Research map / Label-efficient and robust learning / Recognition and long-tail
Invariant Representations with Stochastically Quantized 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 |
|---|---|---|---|
| Use BinaryBernoulli instead of the vanilla classifier | Biased-MNIST classification · Biased-MNIST, ρ=0.995 | accuracy: 72.1 -> 90.64 | Helped |
| Use BinaryBernoulli instead of the vanilla classifier | Biased-MNIST classification · Biased-MNIST, ρ=0.990 | accuracy: 89.1 -> 96.02 | Helped |
| Use BinaryMI instead of the vanilla classifier | Biased-MNIST classification · Biased-MNIST, ρ=0.995 | accuracy: 72.1 -> 89.08 | Helped |
| Use BinaryMI instead of the vanilla classifier | Biased-MNIST classification · Biased-MNIST, ρ=0.990 | accuracy: 89.1 -> 88.54 | Hurt |
| Use a hybrid network rather than a fully binary-precision network (ablation) | Stochastically quantized neural networks · Fair classification experiments | accuracy/fairness tradeoff | Helped |
| Increase γ | BinaryBernoulli on COMPAS · COMPAS | 1-GPA: ρ=0.924 | Helped |
| Increase γ | BinaryBernoulli on COMPAS · COMPAS | AUC: ρ = -0.836 | Hurt |
| Increase γ | BinaryMI · Fairness datasets | 1-GPA: 0.781 | Helped |
| Increase γ | BinaryMI · Fairness datasets | AUC: -0.760 | Hurt |
Closest papers by meaning
- Invariant Representations without Adversarial Training (NeurIPS 2018 · similarity 0.87)
- Probabilistic Invariant Learning with Randomized Linear Classifiers (NeurIPS 2023 · similarity 0.86)
- On 1/n neural representation and robustness (NeurIPS 2020 · similarity 0.85)
- Connecting Jensen–Shannon and Kullback–Leibler Divergences: A New Bound for Representation Learning (NeurIPS 2025 · similarity 0.84)
- On Making $SE(2)$-Invariant Networks Optimal (NeurIPS 2026 · similarity 0.84)
- Training Binary Neural Networks via Gaussian Variational Inference and Low-Rank Semidefinite Programming (NeurIPS 2024 · similarity 0.83)
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.