| 2025 | AAAI | On the Power of Convolution-Augmented Transformer. | Mingchen Li, Xuechen Zhang, Yixiao Huang, Samet Oymak |
| 2025 | AAAI | TimePFN: Effective Multivariate Time Series Forecasting with Synthetic Data. | Ege Onur Taga, Muhammed Emrullah Ildiz, Samet Oymak |
| 2025 | AISTATS | Provable Benefits of Task-Specific Prompts for In-context Learning. | Xiangyu Chang, Yingcong Li, Muti Kara, Samet Oymak, Amit Roy-Chowdhury |
| 2025 | CVPR | AdMiT: Adaptive Multi-Source Tuning in Dynamic Environments. | Xiangyu Chang, Fahim Faisal Niloy, Sk Miraj Ahmed, Srikanth V. Krishnamurthy, Basak Guler, Ananthram Swami, Samet Oymak, Amit K. Roy-Chowdhury |
| 2025 | ICLR | High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws. | Muhammed Emrullah Ildiz, Halil Alperen Gozeten, Ege Onur Taga, Marco Mondelli, Samet Oymak |
| 2025 | ICML | Test-Time Training Provably Improves Transformers as In-context Learners. | Halil Alperen Gozeten, Muhammed Emrullah Ildiz, Xuechen Zhang, Mahdi Soltanolkotabi, Marco Mondelli, Samet Oymak |
| 2025 | ICML | Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition. | Zheyang Xiong, Ziyang Cai, John Cooper, Albert Ge, Vasilis Papageorgiou, Zack Sifakis, Angeliki Giannou, Ziqian Lin, Liu Yang, Saurabh Agarwal, Grigorios Chrysos, Samet Oymak, Kangwook Lee, Dimitris Papailiopoulos |
| 2024 | AAAI | A Score-Based Deterministic Diffusion Algorithm with Smooth Scores for General Distributions. | Karthik Elamvazhuthi, Xuechen Zhang, Matthew Jacobs, Samet Oymak, Fabio Pasqualetti |
| 2024 | AAAI | Class-Attribute Priors: Adapting Optimization to Heterogeneity and Fairness Objective. | Xuechen Zhang, Mingchen Li, Jiasi Chen, Christos Thrampoulidis, Samet Oymak |
| 2024 | AISTATS | Understanding Inverse Scaling and Emergence in Multitask Representation Learning. | Muhammed Emrullah Ildiz, Zhe Zhao, Samet Oymak |
| 2024 | AISTATS | Mechanics of Next Token Prediction with Self-Attention. | Yingcong Li, Yixiao Huang, Muhammed Emrullah Ildiz, Ankit Singh Rawat, Samet Oymak |
| 2024 | ICML | From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers. | Muhammed Emrullah Ildiz, Yixiao Huang, Yingcong Li, Ankit Singh Rawat, Samet Oymak |
| 2024 | ICML | Can Mamba Learn How To Learn? A Comparative Study on In-Context Learning Tasks. | Jongho Park, Jaeseung Park, Zheyang Xiong, Nayoung Lee, Jaewoong Cho, Samet Oymak, Kangwook Lee, Dimitris Papailiopoulos |
| 2024 | WACV | Effective Restoration of Source Knowledge in Continual Test Time Adaptation. | Fahim Faisal Niloy, Sk Miraj Ahmed, Dripta S. Raychaudhuri, Samet Oymak, Amit K. Roy-Chowdhury |
| 2023 | AAAI | Provable Pathways: Learning Multiple Tasks over Multiple Paths. | Yingcong Li, Samet Oymak |
| 2023 | AAAI | Stochastic Contextual Bandits with Long Horizon Rewards. | Yuzhen Qin, Yingcong Li, Fabio Pasqualetti, Maryam Fazel, Samet Oymak |
| 2023 | ICASSP | On The Fairness of Multitask Representation Learning. | Yingcong Li, Samet Oymak |
| 2023 | ICML | Transformers as Algorithms: Generalization and Stability in In-context Learning. | Yingcong Li, Muhammed Emrullah Ildiz, Dimitris Papailiopoulos, Samet Oymak |
| 2023 | ICML | On the Role of Attention in Prompt-tuning. | Samet Oymak, Ankit Singh Rawat, Mahdi Soltanolkotabi, Christos Thrampoulidis |
| 2023 | SIGCOMM | Text-to-3D Generative AI on Mobile Devices: Measurements and Optimizations. | Xuechen Zhang, Zheng Li, Samet Oymak, Jiasi Chen |
| 2022 | ICML | FedNest: Federated Bilevel, Minimax, and Compositional Optimization. | Davoud Ataee Tarzanagh, Mingchen Li, Christos Thrampoulidis, Samet Oymak |
| 2021 | AAAI | Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks. | Xiangyu Chang, Yingcong Li, Samet Oymak, Christos Thrampoulidis |
| 2021 | AISTATS | A Theoretical Characterization of Semi-supervised Learning with Self-training for Gaussian Mixture Models. | Samet Oymak, Talha Cihad Gulcu |
| 2021 | CVPR | Unsupervised Multi-Source Domain Adaptation Without Access to Source Data. | Sk Miraj Ahmed, Dripta S. Raychaudhuri, Sujoy Paul, Samet Oymak, Amit K. Roy-Chowdhury |
| 2021 | ICASSP | On the Marginal Benefit of Active Learning: Does Self-Supervision Eat its Cake? | Yao-Chun Chan, Mingchen Li, Samet Oymak |
| 2021 | ICASSP | Sample Efficient Subspace-Based Representations for Nonlinear Meta-Learning. | Halil Ibrahim Gulluk, Yue Sun, Samet Oymak, Maryam Fazel |
| 2021 | ICML | Generalization Guarantees for Neural Architecture Search with Train-Validation Split. | Samet Oymak, Mingchen Li, Mahdi Soltanolkotabi |
| 2020 | AISTATS | Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networks. | Mingchen Li, Mahdi Soltanolkotabi, Samet Oymak |
| 2020 | CISS | Exploring the Role of Loss Functions in Multiclass Classification. | Ahmet Demirkaya, Jiasi Chen, Samet Oymak |
| 2020 | ICDCS | WOLT: Auto-Configuration of Integrated Enterprise PLC-WiFi Networks. | Hisham Alhulayyil, Kittipat Apicharttrisorn, Jiasi Chen, Karthikeyan Sundaresan, Samet Oymak, Srikanth V. Krishnamurthy |
| 2020 | KDD | Unsupervised Paraphrasing via Deep Reinforcement Learning. | A. B. Siddique, Samet Oymak, Vagelis Hristidis |
| 2019 | ACSSC | Generalization, Adaptation and Low-Rank Representation in Neural Networks. | Samet Oymak, Zalan Fabian, Mingchen Li, Mahdi Soltanolkotabi |
| 2019 | COLT | Stochastic Gradient Descent Learns State Equations with Nonlinear Activations. | Samet Oymak |
| 2019 | ICASSP | Exactly Decoding a Vector through Relu Activation. | Samet Oymak, M. Salman Asif |
| 2019 | ICDM | Matrix Profile XVIII: Time Series Mining in the Face of Fast Moving Streams using a Learned Approximate Matrix Profile. | Zachary Zimmerman, Nader Shakibay Senobari, Gareth J. Funning, Evangelos E. Papalexakis, Samet Oymak, Philip Brisk, Eamonn J. Keogh |
| 2019 | ICML | Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path? | Samet Oymak, Mahdi Soltanolkotabi |
| 2019 | ISIT | Learning Feature Nonlinearities with Regularized Binned Regression. | Samet Oymak, Mehrdad Mahdavi, Jiasi Chen |
| 2018 | ICML | Learning Compact Neural Networks with Regularization. | Samet Oymak |
| 2017 | ICASSP | Near-optimal sample complexity bounds for circulant binary embedding. | Samet Oymak, Christos Thrampoulidis, Babak Hassibi |
| 2015 | COLT | Regularized Linear Regression: A Precise Analysis of the Estimation Error. | Christos Thrampoulidis, Samet Oymak, Babak Hassibi |
| 2015 | ICASSP | The proportional mean decomposition: A bridge between the Gaussian and bernoulli ensembles. | Samet Oymak, Babak Hassibi |
| 2014 | ICASSP | Sharp performance bounds for graph clustering via convex optimization. | Ramya Korlakai Vinayak, Samet Oymak, Babak Hassibi |
| 2014 | ISIT | A case for orthogonal measurements in linear inverse problems. | Samet Oymak, Babak Hassibi |
| 2014 | ISIT | Simple error bounds for regularized noisy linear inverse problems. | Christos Thrampoulidis, Samet Oymak, Babak Hassibi |
| 2013 | ISIT | Sparse phase retrieval: Convex algorithms and limitations. | Kishore Jaganathan, Samet Oymak, Babak Hassibi |
| 2012 | ICASSP | Phase retrieval for sparse signals using rank minimization. | Kishore Jaganathan, Samet Oymak, Babak Hassibi |
| 2012 | ICASSP | A simpler approach to weighted ℓ1 minimization. | Anilesh K. Krishnaswamy, Samet Oymak, Babak Hassibi |
| 2012 | ICASSP | Deterministic phase guarantees for robust recovery in incoherent dictionaries. | Cheuk Ting Li, Samet Oymak, Babak Hassibi |
| 2012 | ISIT | Recovery of sparse 1-D signals from the magnitudes of their Fourier transform. | Kishore Jaganathan, Samet Oymak, Babak Hassibi |
| 2012 | ISIT | Recovery threshold for optimal weight ℓ1 minimization. | Samet Oymak, M. Amin Khajehnejad, Babak Hassibi |
| 2011 | ICASSP | Weighted compressed sensing and rank minimization. | Samet Oymak, M. Amin Khajehnejad, Babak Hassibi |
| 2011 | ICASSP | Improved thresholds for rank minimization. | Samet Oymak, M. Amin Khajehnejad, Babak Hassibi |
| 2011 | ISIT | Tight recovery thresholds and robustness analysis for nuclear norm minimization. | Samet Oymak, Babak Hassibi |
| 2011 | ISIT | Subspace expanders and matrix rank minimization. | Samet Oymak, M. Amin Khajehnejad, Babak Hassibi |
| 2011 | ISIT | A simplified approach to recovery conditions for low rank matrices. | Samet Oymak, Karthik Mohan, Maryam Fazel, Babak Hassibi |