Research map / Architectures and efficiency / RNNs and normalization
Globally Injective ReLU Networks
Michael Puthawala, Konik Kothari, Matti Lassas, Ivan Dokmanić, Maarten de Hoop
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| make DCGAN generator layers injective via filters [C; -s^2 C] | DCGAN generator · CelebA | W2^2 latent distance: 33.85 -> 18.59 | Improved |
| make DCGAN generator layers injective via filters [C; -s^2 C] | DCGAN generator · FFHQ | W2^2 latent distance: 19.63 -> 9.87 | Improved |
| make DCGAN generator layers injective via filters [C; -s^2 C] | DCGAN generator · CelebA | FID: 50.56 -> 39.33 | Improved |
| make DCGAN generator layers injective via filters [C; -s^2 C] | DCGAN generator · FFHQ | FID: 47.23 -> 61.22 | Hurt |
| make DCGAN generator layers injective via filters [C; -s^2 C] | DCGAN generator · CelebA | Inception Score: 2.22 -> 2.24 | No clear effect |
| make DCGAN generator layers injective via filters [C; -s^2 C] | DCGAN generator · FFHQ | Inception Score: 2.57 -> 2.56 | No clear effect |
Closest papers by meaning
- Invertibility of Convolutional Generative Networks from Partial Measurements (NeurIPS 2018 · similarity 0.88)
- Globally injective and bijective neural operators (NeurIPS 2023 · similarity 0.88)
- A Rescaling-Invariant Lipschitz Bound Based on Path-Metrics for Modern ReLU Network Parameterizations (ICML 2025 · similarity 0.87)
- Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training (ICML 2025 · similarity 0.87)
- Global Minimizers of $\ell^p$-Regularized Objectives Yield the Sparsest ReLU Neural Networks (NeurIPS 2025 · similarity 0.86)
- Expressivity of ReLU-Networks under Convex Relaxations (ICLR 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
