

Generalization Guarantees for Neural Architecture Search with Train-Validation Split


May 10, 2021
Samet Oymak, Mingchen Li, Mahdi Soltanolkotabi

Figure 1 for Generalization Guarantees for Neural Architecture Search with Train-Validation Split
Figure 2 for Generalization Guarantees for Neural Architecture Search with Train-Validation Split
Figure 3 for Generalization Guarantees for Neural Architecture Search with Train-Validation Split
Figure 4 for Generalization Guarantees for Neural Architecture Search with Train-Validation Split
* to appear in ICML 2021 
  Access Paper or Ask Questions

Unsupervised Multi-source Domain Adaptation Without Access to Source Data


Apr 05, 2021
Sk Miraj Ahmed, Dripta S. Raychaudhuri, Sujoy Paul, Samet Oymak, Amit K. Roy-Chowdhury

Figure 1 for Unsupervised Multi-source Domain Adaptation Without Access to Source Data
Figure 2 for Unsupervised Multi-source Domain Adaptation Without Access to Source Data
Figure 3 for Unsupervised Multi-source Domain Adaptation Without Access to Source Data
Figure 4 for Unsupervised Multi-source Domain Adaptation Without Access to Source Data
* This paper will appear at CVPR 2021 
  Access Paper or Ask Questions

Label-Imbalanced and Group-Sensitive Classification under Overparameterization


Mar 02, 2021
Ganesh Ramachandra Kini, Orestis Paraskevas, Samet Oymak, Christos Thrampoulidis

Figure 1 for Label-Imbalanced and Group-Sensitive Classification under Overparameterization
Figure 2 for Label-Imbalanced and Group-Sensitive Classification under Overparameterization
Figure 3 for Label-Imbalanced and Group-Sensitive Classification under Overparameterization
Figure 4 for Label-Imbalanced and Group-Sensitive Classification under Overparameterization

  Access Paper or Ask Questions

Sample Efficient Subspace-based Representations for Nonlinear Meta-Learning


Feb 26, 2021
Halil Ibrahim Gulluk, Yue Sun, Samet Oymak, Maryam Fazel

Figure 1 for Sample Efficient Subspace-based Representations for Nonlinear Meta-Learning
Figure 2 for Sample Efficient Subspace-based Representations for Nonlinear Meta-Learning
* To appear in ICASSP 21' 
  Access Paper or Ask Questions

Super-Convergence with an Unstable Learning Rate


Feb 22, 2021
Samet Oymak

Figure 1 for Super-Convergence with an Unstable Learning Rate

  Access Paper or Ask Questions

Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks


Dec 16, 2020
Xiangyu Chang, Yingcong Li, Samet Oymak, Christos Thrampoulidis

Figure 1 for Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks
Figure 2 for Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks
Figure 3 for Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks
Figure 4 for Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks
* to appear at AAAI 2021 
  Access Paper or Ask Questions

On the Marginal Benefit of Active Learning: Does Self-Supervision Eat Its Cake?


Nov 16, 2020
Yao-Chun Chan, Mingchen Li, Samet Oymak

Figure 1 for On the Marginal Benefit of Active Learning: Does Self-Supervision Eat Its Cake?
Figure 2 for On the Marginal Benefit of Active Learning: Does Self-Supervision Eat Its Cake?
Figure 3 for On the Marginal Benefit of Active Learning: Does Self-Supervision Eat Its Cake?
Figure 4 for On the Marginal Benefit of Active Learning: Does Self-Supervision Eat Its Cake?

  Access Paper or Ask Questions

Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View


Nov 16, 2020
Christos Thrampoulidis, Samet Oymak, Mahdi Soltanolkotabi

Figure 1 for Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View
Figure 2 for Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View
Figure 3 for Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View
Figure 4 for Theoretical Insights Into Multiclass Classification: A High-dimensional Asymptotic View
* To Appear at NeurIPS 2020. 62 pages, 7 figures 
  Access Paper or Ask Questions

Unsupervised Paraphrasing via Deep Reinforcement Learning


Jul 05, 2020
A. B. Siddique, Samet Oymak, Vagelis Hristidis

Figure 1 for Unsupervised Paraphrasing via Deep Reinforcement Learning
Figure 2 for Unsupervised Paraphrasing via Deep Reinforcement Learning
Figure 3 for Unsupervised Paraphrasing via Deep Reinforcement Learning
Figure 4 for Unsupervised Paraphrasing via Deep Reinforcement Learning

  Access Paper or Ask Questions

Statistical and Algorithmic Insights for Semi-supervised Learning with Self-training


Jun 19, 2020
Samet Oymak, Talha Cihad Gulcu

Figure 1 for Statistical and Algorithmic Insights for Semi-supervised Learning with Self-training
Figure 2 for Statistical and Algorithmic Insights for Semi-supervised Learning with Self-training
Figure 3 for Statistical and Algorithmic Insights for Semi-supervised Learning with Self-training
Figure 4 for Statistical and Algorithmic Insights for Semi-supervised Learning with Self-training
* 25 pages 
  Access Paper or Ask Questions

Exploring Weight Importance and Hessian Bias in Model Pruning


Jun 19, 2020
Mingchen Li, Yahya Sattar, Christos Thrampoulidis, Samet Oymak

Figure 1 for Exploring Weight Importance and Hessian Bias in Model Pruning
Figure 2 for Exploring Weight Importance and Hessian Bias in Model Pruning
Figure 3 for Exploring Weight Importance and Hessian Bias in Model Pruning
Figure 4 for Exploring Weight Importance and Hessian Bias in Model Pruning
* 28 pages 
  Access Paper or Ask Questions

On the Role of Dataset Quality and Heterogeneity in Model Confidence


Feb 23, 2020
Yuan Zhao, Jiasi Chen, Samet Oymak

Figure 1 for On the Role of Dataset Quality and Heterogeneity in Model Confidence
Figure 2 for On the Role of Dataset Quality and Heterogeneity in Model Confidence
Figure 3 for On the Role of Dataset Quality and Heterogeneity in Model Confidence
Figure 4 for On the Role of Dataset Quality and Heterogeneity in Model Confidence
* 25 pages, 14 figures 
  Access Paper or Ask Questions

Non-asymptotic and Accurate Learning of Nonlinear Dynamical Systems


Feb 20, 2020
Yahya Sattar, Samet Oymak

Figure 1 for Non-asymptotic and Accurate Learning of Nonlinear Dynamical Systems
Figure 2 for Non-asymptotic and Accurate Learning of Nonlinear Dynamical Systems
Figure 3 for Non-asymptotic and Accurate Learning of Nonlinear Dynamical Systems

  Access Paper or Ask Questions

Generalization Guarantees for Neural Networks via Harnessing the Low-rank Structure of the Jacobian


Jul 04, 2019
Samet Oymak, Zalan Fabian, Mingchen Li, Mahdi Soltanolkotabi

Figure 1 for Generalization Guarantees for Neural Networks via Harnessing the Low-rank Structure of the Jacobian
Figure 2 for Generalization Guarantees for Neural Networks via Harnessing the Low-rank Structure of the Jacobian
Figure 3 for Generalization Guarantees for Neural Networks via Harnessing the Low-rank Structure of the Jacobian
Figure 4 for Generalization Guarantees for Neural Networks via Harnessing the Low-rank Structure of the Jacobian

  Access Paper or Ask Questions

Quickly Finding the Best Linear Model in High Dimensions


Jul 03, 2019
Yahya Sattar, Samet Oymak

Figure 1 for Quickly Finding the Best Linear Model in High Dimensions
Figure 2 for Quickly Finding the Best Linear Model in High Dimensions
Figure 3 for Quickly Finding the Best Linear Model in High Dimensions

  Access Paper or Ask Questions

Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks


Apr 07, 2019
Mingchen Li, Mahdi Soltanolkotabi, Samet Oymak

Figure 1 for Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks
Figure 2 for Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks
Figure 3 for Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks
Figure 4 for Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks

  Access Paper or Ask Questions

Towards moderate overparameterization: global convergence guarantees for training shallow neural networks


Feb 12, 2019
Samet Oymak, Mahdi Soltanolkotabi

Figure 1 for Towards moderate overparameterization: global convergence guarantees for training shallow neural networks
Figure 2 for Towards moderate overparameterization: global convergence guarantees for training shallow neural networks

  Access Paper or Ask Questions

Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?


Dec 25, 2018
Samet Oymak, Mahdi Soltanolkotabi

Figure 1 for Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?
Figure 2 for Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?
Figure 3 for Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?

  Access Paper or Ask Questions

Stochastic Gradient Descent Learns State Equations with Nonlinear Activations


Sep 09, 2018
Samet Oymak

Figure 1 for Stochastic Gradient Descent Learns State Equations with Nonlinear Activations
Figure 2 for Stochastic Gradient Descent Learns State Equations with Nonlinear Activations
* 23 pages, 4 figures 
  Access Paper or Ask Questions

High Dimensional Data Enrichment: Interpretable, Fast, and Data-Efficient


Jun 15, 2018
Amir Asiaee, Samet Oymak, Kevin R. Coombes, Arindam Banerjee

Figure 1 for High Dimensional Data Enrichment: Interpretable, Fast, and Data-Efficient
Figure 2 for High Dimensional Data Enrichment: Interpretable, Fast, and Data-Efficient
Figure 3 for High Dimensional Data Enrichment: Interpretable, Fast, and Data-Efficient

  Access Paper or Ask Questions

Non-asymptotic Identification of LTI Systems from a Single Trajectory


Jun 14, 2018
Samet Oymak, Necmiye Ozay

Figure 1 for Non-asymptotic Identification of LTI Systems from a Single Trajectory
Figure 2 for Non-asymptotic Identification of LTI Systems from a Single Trajectory
* 26 pages, 8 figures 
  Access Paper or Ask Questions

Learning Compact Neural Networks with Regularization


Jun 06, 2018
Samet Oymak

Figure 1 for Learning Compact Neural Networks with Regularization
Figure 2 for Learning Compact Neural Networks with Regularization
Figure 3 for Learning Compact Neural Networks with Regularization
Figure 4 for Learning Compact Neural Networks with Regularization
* ICML 2018, 46 pages, 11 figures 
  Access Paper or Ask Questions

End-to-end Learning of a Convolutional Neural Network via Deep Tensor Decomposition


May 16, 2018
Samet Oymak, Mahdi Soltanolkotabi

Figure 1 for End-to-end Learning of a Convolutional Neural Network via Deep Tensor Decomposition
Figure 2 for End-to-end Learning of a Convolutional Neural Network via Deep Tensor Decomposition
Figure 3 for End-to-end Learning of a Convolutional Neural Network via Deep Tensor Decomposition
Figure 4 for End-to-end Learning of a Convolutional Neural Network via Deep Tensor Decomposition
* 29 pages, 12 figures 
  Access Paper or Ask Questions

Universality laws for randomized dimension reduction, with applications


Sep 17, 2017
Samet Oymak, Joel A. Tropp

Figure 1 for Universality laws for randomized dimension reduction, with applications
Figure 2 for Universality laws for randomized dimension reduction, with applications
Figure 3 for Universality laws for randomized dimension reduction, with applications
Figure 4 for Universality laws for randomized dimension reduction, with applications
* v2 and v3 with technical corrections. Code for reproducing figures available at http://users.cms.caltech.edu/~jtropp/ 
  Access Paper or Ask Questions

Learning Feature Nonlinearities with Non-Convex Regularized Binned Regression


May 20, 2017
Samet Oymak, Mehrdad Mahdavi, Jiasi Chen

Figure 1 for Learning Feature Nonlinearities with Non-Convex Regularized Binned Regression
Figure 2 for Learning Feature Nonlinearities with Non-Convex Regularized Binned Regression
Figure 3 for Learning Feature Nonlinearities with Non-Convex Regularized Binned Regression
* 22 pages, 7 figures 
  Access Paper or Ask Questions

Fast and Reliable Parameter Estimation from Nonlinear Observations


Oct 23, 2016
Samet Oymak, Mahdi Soltanolkotabi

Figure 1 for Fast and Reliable Parameter Estimation from Nonlinear Observations
Figure 2 for Fast and Reliable Parameter Estimation from Nonlinear Observations
* 23 pages, 4 figures 
  Access Paper or Ask Questions