Differences
This shows you the differences between two versions of the page.
| Both sides previous revisionPrevious revisionNext revision | Previous revision | ||
| projects:quantum:seqnn [2026/05/21 07:07] – [Short version] kymki | projects:quantum:seqnn [2026/05/21 08:45] (current) – [Introduction] kymki | ||
|---|---|---|---|
| Line 1: | Line 1: | ||
| - | ====== SEQNN Stage 5: Entangled Generative Estimation ====== | + | < |
| + | < | ||
| + | <meta charset=" | ||
| + | <meta name=" | ||
| + | < | ||
| + | < | ||
| + | /* Container for the entire Ramble Meter */ | ||
| + | .ramble-meter-container { | ||
| + | display: flex; | ||
| + | align-items: | ||
| + | justify-content: | ||
| + | margin: 20px 0; | ||
| + | } | ||
| - | //Exploratory research note. This work is being shaped toward a publishable paper claim, but the results described here should be read as "work under validation" | + | |
| + | | ||
| + | position: relative; | ||
| + | width: 200px; | ||
| + | height: 40px; /* Scaled down */ | ||
| + | background: linear-gradient(to right, green, yellow, orange, red); | ||
| + | border-radius: | ||
| + | overflow: hidden; | ||
| + | box-shadow: 0 2px 8px rgba(0, 0, 0, 0.3); | ||
| + | } | ||
| - | ===== Introduction ===== | + | /* Needle */ |
| + | .needle { | ||
| + | position: absolute; | ||
| + | top: 5px; /* Adjust for centering */ | ||
| + | left: 50%; /* Default position */ | ||
| + | width: 4px; /* Visible width */ | ||
| + | height: 30px; | ||
| + | background: black; | ||
| + | border-radius: | ||
| + | z-index: 2; | ||
| + | box-shadow: 0 0 10px rgba(0, 0, 0, 0.5); /* Glow effect */ | ||
| + | } | ||
| - | Kalman filters are fascinating. How can they be applied | + | /* Label in the middle of the meter */ |
| + | | ||
| + | position: absolute; | ||
| + | top: 50%; | ||
| + | left: 50%; | ||
| + | transform: translate(-50%, | ||
| + | font-family: | ||
| + | font-size: 12px; /* Adjusted for smaller size */ | ||
| + | font-weight: | ||
| + | color: #fff; | ||
| + | text-shadow: | ||
| + | z-index: 3; | ||
| + | } | ||
| + | |||
| + | /* Tooltip styling */ | ||
| + | .tooltip { | ||
| + | visibility: hidden; | ||
| + | width: 250px; | ||
| + | background-color: | ||
| + | color: #fff; | ||
| + | text-align: center; | ||
| + | padding: 10px; | ||
| + | border-radius: | ||
| + | position: absolute; | ||
| + | top: 50%; /* Vertically aligned */ | ||
| + | left: 110%; /* Position | ||
| + | transform: translateY(-50%); | ||
| + | font-size: 12px; | ||
| + | z-index: 10; | ||
| + | box-shadow: 0 2px 5px rgba(0, 0, 0, 0.3); | ||
| + | } | ||
| + | |||
| + | /* Show tooltip on hover */ | ||
| + | .ramble-meter: | ||
| + | visibility: visible; | ||
| + | } | ||
| + | |||
| + | /* Wrapper for positioning the tooltip and meter */ | ||
| + | .ramble-wrapper { | ||
| + | position: relative; | ||
| + | display: flex; | ||
| + | align-items: | ||
| + | } | ||
| + | </ | ||
| + | < | ||
| + | document.addEventListener("DOMContentLoaded", | ||
| + | const needle = document.querySelector(" | ||
| + | const rambleMeter = document.querySelector(" | ||
| + | const level = rambleMeter.getAttribute(" | ||
| + | needle.style.left = `${Math.min(Math.max(level, | ||
| + | }); | ||
| + | </ | ||
| + | </ | ||
| + | < | ||
| + | <!-- Ramble Meter --> | ||
| + | <div class=" | ||
| + | <div class=" | ||
| + | <div class=" | ||
| + | <div class=" | ||
| + | <div class=" | ||
| + | </ | ||
| + | <div class=" | ||
| + | </ | ||
| + | </ | ||
| + | </ | ||
| + | </ | ||
| + | |||
| + | |||
| + | ====== | ||
| + | |||
| + | // | ||
| + | |||
| + | ===== Introduction ===== | ||
| - | SEQNN, | + | Kalman filtering |
| - | The current work is near the end of Stage 5 in '' | + | SEQNN, |
| - | The current | + | The current estimator |
| ===== The idea ===== | ===== The idea ===== | ||
| Line 28: | Line 132: | ||
| * each node maintains both an estimate and an uncertainty. | * each node maintains both an estimate and an uncertainty. | ||
| - | The important difference is not only "which update rule is used." | + | The important difference is not only "which update rule is used." |
| - | ===== Roadmap position ===== | + | ===== Roadmap position |
| ^ Stage ^ Status ^ | ^ Stage ^ Status ^ | ||
| Line 40: | Line 144: | ||
| | Stage 6: augmented noise-state EKF | not started | | | Stage 6: augmented noise-state EKF | not started | | ||
| - | The practical position is this: the four-qubit overlapping '' | + | The four-qubit overlapping '' |
| ===== The generative formulation ===== | ===== The generative formulation ===== | ||
| Line 126: | Line 230: | ||
| $$ | $$ | ||
| - | In a supervised classifier this can look like a covariance-aware optimizer. In the generative experiments, | + | In a supervised classifier this can look like a covariance-aware optimizer. In the generative experiments, |
| ===== Model ladder ===== | ===== Model ladder ===== | ||
| - | The project | + | The project moved through increasingly demanding observation models. The key pattern is: do not add parameters, entanglement, |
| ^ Stage/model ^ Observation structure ^ What it tests ^ Claim status ^ | ^ Stage/model ^ Observation structure ^ What it tests ^ Claim status ^ | ||
| Line 139: | Line 243: | ||
| | Disjoint entangled '' | | Disjoint entangled '' | ||
| | Overlapping entangled '' | | Overlapping entangled '' | ||
| - | |||
| - | ===== Diagram: model progression ===== | ||
| - | |||
| - | < | ||
| - | <div style=" | ||
| - | <svg xmlns=" | ||
| - | < | ||
| - | <marker id=" | ||
| - | <path d=" | ||
| - | </ | ||
| - | </ | ||
| - | <rect x=" | ||
| - | <text x=" | ||
| - | <text x=" | ||
| - | <text x=" | ||
| - | <circle cx=" | ||
| - | <circle cx=" | ||
| - | <circle cx=" | ||
| - | |||
| - | <rect x=" | ||
| - | <text x=" | ||
| - | <text x=" | ||
| - | <text x=" | ||
| - | <path d=" | ||
| - | |||
| - | <rect x=" | ||
| - | <text x=" | ||
| - | <text x=" | ||
| - | <text x=" | ||
| - | <text x=" | ||
| - | |||
| - | <rect x=" | ||
| - | <text x=" | ||
| - | <text x=" | ||
| - | <text x=" | ||
| - | <line x1=" | ||
| - | <line x1=" | ||
| - | |||
| - | <rect x=" | ||
| - | <text x=" | ||
| - | <text x=" | ||
| - | <text x=" | ||
| - | <circle cx=" | ||
| - | <circle cx=" | ||
| - | <circle cx=" | ||
| - | <circle cx=" | ||
| - | <line x1=" | ||
| - | <line x1=" | ||
| - | <line x1=" | ||
| - | <text x=" | ||
| - | <text x=" | ||
| - | <text x=" | ||
| - | <text x=" | ||
| - | |||
| - | <line x1=" | ||
| - | <line x1=" | ||
| - | <line x1=" | ||
| - | <path d=" | ||
| - | <text x=" | ||
| - | </ | ||
| - | </ | ||
| - | </ | ||
| ===== The Stage 5 observation model ===== | ===== The Stage 5 observation model ===== | ||
| Line 262: | Line 304: | ||
| ===== Models compared in Stage 5 ===== | ===== Models compared in Stage 5 ===== | ||
| - | ^ Model ^ Role ^ State/ | + | ^ Model ^ Role ^ State/ |
| | Adam | optimizer baseline | point estimate, no posterior covariance | whether a standard adaptive optimizer tracks the same sampled streams well | | | Adam | optimizer baseline | point estimate, no posterior covariance | whether a standard adaptive optimizer tracks the same sampled streams well | | ||
| | Gradient descent | optimizer baseline | point estimate, no posterior covariance | whether a tuned first-order method is enough | | | Gradient descent | optimizer baseline | point estimate, no posterior covariance | whether a tuned first-order method is enough | | ||
| Line 363: | Line 405: | ||
| ===== What remains for the Stage 5 publication path ===== | ===== What remains for the Stage 5 publication path ===== | ||
| - | The remaining work is about strengthening the evidence | + | The remaining work is about strengthening the evidence, not changing the core idea. |
| - Decide whether to run a 50-seed sensitivity confirmation. | - Decide whether to run a 50-seed sensitivity confirmation. | ||
| Line 378: | Line 420: | ||
| * It helps show where distributed Fisher factors remain stable or attractive as the chain grows. | * It helps show where distributed Fisher factors remain stable or attractive as the chain grows. | ||
| - | ===== What we are not claiming | + | ===== What I am not claiming ===== |
| - | This is important for the eventual paper framing. | ||
| - | |||
| - | * Not a quantum advantage claim. | ||
| * Not a hardware claim; these are controlled generative simulations. | * Not a hardware claim; these are controlled generative simulations. | ||
| * Not an arbitrary-entangled-circuit claim. | * Not an arbitrary-entangled-circuit claim. | ||
| Line 390: | Line 429: | ||
| * Not a claim that every SEQNN variant works; the independent EKF is intentionally a negative control in Stage 5. | * Not a claim that every SEQNN variant works; the independent EKF is intentionally a negative control in Stage 5. | ||
| - | The narrower claim is stronger: | + | Rather: |
| > In an identifiable overlapping entangled generative circuit, a distributed SEQNN estimator using Fisher/ | > In an identifiable overlapping entangled generative circuit, a distributed SEQNN estimator using Fisher/ | ||
| - | ===== Publication framing ===== | ||
| - | |||
| - | A good paper story is emerging: | ||
| - | |||
| - | - Start with the problem: VQC training usually treats circuit parameters as optimizer variables, not latent states. | ||
| - | - Introduce SEQNN: local EKF estimators attached to quantum circuit parameters. | ||
| - | - Distinguish supervised training from true generative estimation. | ||
| - | - Show the model ladder from local identifiable circuits to richer local observations. | ||
| - | - Use Stage 5 as the main contribution: | ||
| - | - Compare against Adam, GD, SPSA, independent SEQNN-EKF, and centralized EKF. | ||
| - | - Be explicit that Fisher factors are the promoted distributed architecture. | ||
| - | - Leave topology diffusion and augmented noise-state EKF as future work. | ||
| - | |||
| - | The paper claim should be written as exploratory but concrete. The work is not finished because the scaling slice is still needed and the 50-seed sensitivity decision remains open. But Stage 5 now has a defensible center: the overlapping '' | ||
| - | |||
| - | ===== Suggested abstract-style summary ===== | ||
| - | |||
| - | Self-Estimating Quantum Neural Networks frame variational quantum circuit training as sequential Bayesian estimation rather than global optimization. In the current generative benchmark line, circuit parameters are latent states, finite-shot measurements are observations, | ||