| Newton sketch: A near linear-time optimization algorithm with linear-quadratic convergence M Pilanci, MJ Wainwright SIAM Journal on Optimization 27 (1), 205-245, 2017 | 417 | 2017 |
| Iterative Hessian sketch: Fast and accurate solution approximation for constrained least-squares M Pilanci, MJ Wainwright Journal of Machine Learning Research 17 (53), 1-38, 2016 | 267 | 2016 |
| Randomized sketches for kernels: Fast and optimal nonparametric regression Y Yang, M Pilanci, MJ Wainwright | 228 | 2017 |
| Randomized sketches of convex programs with sharp guarantees M Pilanci, MJ Wainwright IEEE Transactions on Information Theory 61 (9), 5096-5115, 2015 | 219 | 2015 |
| Neural networks are convex regularizers: Exact polynomial-time convex optimization formulations for two-layer networks M Pilanci, T Ergen International Conference on Machine Learning, 7695-7705, 2020 | 144 | 2020 |
| Sparse learning via Boolean relaxations M Pilanci, MJ Wainwright, L El Ghaoui Mathematical Programming 151 (1), 63-87, 2015 | 107 | 2015 |
| Revealing the structure of deep neural networks via convex duality T Ergen, M Pilanci International Conference on Machine Learning, 3004-3014, 2021 | 85 | 2021 |
| Convex geometry and duality of over-parameterized neural networks T Ergen, M Pilanci Journal of machine learning research 22 (212), 1-63, 2021 | 75 | 2021 |
| Recovery of sparse probability measures via convex programming M Pilanci, L Ghaoui, V Chandrasekaran Advances in Neural Information Processing Systems 25, 2012 | 68 | 2012 |
| The hidden convex optimization landscape of two-layer ReLU neural networks: An exact characterization of the optimal solutions Y Wang, J Lacotte, M Pilanci arXiv preprint arXiv:2006.05900, 2020 | 58 | 2020 |
| Implicit convex regularizers of cnn architectures: Convex optimization of two-and three-layer networks in polynomial time T Ergen, M Pilanci arXiv preprint arXiv:2006.14798, 2020 | 57 | 2020 |
| Vector-output relu neural network problems are copositive programs: Convex analysis of two layer networks and polynomial-time algorithms A Sahiner, T Ergen, J Pauly, M Pilanci arXiv preprint arXiv:2012.13329, 2020 | 52 | 2020 |
| Global optimality beyond two layers: Training deep relu networks via convex programs T Ergen, M Pilanci International Conference on Machine Learning, 2993-3003, 2021 | 49 | 2021 |
| Demystifying batch normalization in relu networks: Equivalent convex optimization models and implicit regularization T Ergen, A Sahiner, B Ozturkler, J Pauly, M Mardani, M Pilanci arXiv preprint arXiv:2103.01499, 2021 | 46 | 2021 |
| Compressing large language models using low rank and low precision decomposition R Saha, N Sagan, V Srivastava, A Goldsmith, M Pilanci Advances in Neural Information Processing Systems 37, 88981-89018, 2024 | 44 | 2024 |
| Unraveling attention via convex duality: Analysis and interpretations of vision transformers A Sahiner, T Ergen, B Ozturkler, J Pauly, M Mardani, M Pilanci International Conference on Machine Learning, 19050-19088, 2022 | 44 | 2022 |
| Fast convex optimization for two-layer relu networks: Equivalent model classes and cone decompositions A Mishkin, A Sahiner, M Pilanci International Conference on Machine Learning, 15770-15816, 2022 | 44 | 2022 |
| Riemannian preconditioned lora for fine-tuning foundation models F Zhang, M Pilanci arXiv preprint arXiv:2402.02347, 2024 | 43 | 2024 |
| Matrix compression via randomized low rank and low precision factorization R Saha, V Srivastava, M Pilanci Advances in Neural Information Processing Systems 36, 18828-18872, 2023 | 41 | 2023 |
| Newton-LESS: Sparsification without trade-offs for the sketched Newton update M Derezinski, J Lacotte, M Pilanci, MW Mahoney Advances in Neural Information Processing Systems 34, 2835-2847, 2021 | 41 | 2021 |
Tolga ErgenResearch Scientist, LG AI ResearchVerified email at stanford.edu
