Lune

Profiles2020-2023

Tolga Ergen

Department of Electrical Engineering Stanford University Stanford

11Papers
1Last author
5Unique co-authors
6First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers11

  1. Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU NetworksAuthor 1 of 2NeurIPS 2023 · 21 citations
  2. Fixing the NTK: From Neural Network Linearizations to Exact Convex ProgramsAuthor 2 of 3NeurIPS 2023 · 1 citation
  3. Parallel Deep Neural Networks Have Zero Duality GapAuthor 2 of 3ICLR 2023 · 1 citation
  4. Globally Optimal Training of Neural Networks with Threshold Activation FunctionsAuthor 1 of 5ICLR 2023
  5. Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit RegularizationAuthor 1 of 6ICLR 2022 · 34 citations
  6. Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form SolutionsAuthor 2 of 7ICLR 2022 · 23 citations
  7. Revealing the Structure of Deep Neural Networks via Convex DualityAuthor 1 of 2ICML 2021 · 77 citations
  8. Vector-output ReLU Neural Network Problems are Copositive Programs: Convex Analysis of Two Layer Networks and Polynomial-time AlgorithmsAuthor 2 of 4ICLR 2021 · 45 citations
  9. Global Optimality Beyond Two Layers: Training Deep ReLU Networks via Convex ProgramsAuthor 1 of 2ICML 2021 · 35 citations
  10. Implicit Convex Regularizers of CNN Architectures: Convex Optimization of Two- and Three-Layer Networks in Polynomial TimeAuthor 1 of 2ICLR 2021 · 4 citations
  11. Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-layer NetworksAuthor 2 of 2ICML 2020 · 142 citations
Dusk over the sea between two cliffs drawn in fine vertical lines