| 2026 | ISIT | An Information-Theoretic Perspective on LLM Tokenizers. | Mete Erdogan, Abhiram Rao Gorle, Shubham Chandak, Mert Pilanci, Tsachy Weissman |
| 2025 | ICASSP | ConvexECG: Lightweight and Explainable Neural Networks for Personalized, Continuous Cardiac Monitoring. | Rayan Ansari, John Cao, Sabyasachi Bandyopadhyay, Sanjiv M. Narayan, Albert J. Rogers, Mert Pilanci |
| 2025 | ICASSP | Spectral-Aware Low-Rank Adaptation for Speaker Verification. | Zhe Li, Man-Wai Mak, Mert Pilanci, Hung-yi Lee, Helen Meng |
| 2025 | ICASSP | Adaptive Large Language Models via Attention Shortcuts. | Prateek Verma, Mert Pilanci |
| 2025 | ICASSP | Subtractive Training for Music Stem Insertion Using Latent Diffusion Models. | Ivan Villa-Renteria, Mason Long Wang, Zachary Shah, Zhe Li, Soohyun Kim, Neelesh Ramachandran, Mert Pilanci |
| 2025 | ICLR | Exploring The Loss Landscape Of Regularized Neural Networks Via Convex Duality. | Sungyoon Kim, Aaron Mishkin, Mert Pilanci |
| 2025 | ICLR | Newton Meets Marchenko-Pastur: Massively Parallel Second-Order Optimization with Hessian Sketching and Debiasing. | Elad Romanov, Fangzhao Zhang, Mert Pilanci |
| 2025 | ICML | Geometric Algebra Planes: Convex Implicit Neural Volumes. | Irmak Sivgin, Sara Fridovich-Keil, Gordon Wetzstein, Mert Pilanci |
| 2025 | ICML | Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes. | Erica Zhang, Fangzhao Zhang, Mert Pilanci |
| 2025 | Interspeech | Disentangling Speaker and Content in Pre-trained Speech Models with Latent Diffusion for Robust Speaker Verification. | Zhe Li, Man-Wai Mak, Jen-Tzung Chien, Mert Pilanci, Zezhong Jin, Helen Meng |
| 2024 | ICLR | Scaling Convex Neural Networks with Burer-Monteiro Factorization. | Arda Sahiner, Tolga Ergen, Batu Ozturkler, John M. Pauly, Morteza Mardani, Mert Pilanci |
| 2024 | ICML | Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time. | Sungyoon Kim, Mert Pilanci |
| 2024 | ICML | Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models. | Fangzhao Zhang, Mert Pilanci |
| 2023 | ICASSP | Convex Optimization of Deep Polynomial and ReLU Activation Neural Networks. | Burak Bartan, Mert Pilanci |
| 2023 | ICASSP | Low Precision Representations for High Dimensional Models. | Rajarshi Saha, Mert Pilanci, Andrea J. Goldsmith |
| 2023 | ICLR | Globally Optimal Training of Neural Networks with Threshold Activation Functions. | Tolga Ergen, Halil Ibrahim Gulluk, Jonathan Lacotte, Mert Pilanci |
| 2023 | ICLR | Parallel Deep Neural Networks Have Zero Duality Gap. | Yifei Wang, Tolga Ergen, Mert Pilanci |
| 2023 | ICML | Optimal Sets and Solution Paths of ReLU Networks. | Aaron Mishkin, Mert Pilanci |
| 2023 | ICML | Optimal Shrinkage for Distributed Second-Order Optimization. | Fangzhao Zhang, Mert Pilanci |
| 2022 | AISTATS | Approximate Function Evaluation via Multi-Armed Bandits. | Tavor Z. Baharav, Gary Cheng, Mert Pilanci, David Tse |
| 2022 | ICLR | Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit Regularization. | Tolga Ergen, Arda Sahiner, Batu Ozturkler, John M. Pauly, Morteza Mardani, Mert Pilanci |
| 2022 | ICLR | Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions. | Arda Sahiner, Tolga Ergen, Batu Ozturkler, Burak Bartan, John M. Pauly, Morteza Mardani, Mert Pilanci |
| 2022 | ICLR | The Hidden Convex Optimization Landscape of Regularized Two-Layer ReLU Networks: an Exact Characterization of Optimal Solutions. | Yifei Wang, Jonathan Lacotte, Mert Pilanci |
| 2022 | ICLR | The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program. | Yifei Wang, Mert Pilanci |
| 2022 | ICML | Neural Fisher Discriminant Analysis: Optimal Neural Network Embeddings in Polynomial Time. | Burak Bartan, Mert Pilanci |
| 2022 | ICML | Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions. | Aaron Mishkin, Arda Sahiner, Mert Pilanci |
| 2022 | ICML | Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers. | Arda Sahiner, Tolga Ergen, Batu Ozturkler, John M. Pauly, Morteza Mardani, Mert Pilanci |
| 2022 | ISIT | Orthonormal Sketches for Secure Coded Regression. | Neophytos Charalambides, Hessam Mahdavifar, Mert Pilanci, Alfred O. Hero III |
| 2022 | MICCAI | Scale-Equivariant Unrolled Neural Networks for Data-Efficient Accelerated MRI Reconstruction. | Beliz Gunel, Arda Sahiner, Arjun D. Desai, Akshay S. Chaudhari, Shreyas Vasanawala, Mert Pilanci, John M. Pauly |
| 2021 | ICASSP | Approximate Weighted C R Coded Matrix Multiplication. | Neophytos Charalambides, Mert Pilanci, Alfred O. Hero III |
| 2021 | ICASSP | Convex Neural Autoregressive Models: Towards Tractable, Expressive, and Theoretically-Backed Models for Sequential Forecasting and Generation. | Vikul Gupta, Burak Bartan, Tolga Ergen, Mert Pilanci |
| 2021 | ICLR | Implicit Convex Regularizers of CNN Architectures: Convex Optimization of Two- and Three-Layer Networks in Polynomial Time. | Tolga Ergen, Mert Pilanci |
| 2021 | ICLR | Vector-output ReLU Neural Network Problems are Copositive Programs: Convex Analysis of Two Layer Networks and Polynomial-time Algorithms. | Arda Sahiner, Tolga Ergen, John M. Pauly, Mert Pilanci |
| 2021 | ICLR | Convex Regularization behind Neural Reconstruction. | Arda Sahiner, Morteza Mardani, Batu Ozturkler, Mert Pilanci, John M. Pauly |
| 2021 | ICML | Training Quantized Neural Networks to Global Optimality via Semidefinite Programming. | Burak Bartan, Mert Pilanci |
| 2021 | ICML | Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs. | Tolga Ergen, Mert Pilanci |
| 2021 | ICML | Revealing the Structure of Deep Neural Networks via Convex Duality. | Tolga Ergen, Mert Pilanci |
| 2021 | ICML | Adaptive Newton Sketch: Linear-time Optimization with Quadratic Convergence and Effective Hessian Dimensionality. | Jonathan Lacotte, Yifei Wang, Mert Pilanci |
| 2020 | ACSSC | Separating the Effects of Batch Normalization on CNN Training Speed and Stability Using Classical Adaptive Filter Theory. | Elaina Chai, Mert Pilanci, Boris Murmann |
| 2020 | AISTATS | Convex Geometry of Two-Layer ReLU Networks: Implicit Autoencoding and Interpretable Models. | Tolga Ergen, Mert Pilanci |
| 2020 | ICASSP | Weighted Gradient Coding with Leverage Score Sampling. | Neophytos Charalambides, Mert Pilanci, Alfred O. Hero III |
| 2020 | ICML | Optimal Randomized First-Order Methods for Least-Squares Problems. | Jonathan Lacotte, Mert Pilanci |
| 2020 | ICML | Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-layer Networks. | Mert Pilanci, Tolga Ergen |
| 2019 | ICASSP | Convex Relaxations of Convolutional Neural Nets. | Burak Bartan, Mert Pilanci |
| 2019 | ICASSP | Iterative Hessian Sketch with Momentum. | Ibrahim Kurban zaslan, Mert Pilanci, Orhan Arikan |
| 2014 | ISIT | Randomized sketches of convex programs with sharp guarantees. | Mert Pilanci, Martin J. Wainwright |
| 2012 | ICASSP | Expectation maximization based matching pursuit. | Ali Cafer Grbz, Mert Pilanci, Orhan Arikan |
| 2011 | ICASSP | Recovery of sparse perturbations in Least Squares problems. | Mert Pilanci, Orhan Arikan |
| 2009 | ICASSP | Structured least squares with bounded data uncertainties. | Mert Pilanci, Orhan Arikan, Barlas Oguz, Mustafa . Pinar |