default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDMert Pilanci
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[j20]Neophytos Charalambides
, Hessam Mahdavifar, Mert Pilanci, Alfred O. Hero III:
Iterative Sketching for Secure Coded Regression. IEEE J. Sel. Areas Inf. Theory 5: 148-161 (2024)- [j19]Yifei Wang, Peng Chen, Mert Pilanci, Wuchen Li:
Optimal Neural Network Approximation of Wasserstein Gradient Direction via Convex Optimization. SIAM J. Math. Data Sci. 6(4): 978-999 (2024) - [j18]Neophytos Charalambides, Mert Pilanci, Alfred O. Hero III:
Gradient Coding With Iterative Block Leverage Score Sampling. IEEE Trans. Inf. Theory 70(9): 6639-6664 (2024) - [j17]Yifei Wang, Mert Pilanci:
Correction to: Sketching the Krylov subspace: faster computation of the entire ridge regularization path. J. Supercomput. 80(1): 1366 (2024) - [c56]Emi Zeger, Nicholas Bambos, Mert Pilanci:
Power-Managed Data Centers for Sustainable Computing. ICC 2024: 2833-2839 - [c55]Arda Sahiner, Tolga Ergen, Batu Ozturkler, John M. Pauly, Morteza Mardani, Mert Pilanci:
Scaling Convex Neural Networks with Burer-Monteiro Factorization. ICLR 2024 - [c54]Sungyoon Kim, Mert Pilanci:
Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time. ICML 2024 - [c53]Fangzhao Zhang, Mert Pilanci:
Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models. ICML 2024 - [i87]Alexandros E. Tzikas, Licio Romao, Mert Pilanci, Alessandro Abate, Mykel J. Kochenderfer:
Distributed Markov Chain Monte Carlo Sampling based on the Alternating Direction Method of Multipliers. CoRR abs/2401.15838 (2024) - [i86]Fangzhao Zhang, Mert Pilanci:
Analyzing Neural Network-Based Generative Diffusion Models through Convex Optimization. CoRR abs/2402.01965 (2024) - [i85]Fangzhao Zhang, Mert Pilanci:
Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models. CoRR abs/2402.02347 (2024) - [i84]Sungyoon Kim, Mert Pilanci:
Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time. CoRR abs/2402.03625 (2024) - [i83]Soheil Hor, Ying Qian, Mert Pilanci, Amin Arbabian:
Adaptive Inference: Theoretical Limits and Unexplored Opportunities. CoRR abs/2402.04359 (2024) - [i82]Emi Zeger, Yifei Wang, Aaron Mishkin, Tolga Ergen, Emmanuel J. Candès, Mert Pilanci:
A Library of Mirrors: Deep Neural Nets in Low Dimensions are Convex Lasso Models with Reflection Features. CoRR abs/2403.01046 (2024) - [i81]Aaron Mishkin, Mert Pilanci, Mark Schmidt:
Faster Convergence of Stochastic Accelerated Gradient Descent under Interpolation. CoRR abs/2404.02378 (2024) - [i80]Fangzhao Zhang, Mert Pilanci:
Spectral Adapter: Fine-Tuning in Spectral Space. CoRR abs/2405.13952 (2024) - [i79]Daniel Kuelbs, Sanjay Lall, Mert Pilanci:
Adversarial Training of Two-Layer Polynomial and ReLU Activation Networks via Convex Optimization. CoRR abs/2405.14033 (2024) - [i78]Rajarshi Saha, Naomi Sagan, Varun Srivastava, Andrea J. Goldsmith, Mert Pilanci:
Compressing Large Language Models using Low Rank and Low Precision Decomposition. CoRR abs/2405.18886 (2024) - [i77]Yifei Wang, Sungyoon Kim, Paul Chu, Indu Subramaniam, Mert Pilanci:
Randomized Geometric Algebra Methods for Convex Neural Networks. CoRR abs/2406.02806 (2024) - [i76]Emil Biju, Anirudh Sriram, Mert Pilanci:
AdaPTwin: Low-Cost Adaptive Compression of Product Twins in Transformers. CoRR abs/2406.08904 (2024) - [i75]Prateek Verma, Mert Pilanci:
Towards Signal Processing In Large Language Models. CoRR abs/2406.10254 (2024) - [i74]Ivan Villa-Renteria, Mason L. Wang, Zachary Shah, Zhe Li, Soohyun Kim, Neelesh Ramachandran, Mert Pilanci:
Subtractive Training for Music Stem Insertion using Latent Diffusion Models. CoRR abs/2406.19328 (2024) - [i73]Prateek Verma, Mert Pilanci:
Adaptive Large Language Models By Layerwise Attention Shortcuts. CoRR abs/2409.10870 (2024) - [i72]Rayan Ansari, John Cao, Sabyasachi Bandyopadhyay, Sanjiv M. Narayan, Albert J. Rogers, Mert Pilanci:
ConvexECG: Lightweight and Explainable Neural Networks for Personalized, Continuous Cardiac Monitoring. CoRR abs/2409.12493 (2024) - [i71]Erica Zhang, Fangzhao Zhang, Mert Pilanci:
Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes. CoRR abs/2410.02145 (2024) - 2023
- [j16]Burak Bartan, Mert Pilanci:
Randomized Polar Codes for Anytime Distributed Machine Learning. IEEE J. Sel. Areas Inf. Theory 4: 393-404 (2023) - [j15]Neophytos Charalambides, Mert Pilanci, Alfred O. Hero III:
Securely Aggregated Coded Matrix Inversion. IEEE J. Sel. Areas Inf. Theory 4: 405-419 (2023) - [j14]Burak Bartan, Mert Pilanci:
Distributed Sketching for Randomized Optimization: Exact Characterization, Concentration, and Lower Bounds. IEEE Trans. Inf. Theory 69(6): 3850-3879 (2023) - [j13]Yifei Wang, Mert Pilanci:
Sketching the Krylov subspace: faster computation of the entire ridge regularization path. J. Supercomput. 79(16): 18748-18776 (2023) - [c52]Burak Bartan, Mert Pilanci:
Convex Optimization of Deep Polynomial and ReLU Activation Neural Networks. ICASSP 2023: 1-5 - [c51]Rajarshi Saha, Mert Pilanci, Andrea J. Goldsmith:
Low Precision Representations for High Dimensional Models. ICASSP 2023: 1-5 - [c50]Tolga Ergen, Halil Ibrahim Gulluk, Jonathan Lacotte, Mert Pilanci:
Globally Optimal Training of Neural Networks with Threshold Activation Functions. ICLR 2023 - [c49]Yifei Wang, Tolga Ergen, Mert Pilanci:
Parallel Deep Neural Networks Have Zero Duality Gap. ICLR 2023 - [c48]Aaron Mishkin, Mert Pilanci:
Optimal Sets and Solution Paths of ReLU Networks. ICML 2023: 24888-24924 - [c47]Fangzhao Zhang, Mert Pilanci:
Optimal Shrinkage for Distributed Second-Order Optimization. ICML 2023: 41523-41549 - [c46]Rajat Vadiraj Dwaraknath, Tolga Ergen, Mert Pilanci:
Fixing the NTK: From Neural Network Linearizations to Exact Convex Programs. NeurIPS 2023 - [c45]Tolga Ergen, Mert Pilanci:
Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks. NeurIPS 2023 - [c44]Rajarshi Saha, Varun Srivastava, Mert Pilanci:
Matrix Compression via Randomized Low Rank and Low Precision Factorization. NeurIPS 2023 - [i70]Neophytos Charalambides, Mert Pilanci, Alfred O. Hero III:
Federated Coded Matrix Inversion. CoRR abs/2301.03539 (2023) - [i69]Les Atlas, Nicholas Rasmussen, Felix Schwock, Mert Pilanci:
Complex Clipping for Improved Generalization in Machine Learning. CoRR abs/2302.13527 (2023) - [i68]Tolga Ergen, Halil Ibrahim Gulluk, Jonathan Lacotte, Mert Pilanci:
Globally Optimal Training of Neural Networks with Threshold Activation Functions. CoRR abs/2303.03382 (2023) - [i67]Aaron Mishkin, Mert Pilanci:
Optimal Sets and Solution Paths of ReLU Networks. CoRR abs/2306.00119 (2023) - [i66]Neophytos Charalambides, Mert Pilanci, Alfred O. Hero III:
Gradient Coding through Iterative Block Leverage Score Sampling. CoRR abs/2308.03096 (2023) - [i65]Neophytos Charalambides, Hessam Mahdavifar, Mert Pilanci, Alfred O. Hero III:
Iterative Sketching for Secure Coded Regression. CoRR abs/2308.04185 (2023) - [i64]Burak Bartan, Mert Pilanci:
Randomized Polar Codes for Anytime Distributed Machine Learning. CoRR abs/2309.00682 (2023) - [i63]Rajat Vadiraj Dwaraknath, Tolga Ergen, Mert Pilanci:
Fixing the NTK: From Neural Network Linearizations to Exact Convex Programs. CoRR abs/2309.15096 (2023) - [i62]Mert Pilanci:
From Complexity to Clarity: Analytical Expressions of Deep Neural Network Weights via Clifford's Geometric Algebra and Convexity. CoRR abs/2309.16512 (2023) - [i61]Rajarshi Saha, Varun Srivastava, Mert Pilanci:
Matrix Compression via Randomized Low Rank and Low Precision Factorization. CoRR abs/2310.11028 (2023) - [i60]Yifei Wang, Mert Pilanci:
Polynomial-Time Solutions for ReLU Network Training: A Complexity Classification via Max-Cut and Zonotopes. CoRR abs/2311.10972 (2023) - [i59]Annesha Ghosh, Gordon Wetzstein, Mert Pilanci, Sara Fridovich-Keil:
Volumetric Reconstruction Resolves Off-Resonance Artifacts in Static and Dynamic PROPELLER MRI. CoRR abs/2311.13177 (2023) - [i58]Tolga Ergen, Mert Pilanci:
The Convex Landscape of Neural Networks: Characterizing Global Optima and Stationary Points via Lasso Models. CoRR abs/2312.12657 (2023) - 2022
- [j12]Rajarshi Saha, Mert Pilanci, Andrea J. Goldsmith:
Efficient Randomized Subspace Embeddings for Distributed Optimization Under a Communication Budget. IEEE J. Sel. Areas Inf. Theory 3(2): 183-196 (2022) - [j11]Soheil Hor, Mert Pilanci, Amin Arbabian:
A Data-Driven Waveform Adaptation Method for Mm-Wave Gait Classification at the Edge. IEEE Signal Process. Lett. 29: 26-30 (2022) - [j10]Mert Pilanci:
Computational Polarization: An Information-Theoretic Method for Resilient Computing. IEEE Trans. Inf. Theory 68(4): 2211-2238 (2022) - [j9]Jonathan Lacotte, Mert Pilanci:
Adaptive and Oblivious Randomized Subspace Methods for High-Dimensional Optimization: Sharp Analysis and Lower Bounds. IEEE Trans. Inf. Theory 68(5): 3281-3303 (2022) - [c43]Tavor Z. Baharav, Gary Cheng, Mert Pilanci, David Tse:
Approximate Function Evaluation via Multi-Armed Bandits. AISTATS 2022: 108-135 - [c42]Neophytos Charalambides, Mert Pilanci, Alfred O. Hero III:
Secure Linear MDS Coded Matrix Inversion. Allerton 2022: 1-8 - [c41]Tolga Ergen, Arda Sahiner, Batu Ozturkler, John M. Pauly, Morteza Mardani, Mert Pilanci:
Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit Regularization. ICLR 2022 - [c40]Arda Sahiner, Tolga Ergen, Batu Ozturkler, Burak Bartan, John M. Pauly, Morteza Mardani, Mert Pilanci:
Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions. ICLR 2022 - [c39]Yifei Wang, Jonathan Lacotte, Mert Pilanci:
The Hidden Convex Optimization Landscape of Regularized Two-Layer ReLU Networks: an Exact Characterization of Optimal Solutions. ICLR 2022 - [c38]Yifei Wang, Mert Pilanci:
The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program. ICLR 2022 - [c37]Burak Bartan, Mert Pilanci:
Neural Fisher Discriminant Analysis: Optimal Neural Network Embeddings in Polynomial Time. ICML 2022: 1647-1663 - [c36]Aaron Mishkin, Arda Sahiner, Mert Pilanci:
Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions. ICML 2022: 15770-15816 - [c35]Arda Sahiner, Tolga Ergen, Batu Ozturkler, John M. Pauly, Morteza Mardani, Mert Pilanci:
Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers. ICML 2022: 19050-19088 - [c34]Neophytos Charalambides, Hessam Mahdavifar, Mert Pilanci, Alfred O. Hero III:
Orthonormal Sketches for Secure Coded Regression. ISIT 2022: 826-831 - [c33]Beliz Gunel, Arda Sahiner, Arjun D. Desai, Akshay S. Chaudhari, Shreyas Vasanawala, Mert Pilanci, John M. Pauly:
Scale-Equivariant Unrolled Neural Networks for Data-Efficient Accelerated MRI Reconstruction. MICCAI (6) 2022: 737-747 - [c32]Shuyun Tang, Xinying Hu, Les Atlas, Amil Khanzada, Mert Pilanci:
Hierarchical Multi-modal Transformer for Automatic Detection of COVID-19. SPML 2022: 197-202 - [i57]Esin Darici, Nicholas Rasmussen, J. Jennifer Ranjani, Jaclyn Xiao, Gunvant Chaudhari, Akanksha Rajput, Praveen Govindan, Minami Yamaura, Laura Gomezjurado, Amil Khanzada, Mert Pilanci:
Using Deep Learning with Large Aggregated Datasets for COVID-19 Classification from Cough. CoRR abs/2201.01669 (2022) - [i56]Neophytos Charalambides, Hessam Mahdavifar, Mert Pilanci, Alfred O. Hero III:
Orthonormal Sketches for Secure Coded Regression}. CoRR abs/2201.08522 (2022) - [i55]Richard Swartzbaugh, Amil Khanzada, Praveen Govindan, Mert Pilanci, Ayomide Owoyemi, Les Atlas, Hugo Estrada, Richard Nall, Michael Lotito, Rich Falcone, J. Jennifer Ranjani:
Using a Novel COVID-19 Calculator to Measure Positive U.S. Socio-Economic Impact of a COVID-19 Pre-Screening Solution (AI/ML). CoRR abs/2201.11109 (2022) - [i54]Aaron Mishkin, Arda Sahiner, Mert Pilanci:
Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions. CoRR abs/2202.01331 (2022) - [i53]Rajarshi Saha, Mert Pilanci, Andrea J. Goldsmith:
Minimax Optimal Quantization of Linear Models: Information-Theoretic Limits and Efficient Algorithms. CoRR abs/2202.11277 (2022) - [i52]Burak Bartan, Mert Pilanci:
Distributed Sketching for Randomized Optimization: Exact Characterization, Concentration and Lower Bounds. CoRR abs/2203.09755 (2022) - [i51]Tavor Z. Baharav, Gary Cheng, Mert Pilanci, David Tse:
Approximate Function Evaluation via Multi-Armed Bandits. CoRR abs/2203.10124 (2022) - [i50]Beliz Gunel, Arda Sahiner, Arjun D. Desai, Akshay S. Chaudhari, Shreyas Vasanawala, Mert Pilanci, John M. Pauly:
Scale-Equivariant Unrolled Neural Networks for Data-Efficient Accelerated MRI Reconstruction. CoRR abs/2204.10436 (2022) - [i49]Arda Sahiner, Tolga Ergen, Batu Ozturkler, John M. Pauly, Morteza Mardani, Mert Pilanci:
Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers. CoRR abs/2205.08078 (2022) - [i48]Yifei Wang, Peng Chen, Mert Pilanci, Wuchen Li:
Optimal Neural Network Approximation of Wasserstein Gradient Direction via Convex Optimization. CoRR abs/2205.13098 (2022) - [i47]Neophytos Charalambides, Mert Pilanci, Alfred O. Hero III:
Secure Linear MDS Coded Matrix Inversion. CoRR abs/2207.06271 (2022) - [i46]Batu Ozturkler, Arda Sahiner, Tolga Ergen, Arjun D. Desai, Christopher M. Sandino, Shreyas Vasanawala, John M. Pauly, Morteza Mardani, Mert Pilanci:
GLEAM: Greedy Learning for Large-Scale Accelerated MRI Reconstruction. CoRR abs/2207.08393 (2022) - [i45]Yifei Wang, Yixuan Hua, Emmanuel J. Candès, Mert Pilanci:
ReLU Neural Networks Learn the Simplest Models: Neural Isometry and Exact Recovery. CoRR abs/2209.15265 (2022) - 2021
- [j8]Tolga Ergen, Mert Pilanci:
Convex Geometry and Duality of Over-parameterized Neural Networks. J. Mach. Learn. Res. 22: 212:1-212:63 (2021) - [c31]Lawrence H. Kim, Rahul Goel, Jia Liang, Mert Pilanci, Pablo E. Paredes:
Linear Predictive Coding for Acute Stress Prediction from Computer Mouse Movements. EMBC 2021: 7465-7469 - [c30]Vikul Gupta, Burak Bartan, Tolga Ergen, Mert Pilanci:
Convex Neural Autoregressive Models: Towards Tractable, Expressive, and Theoretically-Backed Models for Sequential Forecasting and Generation. ICASSP 2021: 3890-3894 - [c29]Neophytos Charalambides, Mert Pilanci, Alfred O. Hero III:
Approximate Weighted C R Coded Matrix Multiplication. ICASSP 2021: 5095-5099 - [c28]Tolga Ergen, Mert Pilanci:
Implicit Convex Regularizers of CNN Architectures: Convex Optimization of Two- and Three-Layer Networks in Polynomial Time. ICLR 2021 - [c27]Arda Sahiner, Tolga Ergen, John M. Pauly, Mert Pilanci:
Vector-output ReLU Neural Network Problems are Copositive Programs: Convex Analysis of Two Layer Networks and Polynomial-time Algorithms. ICLR 2021 - [c26]Arda Sahiner, Morteza Mardani, Batu Ozturkler, Mert Pilanci, John M. Pauly:
Convex Regularization behind Neural Reconstruction. ICLR 2021 - [c25]Burak Bartan, Mert Pilanci:
Training Quantized Neural Networks to Global Optimality via Semidefinite Programming. ICML 2021: 694-704 - [c24]Tolga Ergen, Mert Pilanci:
Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs. ICML 2021: 2993-3003 - [c23]Tolga Ergen, Mert Pilanci:
Revealing the Structure of Deep Neural Networks via Convex Duality. ICML 2021: 3004-3014 - [c22]Jonathan Lacotte, Yifei Wang, Mert Pilanci:
Adaptive Newton Sketch: Linear-time Optimization with Quadratic Convergence and Effective Hessian Dimensionality. ICML 2021: 5926-5936 - [c21]Michal Derezinski, Jonathan Lacotte, Mert Pilanci, Michael W. Mahoney:
Newton-LESS: Sparsification without Trade-offs for the Sketched Newton Update. NeurIPS 2021: 2835-2847 - [i44]Burak Bartan, Mert Pilanci:
Neural Spectrahedra and Semidefinite Lifts: Global Convex Optimization of Polynomial Activation Neural Networks in Fully Polynomial-Time. CoRR abs/2101.02429 (2021) - [i43]Tolga Ergen, Arda Sahiner, Batu Ozturkler, John M. Pauly, Morteza Mardani, Mert Pilanci:
Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit Regularization. CoRR abs/2103.01499 (2021) - [i42]Rajarshi Saha, Mert Pilanci, Andrea J. Goldsmith:
Distributed Learning and Democratic Embeddings: Polynomial-Time Source Coding Schemes Can Achieve Minimax Lower Bounds for Distributed Gradient Descent under Communication Constraints. CoRR abs/2103.07578 (2021) - [i41]Jonathan Lacotte, Mert Pilanci:
Fast Convex Quadratic Optimization Solvers with Adaptive Sketching-based Preconditioners. CoRR abs/2104.14101 (2021) - [i40]Burak Bartan, Mert Pilanci:
Training Quantized Neural Networks to Global Optimality via Semidefinite Programming. CoRR abs/2105.01420 (2021) - [i39]Jonathan Lacotte, Yifei Wang, Mert Pilanci:
Adaptive Newton Sketch: Linear-time Optimization with Quadratic Convergence and Effective Hessian Dimensionality. CoRR abs/2105.07291 (2021) - [i38]Arda Sahiner, Tolga Ergen, Batu Ozturkler, Burak Bartan, John M. Pauly, Morteza Mardani, Mert Pilanci:
Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions. CoRR abs/2107.05680 (2021) - [i37]Michal Derezinski, Jonathan Lacotte, Mert Pilanci, Michael W. Mahoney:
Newton-LESS: Sparsification without Trade-offs for the Sketched Newton Update. CoRR abs/2107.07480 (2021) - [i36]Mert Pilanci:
Computational Polarization: An Information-theoretic Method for Resilient Computing. CoRR abs/2109.03877 (2021) - [i35]Tolga Ergen, Mert Pilanci:
Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs. CoRR abs/2110.05518 (2021) - [i34]Yifei Wang, Tolga Ergen, Mert Pilanci:
Parallel Deep Neural Networks Have Zero Duality Gap. CoRR abs/2110.06482 (2021) - [i33]Yifei Wang, Mert Pilanci:
The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program. CoRR abs/2110.06488 (2021) - [i32]Tolga Ergen, Mert Pilanci:
Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks. CoRR abs/2110.09548 (2021) - 2020
- [j7]Srivatsan Sridhar, Mert Pilanci, Ayfer Özgür:
Lower Bounds and a Near-Optimal Shrinkage Estimator for Least Squares Using Random Projections. IEEE J. Sel. Areas Inf. Theory 1(3): 660-668 (2020) - [j6]Surin Ahn, Ayfer Özgür, Mert Pilanci:
Global Multiclass Classification and Dataset Construction via Heterogeneous Local Experts. IEEE J. Sel. Areas Inf. Theory 1(3): 870-883 (2020) - [c20]Elaina Chai, Mert Pilanci, Boris Murmann:
Separating the Effects of Batch Normalization on CNN Training Speed and Stability Using Classical Adaptive Filter Theory. ACSSC 2020: 1214-1221 - [c19]Tolga Ergen, Mert Pilanci:
Convex Geometry of Two-Layer ReLU Networks: Implicit Autoencoding and Interpretable Models. AISTATS 2020: 4024-4033 - [c18]Neophytos Charalambides, Mert Pilanci, Alfred O. Hero III:
Weighted Gradient Coding with Leverage Score Sampling. ICASSP 2020: 5215-5219 - [c17]Jonathan Lacotte, Mert Pilanci:
Optimal Randomized First-Order Methods for Least-Squares Problems. ICML 2020: 5587-5597 - [c16]Mert Pilanci, Tolga Ergen:
Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-layer Networks. ICML 2020: 7695-7705 - [c15]Michal Derezinski, Burak Bartan, Mert Pilanci, Michael W. Mahoney:
Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization. NeurIPS 2020 - [c14]Jonathan Lacotte, Sifan Liu, Edgar Dobriban, Mert Pilanci:
Optimal Iterative Sketching Methods with the Subsampled Randomized Hadamard Transform. NeurIPS 2020 - [c13]Jonathan Lacotte, Mert Pilanci:
Effective Dimension Adaptive Sketching Methods for Faster Regularized Least-Squares Optimization. NeurIPS 2020 - [i31]Jonathan Lacotte, Sifan Liu, Edgar Dobriban, Mert Pilanci:
Limiting Spectrum of Randomized Hadamard Transform and Optimal Iterative Sketching Methods. CoRR abs/2002.00864 (2020) - [i30]Alexandre d'Aspremont, Mert Pilanci:
Global Convergence of Frank Wolfe on One Hidden Layer Networks. CoRR abs/2002.02208 (2020) - [i29]Neophytos Charalambides, Mert Pilanci, Alfred O. Hero III:
Weighted Gradient Coding with Leverage Score Sampling. CoRR abs/2002.02291 (2020) - [i28]Burak Bartan, Mert Pilanci:
Distributed Sketching Methods for Privacy Preserving Regression. CoRR abs/2002.06538 (2020) - [i27]Burak Bartan, Mert Pilanci:
Distributed Averaging Methods for Randomized Second Order Optimization. CoRR abs/2002.06540 (2020) - [i26]Jonathan Lacotte, Mert Pilanci:
Optimal Randomized First-Order Methods for Least-Squares Problems. CoRR abs/2002.09488 (2020) - [i25]Tolga Ergen, Mert Pilanci:
Convex Duality of Deep Neural Networks. CoRR abs/2002.09773 (2020) - [i24]Mert Pilanci, Tolga Ergen:
Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-Layer Networks. CoRR abs/2002.10553 (2020) - [i23]Elaina Chai, Mert Pilanci, Boris Murmann:
Separating the Effects of Batch Normalization on CNN Training Speed and Stability Using Classical Adaptive Filter Theory. CoRR abs/2002.10674 (2020) - [i22]Tolga Ergen, Mert Pilanci:
Convex Geometry and Duality of Over-parameterized Neural Networks. CoRR abs/2002.11219 (2020) - [i21]Neophytos Charalambides, Mert Pilanci, Alfred O. Hero III:
Straggler Robust Distributed Matrix Inverse Approximation. CoRR abs/2003.02948 (2020) - [i20]Surin Ahn, Ayfer Özgür, Mert Pilanci:
Global Multiclass Classification from Heterogeneous Local Models. CoRR abs/2005.10848 (2020) - [i19]Jonathan Lacotte, Mert Pilanci:
Effective Dimension Adaptive Sketching Methods for Faster Regularized Least-Squares Optimization. CoRR abs/2006.05874 (2020) - [i18]Jonathan Lacotte, Mert Pilanci:
All Local Minima are Global for Two-Layer ReLU Neural Networks: The Hidden Convex Optimization Landscape. CoRR abs/2006.05900 (2020) - [i17]Srivatsan Sridhar, Mert Pilanci, Ayfer Özgür:
Lower Bounds and a Near-Optimal Shrinkage Estimator for Least Squares using Random Projections. CoRR abs/2006.08160 (2020) - [i16]Tolga Ergen, Mert Pilanci:
Training Convolutional ReLU Neural Networks in Polynomial Time: Exact Convex Optimization Formulations. CoRR abs/2006.14798 (2020) - [i15]Michal Derezinski, Burak Bartan, Mert Pilanci, Michael W. Mahoney:
Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization. CoRR abs/2007.01327 (2020) - [i14]Neophytos Charalambides, Mert Pilanci, Alfred O. Hero III:
Approximate Weighted CR Coded Matrix Multiplication. CoRR abs/2011.09709 (2020) - [i13]Arda Sahiner, Morteza Mardani, Batu Ozturkler, Mert Pilanci, John M. Pauly:
Convex Regularization Behind Neural Reconstruction. CoRR abs/2012.05169 (2020) - [i12]Jonathan Lacotte, Mert Pilanci:
Adaptive and Oblivious Randomized Subspace Methods for High-Dimensional Optimization: Sharp Analysis and Lower Bounds. CoRR abs/2012.07054 (2020) - [i11]Arda Sahiner, Tolga Ergen, John M. Pauly, Mert Pilanci:
Vector-output ReLU Neural Network Problems are Copositive Programs: Convex Analysis of Two Layer Networks and Polynomial-time Algorithms. CoRR abs/2012.13329 (2020)
2010 – 2019
- 2019
- [c12]Tolga Ergen, Mert Pilanci:
Convex Optimization for Shallow Neural Networks. Allerton 2019: 79-83 - [c11]Burak Bartan, Mert Pilanci:
Distributed Black-Box optimization via Error Correcting Codes. Allerton 2019: 246-252 - [c10]Burak Bartan, Mert Pilanci:
Straggler Resilient Serverless Computing Based on Polar Codes. Allerton 2019: 276-283 - [c9]Burak Bartan, Mert Pilanci:
Convex Relaxations of Convolutional Neural Nets. ICASSP 2019: 4928-4932 - [c8]Ibrahim Kurban Özaslan, Mert Pilanci, Orhan Arikan:
Iterative Hessian Sketch with Momentum. ICASSP 2019: 7470-7474 - [c7]Jonathan Lacotte, Mert Pilanci, Marco Pavone:
High-Dimensional Optimization in Adaptive Random Subspaces. NeurIPS 2019: 10846-10856 - [c6]Ibrahim Kurban Özaslan, Mert Pilanci, Orhan Arikan:
Fast and Robust Solution Techniques for Large Scale Linear System of Equations. SIU 2019: 1-4 - [i10]Burak Bartan, Mert Pilanci:
Convex Relaxations of Convolutional Neural Nets. CoRR abs/1901.00035 (2019) - [i9]Burak Bartan, Mert Pilanci:
Polar Coded Distributed Matrix Multiplication. CoRR abs/1901.06811 (2019) - [i8]Jonathan Lacotte, Mert Pilanci, Marco Pavone:
High-Dimensional Optimization in Adaptive Random Subspaces. CoRR abs/1906.11809 (2019) - [i7]Burak Bartan, Mert Pilanci:
Distributed Black-Box Optimization via Error Correcting Codes. CoRR abs/1907.05984 (2019) - [i6]Jonathan Lacotte, Mert Pilanci:
Faster Least Squares Optimization. CoRR abs/1911.02675 (2019) - [i5]Ibrahim Kurban Özaslan, Mert Pilanci, Orhan Arikan:
Regularized Momentum Iterative Hessian Sketch for Large Scale Linear System of Equations. CoRR abs/1912.03514 (2019) - 2017
- [j5]Mert Pilanci, Martin J. Wainwright:
Newton Sketch: A Near Linear-Time Optimization Algorithm with Linear-Quadratic Convergence. SIAM J. Optim. 27(1): 205-245 (2017) - 2016
- [b1]Mert Pilanci:
Fast Randomized Algorithms for Convex Optimization and Statistical Estimation. University of California, Berkeley, USA, 2016 - [j4]Mert Pilanci, Martin J. Wainwright:
Iterative Hessian Sketch: Fast and Accurate Solution Approximation for Constrained Least-Squares. J. Mach. Learn. Res. 17: 53:1-53:38 (2016) - 2015
- [j3]Mert Pilanci, Martin J. Wainwright, Laurent El Ghaoui:
Sparse learning via Boolean relaxations. Math. Program. 151(1): 63-87 (2015) - [j2]Mert Pilanci, Martin J. Wainwright:
Randomized Sketches of Convex Programs With Sharp Guarantees. IEEE Trans. Inf. Theory 61(9): 5096-5115 (2015) - [i4]Yun Yang, Mert Pilanci, Martin J. Wainwright:
Randomized sketches for kernels: Fast and optimal non-parametric regression. CoRR abs/1501.06195 (2015) - [i3]Mert Pilanci, Martin J. Wainwright:
Newton Sketch: A Linear-time Optimization Algorithm with Linear-Quadratic Convergence. CoRR abs/1505.02250 (2015) - 2014
- [c5]Mert Pilanci, Martin J. Wainwright:
Randomized sketches of convex programs with sharp guarantees. ISIT 2014: 921-925 - [i2]Mert Pilanci, Martin J. Wainwright:
Randomized Sketches of Convex Programs with Sharp Guarantees. CoRR abs/1404.7203 (2014) - [i1]Mert Pilanci, Martin J. Wainwright:
Iterative Hessian sketch: Fast and accurate solution approximation for constrained least-squares. CoRR abs/1411.0347 (2014) - 2012
- [c4]Ali Cafer Gürbüz, Mert Pilanci, Orhan Arikan:
Expectation maximization based matching pursuit. ICASSP 2012: 3313-3316 - [c3]Mert Pilanci, Laurent El Ghaoui, Venkat Chandrasekaran:
Recovery of Sparse Probability Measures via Convex Programming. NIPS 2012: 2429-2437 - 2011
- [c2]Mert Pilanci, Orhan Arikan:
Recovery of sparse perturbations in Least Squares problems. ICASSP 2011: 3912-3915 - 2010
- [j1]Mert Pilanci, Orhan Arikan, Mustafa Ç. Pinar:
Structured least squares problems and robust estimators. IEEE Trans. Signal Process. 58(5): 2453-2465 (2010)
2000 – 2009
- 2009
- [c1]Mert Pilanci, Orhan Arikan, Barlas Oguz, Mustafa Ç. Pinar:
Structured least squares with bounded data uncertainties. ICASSP 2009: 3261-3264
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-11-08 20:31 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
