Research map / Learning theory and algorithms / Prediction and decision losses
One Network Fits All? Modular versus Monolithic Task Formulations in Neural Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Increase the number of columns in the WHERE clause | Two-layer neural network for SQL-style aggregation · Penn World Table | Test R-squared: (93.31 ± 0.11) %; (93.01 ± 2.7)%; (91.86 ± 2.59) %; (94.84 ± 1.86) %; (92.51 ± 2.2) % | No clear effect |
| Increase the number of clusters | Single two-layer neural network on well-separated clusters · Synthetic binary classification on Gaussian clusters | Classification error | No clear effect |
| Increase the decision-tree threshold margin | Two-layer neural network learning polynomial functions at tree leaves · Synthetic decision-tree regression | Accuracy | Helped |
Closest papers by meaning
- Which Tasks Should Be Learned Together in Multi-task Learning? (ICML 2020 · similarity 0.90)
- Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks (ICML 2024 · similarity 0.88)
- PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning (CVPR 2018 · similarity 0.86)
- A New Neural Kernel Regime: The Inductive Bias of Multi-Task Learning (NeurIPS 2024 · similarity 0.85)
- Breaking Neural Network Scaling Laws with Modularity (ICLR 2025 · similarity 0.85)
- Amalgamating Multi-Task Models with Heterogeneous Architectures (AAAI 2024 · 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.