Research map / Probabilistic and scientific modeling / Bayesian optimization
PROTES: Probabilistic Optimization with Tensor Sampling
Anastasia Batsheva, Andrei Chertkov, Gleb Ryzhakov, Ivan Oseledets
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 |
|---|---|---|---|
| Use PROTES instead of the strongest reported alternatives | discretized analytic functions P-01–P-10 · P-01–P-10 | minimum objective | No clear effect |
| Use PROTES instead of the strongest reported alternatives | QUBO benchmarks P-11–P-14 · P-11–P-14 | minimum objective | Improved |
| Use PROTES instead of the strongest reported alternatives | unconstrained optimal control · P-15–P-17 | minimum objective | Improved |
| Use PROTES rather than TTOpt | constrained optimal control · P-18 | minimum objective: 1.1e-02 vs 1.4e-02 | Hurt |
| Use PROTES instead of alternatives | constrained optimal control · P-19–P-20 | minimum objective | Improved |
| Use PROTES rather than baselines across repeated runs | binary knapsack P-14 · P-14, 10 runs | mean objective: -3095 vs -2992 | Improved |
| Use PROTES rather than Portfolio (BS-7) | binary knapsack P-14 · P-14, 10 runs | best objective: -3103 vs -3103 | No clear effect |
| Vary K, selected-candidate count k, and TT-rank R (ablation) | PROTES · P-01 and P-14 | optimization result | No clear effect |
| Use very small learning rates 0.005 or 0.01 (ablation) | PROTES · P-01 | optimization result | Hurt |
| Vary learning rate, gradient steps, and TT-rank (ablation) | PROTES · P-14 | relative error | Mixed |
Closest papers by meaning
- Combinatorial Bandit Bayesian Optimization for Tensor Outputs (ICLR 2026 · similarity 0.86)
- Monte Carlo Tree Descent for Black-Box Optimization (NeurIPS 2022 · similarity 0.85)
- ROOT: Rethinking Offline Optimization as Distributional Translation via Probabilistic Bridge (NeurIPS 2025 · similarity 0.85)
- Posterior Inference with Diffusion Models for High-dimensional Black-box Optimization (ICML 2025 · similarity 0.84)
- Batched Energy-Entropy acquisition for Bayesian Optimization (NeurIPS 2024 · similarity 0.84)
- Informed Initialization for Bayesian Optimization and Active Learning (NeurIPS 2025 · 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.
