Research map / Learning theory and algorithms / Sample complexity
Learning from Stochastically Revealed Preference
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 dimension from n=10 to n=25 | Algorithm 1 · Gaussian setting, uniform distribution (i) | predictive accuracy: 98.8% -> 59.9% | Hurt |
| increase dimension from n=10 to n=25 | Algorithm 1 · Gaussian setting, discrete distribution (ii) | predictive accuracy: 96.9% -> 56.9% | Hurt |
| increase dimension from n=10 to n=25 | Algorithm 1 · Gaussian setting, fixed-a distribution (iii) | predictive accuracy: 92.6% -> 68.5% | Hurt |
| increase dimension from n=10 to n=25 | Algorithm 2 · delta-corruption setting, uniform distribution (i) | predictive accuracy: 96.0% -> 55.7% | Hurt |
| increase dimension from n=10 to n=25 | Algorithm 2 · delta-corruption setting, discrete distribution (ii) | predictive accuracy: 97.6% -> 63.1% | Hurt |
| increase dimension from n=10 to n=25 | Algorithm 2 · delta-corruption setting, fixed-a distribution (iii) | predictive accuracy: 87.1% -> 58.7% | Hurt |
| increase dimension from n=3 to n=5 | Algorithm 1 · Gaussian setting, fixed-a distribution (iii) | predictive accuracy: 99.9% -> 94.8% | Hurt |
| increase dimension from n=5 to n=10 | Algorithm 2 · delta-corruption setting, fixed-a distribution (iii) | predictive accuracy: 98.7% -> 87.1% | Hurt |
| change distribution of (a,b) from uniform (i) to fixed-a (iii) at n=25 | Algorithm 1 · Gaussian setting | predictive accuracy: 59.9% -> 68.5% | Helped |
| change distribution of (a,b) from fixed-a (ii) to fixed-a (iii) at n=5 | Algorithm 2 · delta-corruption setting | predictive accuracy: 97.9% -> 98.7% | Mixed |
Closest papers by meaning
- Learning Utilities from Demonstrations in Markov Decision Processes (ICML 2025 · similarity 0.88)
- Multidimensional Bayesian Utility Maximization: Tight Approximations to Welfare (NeurIPS 2025 · similarity 0.87)
- Model Alignment as Prospect Theoretic Optimization (ICML 2024 · similarity 0.84)
- Enhancing Preference-based Linear Bandits via Human Response Time (NeurIPS 2024 · similarity 0.84)
- Regret Analysis of Repeated Delegated Choice (AAAI 2024 · similarity 0.84)
- Learning from negative feedback, or positive feedback or both (ICLR 2025 · similarity 0.84)
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.