Research map / Optimization / Optimizers
Factorization Ranking Model for Move Prediction in the Game of Go
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 FBT instead of LFR (k=10, S3) | Fsmall features · Go move prediction | accuracy: 31.94% -> 34.01% | Helped |
| use FBT instead of LFR (k=5, S1) | Fsmall features · Go move prediction | accuracy: 30.01% -> 32.56% | Helped |
| use FBT instead of LFR (k=10, S3) | Flarge features · Go move prediction | accuracy: 37.69% -> 38.75% | Helped |
| use FBT instead of LFR (k=5, S1) | Flarge features · Go move prediction | accuracy: 34.38% -> 35.83% | Helped |
| increase factorization dimension k from 5 to 10 | FBT · Go move prediction Fsmall S3 | accuracy: 33.46% -> 34.01% | Helped |
| increase factorization dimension k from 5 to 10 | LFR · Go move prediction Fsmall S3 | accuracy: 31.13% -> 31.94% | Helped |
| increase training set from S1 to S3 | FBT10 · Go move prediction Fsmall | accuracy: 32.82% -> 34.01% | Helped |
| increase training set from S1 to S3 | FBT10 · Go move prediction Flarge | accuracy: 35.96% -> 38.75% | Helped |
| add large patterns (Flarge instead of Fsmall) | FBT10 on S3 · Go move prediction | accuracy: 34.01% -> 38.75% | Helped |
| approximate gradient with 5 samples instead of full gradient (ablation) | FBT, k=5 · Go move prediction Fsmall S1 | accuracy: 32.56% -> 30.04% | Hurt |
| approximate gradient with 30 samples instead of full gradient (ablation) | FBT, k=5 · Go move prediction Fsmall S1 | accuracy: 32.56% -> 31.78 % | Hurt |
| approximate gradient with 30 samples instead of full gradient (ablation) | FBT, k=5 · Go move prediction Fsmall S3 | accuracy: 33.46% -> 33.12% | No clear effect |
Closest papers by meaning
- Where Will Players Move Next? Dynamic Graphs and Hierarchical Fusion for Movement Forecasting in Badminton (AAAI 2023 · similarity 0.83)
- An Analysis of Elo Rating Systems via Markov Chains (NeurIPS 2024 · similarity 0.81)
- The PokeAgent Challenge: Competitive and Long-Context Learning at Scale (NeurIPS 2026 · similarity 0.81)
- Active Ranking and Matchmaking, with Perfect Matchings (ICML 2024 · similarity 0.81)
- Implicit Search via Discrete Diffusion: A Study on Chess (ICLR 2025 · similarity 0.80)
- Foundations of the Theory of Performance-Based Ranking (CVPR 2025 · similarity 0.80)
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.