Process-Tensor Tomography of SGD: Measuring Non-Markovian Memory via Back-Flow of Distinguishability
Process-Tensor Tomography of SGD: Measuring Non-Markovian Memory via Back-Flow of Distinguishability explores A novel method to measure memory effects in SGD training by analyzing the non-Markovian back-flow of outcomes.. Commercial viability score: 2/10 in LLM Training.
BUILDER'S SANDBOX
Build This Paper
Use an AI coding agent to implement this research.
OpenAI CodexAI Agent
Lightweight coding agent in your terminal.
Claude CodeAI Agent
Agentic coding tool for terminal workflows.
AntiGravity IDEScaffolding
AI agent mindset installer and workflow scaffolder.
CursorIDE
AI-first code editor built on VS Code.
VS CodeIDE
Free, open-source editor by Microsoft.
Recommended Stack
Startup Essentials
Estimated $10K - $14K over 6-10 weeks.
See exactly what it costs to build this -- with 3 comparable funded startups.
7-day free trial. Cancel anytime.
Discover the researchers behind this paper and find similar experts.
7-day free trial. Cancel anytime.
Related Papers
- Prior WorkA Quantitative Characterization of Forgetting in Post-TrainingViability: 2.0
- Higher ViabilityThe Geometric Inductive Bias of Grokking: Bypassing Phase Transitions via Architectural TopologyViability: 5.0
- Higher ViabilityArchitectural Proprioception in State Space Models: Thermodynamic Training Induces Anticipatory Halt DetectionViability: 5.0
- Higher ViabilityTS-Memory: Plug-and-Play Memory for Time Series Foundation ModelsViability: 7.0
- Higher ViabilityDetecting and Mitigating Memorization in Diffusion Models through Anisotropy of the Log-Probability