Research map / Learning theory and algorithms / Prediction and decision losses
Generalizing GANs: A Turing Perspective
Roderich Gross, Yue Gu, Wei Li, Melvin Gauci
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 |
|---|---|---|---|
| allow discriminator to interact (control stimulus) rather than observe passively (ablation) | Turing Learning for stochastic PFSM agent inference · Case Study 1 | accuracy of inferred model parameters | Improved |
| allow discriminator to control robot movements rather than observe passively (ablation) | Turing Learning for e-puck sensor configuration inference · Case Study 2 | accuracy of inferred sensor orientations | Improved |
| allow discriminator to control robot movements rather than observe passively (ablation) | Turing Learning for e-puck sensor configuration inference · Case Study 2 | accuracy of inferred sensor displacements | No clear effect |
| discriminator control outputs ignored in replay (open-loop) versus closed-loop control (ablation) | Case Study 2 discriminator · Case Study 2 closed-loop validation | correct judgment rate: 69.45% to 58.60% | Hurt |
| discriminator interaction via closed-loop control of stimulus/movements | Turing Learning across both case studies · Case Studies 1 and 2 | accuracy of models | Improved |
Closest papers by meaning
- A Neural Tangent Kernel Perspective of GANs (ICML 2022 · similarity 0.87)
- Are GANs Created Equal? A Large-Scale Study (NeurIPS 2018 · similarity 0.86)
- Improved Techniques for Training GANs (NeurIPS 2016 · similarity 0.86)
- Rectifying GAN Gradient Supervision Via Score Functions (TPAMI 2026 · similarity 0.85)
- Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step (ICLR 2018 · similarity 0.85)
- Diffusing States and Matching Scores: A New Framework for Imitation Learning (ICLR 2025 · similarity 0.85)
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.
