Tolga Ergen

CoRR, 2023

Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Fixing the NTK: From Neural Network Linearizations to Exact Convex Programs.

[BibT_eX]

[DOI]

Rajat Vadiraj Dwaraknath

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Parallel Deep Neural Networks Have Zero Duality Gap.

[BibT_eX]

[DOI]

Yifei Wang

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Globally Optimal Training of Neural Networks with Threshold Activation Functions.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Convexifying Transformers: Improving optimization and understanding of transformer networks.

[BibT_eX]

[DOI]

Behnam Neyshabur

Harsh Mehta

CoRR, 2022

GLEAM: Greedy Learning for Large-Scale Accelerated MRI Reconstruction.

[BibT_eX]

[DOI]

Christopher M. Sandino

CoRR, 2022

Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit Regularization.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Convex Geometry and Duality of Over-parameterized Neural Networks.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2021

Revealing the Structure of Deep Neural Networks via Convex Duality.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex Programs.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Vector-output ReLU Neural Network Problems are Copositive Programs: Convex Analysis of Two Layer Networks and Polynomial-time Algorithms.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Implicit Convex Regularizers of CNN Architectures: Convex Optimization of Two- and Three-Layer Networks in Polynomial Time.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Convex Neural Autoregressive Models: Towards Tractable, Expressive, and Theoretically-Backed Models for Sequential Forecasting and Generation.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Acoustics, 2021

2020

Energy-Efficient LSTM Networks for Online Learning.

[BibT_eX]

[DOI]

Ali H. Mirza

IEEE Trans. Neural Networks Learn. Syst., 2020

Unsupervised Anomaly Detection With LSTM Neural Networks.

[BibT_eX]

[DOI]

IEEE Trans. Neural Networks Learn. Syst., 2020

A novel distributed anomaly detection algorithm based on support vector machines.

[BibT_eX]

[DOI]

Digit. Signal Process., 2020

Training Convolutional ReLU Neural Networks in Polynomial Time: Exact Convex Optimization Formulations.

[BibT_eX]

[DOI]

CoRR, 2020

Convex Duality of Deep Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2020

Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-layer Networks.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

Convex Geometry of Two-Layer ReLU Networks: Implicit Autoencoding and Interpretable Models.

[BibT_eX]

[DOI]

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019

Team-optimal online estimation of dynamic parameters over distributed tree networks.

[BibT_eX]

[DOI]

Osman Fatih Kiliç

Muhammed O. Sayin

Signal Process., 2019

Convex Optimization for Shallow Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the 57th Annual Allerton Conference on Communication, 2019

2018

Online Training of LSTM Networks in Distributed Systems for Variable Length Data Sequences.

[BibT_eX]

[DOI]

IEEE Trans. Neural Networks Learn. Syst., 2018

Efficient Online Learning Algorithms Based on LSTM Neural Networks.

[BibT_eX]

[DOI]

IEEE Trans. Neural Networks Learn. Syst., 2018

Recurrent neural networks based online learning algorithms for distributed systems.

[BibT_eX]

[DOI]

Safa Onur Sahin

Proceedings of the 26th Signal Processing and Communications Applications Conference, 2018

A novel anomaly detection approach based on neural networks.

[BibT_eX]

[DOI]

Mine Kerpicci

Proceedings of the 26th Signal Processing and Communications Applications Conference, 2018

A highly efficient recurrent neural network architecture for data regression.

[BibT_eX]

[DOI]

Emir Ceyani

Proceedings of the 26th Signal Processing and Communications Applications Conference, 2018

2017

Unsupervised and Semi-supervised Anomaly Detection with LSTM Neural Networks.

[BibT_eX]

[DOI]

Ali Hassan Mirza

CoRR, 2017

An efficient bandit algorithm for general weight assignments.

[BibT_eX]

[DOI]

Kaan Gökcesu

Selami Çiftçi

Proceedings of the 25th Signal Processing and Communications Applications Conference, 2017

Online distributed nonlinear regression via neural networks.

[BibT_eX]

[DOI]

Proceedings of the 25th Signal Processing and Communications Applications Conference, 2017

Neural networks based online learning.

[BibT_eX]

[DOI]

Proceedings of the 25th Signal Processing and Communications Applications Conference, 2017

Novelty detection using soft partitioning and hierarchical models.

[BibT_eX]

[DOI]

Kaan Gökcesu

Mustafa Simsek