Conditional Learning Bounds
Bounds require a specified observation experiment, task, learner and admissible dynamics. A seven-role implementation can be tested against smaller implementations under matched observations and budgets.
Specify what is being learned, what one observation contains and what success means. A software coherence matrix does not by itself turn classical examples into independent quantum copies. The reconstruction protocol distinguishes identifiable data targets from arbitrary encoders; T-42a supplies no universal canonical encoder.
1. Formal definition of the learning task
1.1 Learning task for the holon
Let a task have hypotheses , an observation law , a prior or a specified worst-case criterion, allowed observation/decision policies and a loss. A learner uses observations to update a declared state or parameters. Its required sample count is the smallest count achieving the registered risk at most . State validity, computational cost and safety are additional constraints. Counts of observations, physical time and optimization iterations have different units.
1.2 Criterion for successful learning
Use independent held-out data for performance and frozen readouts for the full Cap₂ predicate. Classification accuracy, a matrix predicate and phenomenal interpretation are separate claims. Calibrating an encoder with the evaluation labels changes the experiment and invalidates the originally registered risk.
1.3 Learning as attractor update
An update of , the observation model or a policy is a model choice [D/H]. It need not be an attractor update, and an attractor needs an actual stability proof. Frozen-target replacement is linear CPTP; state-dependent feedback generally produces a nonlinear state map. Purity of the target alone does not guarantee that regeneration raises current purity.
2. Information bounds (T-109) [T under the stated experiment]
T-109: exact binary discrimination and Chernoff scope
For equal priors and i.i.d. copies of known physical quantum states , allowing all collective POVMs, the Helstrom optimum is
Therefore every test with error at most must satisfy . This is an exact finite-sample criterion. Restricted measurements can require more copies.
Define , . For , quantum Chernoff gives
Thus is sufficient for the unrestricted optimal test, not the former necessary lower bound. The exponent is asymptotically optimal; it does not supply an exact finite-sample equality. See Audenaert et al. and Nussbaum–Szkoła.
A useful genuine necessary bound follows from root fidelity and the trace-distance/fidelity inequality:
For and , attaining error at most requires
Indeed the lower-error expression must be at most , implying . Multiplicativity of fidelity gives the product exponent. The underlying inequalities and Helstrom formula are in Watrous, Chapter 3. Identical states () are indistinguishable under this task; orthogonal supports can be distinguished in one copy. Zero observations with equal priors still have error .
2.1 Local alternatives
Quadratic exponents occur for regular nearby alternatives, with coefficients depending on the states, direction and experiment. They are not universally . For the commuting binary pair
symmetry gives and . This pair is already realized in dimension two. Singular, orthogonal or nonregular alternatives need not have quadratic scaling.
2.2 Numerical Chernoff certificates
For that pair and :
| Sufficient copy count | ||
|---|---|---|
| 0.25 | 0.143841 | 17 |
| 0.10 | 0.020411 | 113 |
| 0.05 | 0.005025 | 459 |
These are certificates for an allowed optimal test, not guaranteed training durations or necessary lower counts. There is no dimensional ceiling : for pure states with overlap , , so becomes arbitrarily large as . The Holevo bound concerns average accessible information for an ensemble in one -level system, a different quantity.
3. Selected dynamical bound (T-110)
T-110: a scalar accumulator [T]
Choose one mode with attenuation and a constant aligned impulse . For , ,
For a target , the non-strict cut is reached in finite time iff . Its first step is
At equality only the limit reaches it. For , the first step reaches the cut iff ; for , and . A strict cut uses a floor plus one. The proof is the geometric-series identity followed by solving ; dividing by reverses the inequality.
For vector impulses with , the triangle inequality gives only . Thus the scalar envelope yields a necessary time to attain norm , but cancellation can prevent attainment. A claimed impulse update of a density matrix still needs a PSD/trace-preserving realization.
3.1 Physical meaning
The value belongs to a normalized Fano coherence mode in the specified generator. It is not a universal physical clock or the decay rate of every variable. Translating steps into seconds needs an independently measured rate. Non-normal coupled dynamics may need a transient prefactor rather than a single scalar exponential.
3.2 Role of regeneration
Feedback can alter the mode, attenuation and impulse. A changing or rate invalidates the fixed-coefficient recurrence unless its reduction is proved. Evolution supplies chosen state-preserving models and conditional attractor constructions; positive regeneration alone does not ensure safety or optimal learning.
4. Safety and noise (T-111)
T-111: a sufficient safe-neighborhood condition [T]
Fix a region of valid states satisfying all desired cuts, a norm and a state in its relative interior. Let . A state-valid update with remains in . This is a sufficient condition, not a necessary bound on every successful learning update; a larger update in a safe direction may remain in . A basin or trajectory certificate additionally requires the specified vector field, as in viability.
For the purity cut alone in HS norm, the exact distance is
The reverse triangle inequality around is a lower bound; radial mixing toward attains it within . This is not a Bures distance, a basin radius or the radius to all capability cuts.
If and bounded state-update noise has norm at most , then is sufficient. Unbounded Gaussian noise does not give such a pathwise guarantee and requires a state-preserving noise model plus a finite-horizon exit estimate; see T-145.
4.1 A declared noise experiment
For independent classical observations with equal priors, the optimal test uses the sample mean and has
where is the standard normal CDF, distinct from matrix integration . The signal sum grows as , while its noise standard deviation grows as . This explains scaling under this specific independent Gaussian law, not a separate universal stability law. Noise correlation, bias or a different loss changes the count. Attenuation is an engineering policy; its optimum requires an explicit cost and constraints.
4.2 Stability zones as a policy
A policy may reduce its step as the certified margin shrinks, reject uncertified updates or fall back to a feasible state. Stress bands and action thresholds are choices [D/H], not universally derived clinical categories. Matrix noise and a purity deficit alone do not establish depression, trauma or treatment mechanisms.
5. Combining valid bounds (T-112)
T-112: maximum of necessary bounds [T]
If, for the same task and admissible protocol class, all successful protocols require , and , then
This follows by conjunction. It proves neither equality, existence of a protocol attaining the maximum nor a unique best algorithm. The old label named this lower-bound score; use to avoid identifying it with an optimum. Chernoff's sufficient count cannot be inserted as a necessary .
5.1 Comparing regimes
A verified fidelity lower bound , a specified dynamical envelope and a separately necessary constraint can be compared after aligning units and premises. The largest identifies the strongest currently established obstruction. Distinct bounds may share assumptions or information and need not be independent. Simultaneous attainability requires a common constructive protocol, not separate equality examples.
5.2 Including genesis time
Adding initialization and learning times requires sequential stages with declared clocks. T-148 gives an exact first-passage count for one constant-input recurrence, including a regime in which crossing never occurs. There is no universal genesis guarantee or law from dimension alone. Adding a lower bound to an upper bound does not give an upper bound for total time.
6. Seven dimensions and learning (T-113) [H]
Scope of T-113
An information-theoretic lower bound needs observable distinctions that each smaller model fails to reproduce. Counting seven named functional roles does not prove their independence.
A concrete counterexample is a two-level learner. Encode as and observe independent with mean . Set
For , is the sample mean, and . Each fixed observed update is a convex combination of identity and a replacement CPTP channel. This is finite-dimensional learning through replacement with , without Fano structure. It refutes the universal claim, while leaving a specifically chosen seven-role architecture testable.
6.1 Structural requirements versus universal necessities
If a selected implementation represents the seven Fano points by seven mutually orthogonal nonzero directions, then by dimension counting. This is a requirement of that representation [D], not of every learner. A fixed larger space can contain an invariant seven-dimensional sector and train only its parameters; extra dimensions do not necessarily slow learning. Embeddings and retractions do not establish a unique empirical encoder or functional frame.
6.2 Parameters and the selected efficiency score
A general -level density matrix has real parameters; at it has . The selected ratio
strictly decreases for real : the derivative has the sign of , because starts at zero and has positive derivative. Thus if one separately restricts the class to and selects this score, its maximum is at . The ratio is not a universal resource/learning capacity, and a one-objective maximum does not establish a Pareto frontier. Rates, bootstrap strength, accessible information and genesis time still need their respective physical/model premises.
7. A reproducible binary example
7.1 The two-button task
Choose the commuting pair in §2.1 with equal priors, register the allowed observations and compare independent test error. Matrices encode an actual probability experiment here; no unique universal encoder is assumed.
7.2 Signal and mechanism
For binary samples, reward-driven state updates can use the two-level recurrence above or a declared embedding into . Interpretations such as pleasure and punishment are separate hypotheses. The exact purity derivative of replacement is ; it can be negative even if the target is purer.
7.3 Exact error and sufficient count
For , , the classical optimum is
This finite sum is exact, including ties, and equals the quantum Helstrom value for these commuting states. The following code evaluates it with logarithmic binomial coefficients and also reports the Chernoff sufficient count.
from math import ceil, exp, fsum, lgamma, log, log1p
def exact_binary_error(n, u):
if not (n >= 0 and int(n) == n and 0 < u < 0.5):
raise ValueError("n must be a nonnegative integer and 0<u<1/2")
n = int(n)
p0, p1 = 0.5-u, 0.5+u
terms = []
for k in range(n+1):
log_binom = lgamma(n+1)-lgamma(k+1)-lgamma(n-k+1)
a = k*log(p0)+(n-k)*log1p(-p0)
b = k*log(p1)+(n-k)*log1p(-p1)
terms.append(exp(log_binom+min(a,b)))
return 0.5*fsum(terms)
def chernoff_sufficient_count(u, delta):
if not (0 < u < 0.5 and 0 < delta < 0.5):
raise ValueError("require 0<u<1/2 and 0<delta<1/2")
xi = -0.5*log1p(-4*u*u)
return max(1, ceil(log(1/(2*delta))/xi))
Finite-precision output is a numerical check, not an interval certificate; critical comparisons should use a verified error tolerance.
7.3a Separate signal and safety checks
With , , the Chernoff sufficient count is , while the exact sum can determine the smaller actual discrimination count. For a separately chosen accumulator , , , the exact dynamical count is . These numbers are not interchangeable training lower bounds.
At , the purity-only HS margin is , not . No safety verdict follows without the direction, state validity and other gate margins. A chosen attenuation policy changes the observation law if it discards distinguishability; recompute that law rather than assuming every exponent changes as an arbitrary squared matrix amplitude.
7.4 Registered test criterion
An empirical violation is assessed against the registered observation/task model with uncertainty and held-out data. Beating a sufficient Chernoff count is allowed. Lower error than a valid exact Helstrom optimum would instead challenge the stated encoding, independence/measurement assumptions or implementation. Speed in a simulator alone does not validate the physiological or phenomenal bridge.
8. Comparison with other learning results
8.1 PAC learning and VC dimension
PAC guarantees require a hypothesis class, sampling law and loss; VC dimension measures a different object than the number of density-matrix coordinates. Forty-eight state parameters do not determine a hypothesis class's generalization complexity. A binary testing task is not every learning task.
8.2 Rademacher complexity and generalization
Capacity, regularity, sample dependence and the evaluation protocol affect generalization. An encoder selected using labels can add statistical degrees of freedom even if its output has only 48 coordinates. Parameter dimension alone is neither a sample bound nor an identifiability proof.
8.3 Shannon and Chernoff
Shannon transmission rate, Holevo accessible information and Chernoff error exponent address different experiments. Their units and operational definitions must be stated before comparison. Commuting quantum hypotheses recover the corresponding classical test; no ceiling follows.
8.4 Thermodynamic assumptions
Landauer inequalities apply to a specified physical erasure process, bath and entropy balance, not to every decline of matrix purity. The evolution page states the conditional Reeb–Wolf equality. Neither a unique learning gate nor as a universal cost per training example follows from a software state update.
8.5 Local optimal direction and its limits
For a fixed potential , positive definite metric and prescribed instantaneous speed , Cauchy–Schwarz gives . If the gradient is nonzero the unique minimizing tangent velocity is . This is T-263's local scope. Fixed-target reverse relative entropy has BKM gradient ; an input-dependent target introduces additional derivatives.
The result does not compare different potentials, metrics, observations, discretizations, global convergence or statistical sample rates. It proves neither a unique algorithm, an rate for all learners nor attainment of the preceding bounds. Physics claims such as T-264 require their own declared realization and do not complete such an optimization proof.
9. Practical implications
Use matched architecture tests, identifiable observation laws, separate sample/time/compute costs and state-valid updates. Certify local feasible margins and use an explicit objective for any learning-rate or attenuation optimization. Application to education or therapy requires independently validated biological readouts and clinical evidence; the matrix theorems do not derive a diagnosis or intervention.
10. Links and assumptions
| Result | Valid use here |
|---|---|
| T-109 | Exact quantum i.i.d. binary discrimination; conditional Chernoff certificates |
| T-110 | Exact selected accumulator or its norm envelope |
| T-111 | Sufficient feasible-state neighborhood; separately specified noise law |
| T-112 | Conjunction of valid necessary bounds, without attainment |
| T-113 [H] | Seven-role architecture under a specified task |
| T-42a [✗] | Supplies no universal encoder or equivalent empirical frame |
| T-148 | Conditional constant-input genesis, including no-crossing regimes |
| T-263 | Local steepest direction for specified metric/potential/speed |
11. Conclusion
The established results require explicit experiments and model assumptions. Seven state dimensions, covariance and a local gradient identity do not uniquely determine a learner or its empirical encoding. A stronger theory records these choices and tests their consequences.
Summary
- Exact Helstrom error is a genuine finite-sample obstruction; Chernoff's finite bound is sufficient.
- The scalar accumulator has an exact crossing law under fixed coefficients.
- Safe-neighborhood control is sufficient; full trajectory safety needs a dynamics certificate.
- A maximum of necessary bounds remains a lower bound, not an attained optimum.
- Two-level replacement learning disproves universal necessity; selected seven-role hypotheses remain testable.
What was established
Independent data, an identifiable readout and verified model premises connect these mathematical results to an empirical learning claim. See measurement protocol, viability and evolution.