Article

Move Quality Beyond Arena:　Pure Distillation for Small Go Networks

2026-05-19

Abstract excerpt

<title>Abstract</title> <p>The AlphaZero paradigm dominates computer Go research but is poorly suited to the compute budget available to individual researchers, where 7M-parameter networks trained on a single GPU reliably plateau after a small number of self-play generations. We study an alternative: pure knowledge distillation from a stronger existing engine (KataGo b18c384) into a compact 7M-parameter student,...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 4e2e8f96-7785-58e0-a7e3-18b8de1714d8
DOI: 10.21203/rs.3.rs-9749016/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Move Quality Beyond Arena: Pure Distillation for Small Go NetworksDOI 10.21203/rs.3.rs-9749016/v1Read

PhasePilot: Auditing and steering phase boundaries in budgeted in-context reasoningSemantic proximity Read

Why Compression Creates Intelligence: The Architecture of Experience in Large ModelsSemantic proximity Read

When the Device Decides: Calibration-Conditioned Suitability Estimation for Hybrid QAOA–Classical Max-Cut PipelinesSemantic proximity Read

WITHDRAWN: The Physics of Thought: Reasoning as Thermodynamic Relaxation in Generative ModelsSemantic proximity Read

Inductive Algebraic Resonance Memory for Attention-Free Language ModellingSemantic proximity Read

Epistemic Bridge Protocol: Regulating Epistemic Commitment in Probabilistic Generative AgentsSemantic proximity Read

Execution Grounded Multiagent Systems for Reliable Backend Code Generation with Large Language Models'Semantic proximity Read

A Hybrid Quantum-Classical Framework for Adaptive AI via Nonlinear Self-ReferenceSemantic proximity Read

Competitive, Cooperative, and Everything In-Between: The Janus Protocol for Strategy-Infused Language ModelsSemantic proximity Read

Protocol-Dependent Resolution in Finite-Sample Model SelectionSemantic proximity Read

RLHF-Aligned Open LLMs: A Comparative SurveySemantic proximity Read

Resource-Aware Memory Lifecycle Management for Long-Term RAG Inference with Compact Language ModelsSemantic proximity Read