A Closed-Form Upper Bound for Admissible Learning-Rate Steps in Belief-Space Dynamics

Zixi Li; Youzhen Li

Source-linked AI summary

A Closed-Form Upper Bound for Admissible Learning-Rate Steps in Belief-Space Dynamics

Zixi Li, Youzhen Li

arXiv:2605.06741v1May 7, 2026cs.LG

TL;DR

Learning-rate admissibility is posed as a local belief-space contraction problem rather than a generic hyperparameter choice. The paper analyzes a projected simplex update in KL/Bregman geometry, derives a closed-form bound, and applies entropy as a backoff. The headline conditions are 0 < η < 2µ/L2 for the contraction interval, a cross-entropy entropy-aware factor involving 1/(1 + α(B)), and an MSE normalized endpoint of 1.

Problem
The paper addresses how to choose a safe finite step for projected belief-space updates while preserving contraction under the simplex's natural geometry.
Method
It models the update as a projected Euler step on the probability simplex and pulls the KL/Bregman contraction condition into parameter space through the forward-map Jacobian.
Results
0 < η < 2µ/L2 is the admissible contraction interval; cross-entropy then uses an entropy backoff, while MSE has normalized endpoint 1.
Takeaways & Limitations
In this local model, the admissible learning-rate step is a formula determined by belief-state geometry, with uncertainty narrowing the cross-entropy step through backoff.
Takeaways & Limitations
The statement is deterministic and local; minibatch gradient noise and stochastic curvature require a future high-probability admissibility bound.

Abstract

from arXiv · show

Learning-rate steps are usually treated as hyperparameters. This paper isolates a local beliefspace calculation: when an update is modeled as a projected forward step on the probability simplex, admissibility means contractivity in the natural KL/Bregman geometry. Under this model, the upper bound of an admissible step is not a tuning slogan but a formula.

1 From heuristic admissibility to belief-space admissibility

The paper transfers heuristic admissibility from graph search to belief-space updates, asking whether projected steps preserve contraction in KL/Bregman geometry. The resulting contract limits step size through local curvature and can be further reduced by uncertainty.

From heuristic admissibility to belief-space admissibility: A* permits approximation under a mathematical contract: heuristics must not overestimate remaining cost to preserve optimality.The contract trades speed against safety rather than allowing an uncontrolled guess.
From heuristic admissibility to belief-space admissibility: Adaptive dual search uses normalized entropy to make uncertainty directly restrict the admissible step through a local backoff.Diffuse beliefs receive a larger barrier and therefore a stronger reduction.
From heuristic admissibility to belief-space admissibility: The projected forward move is the belief-space analogue of a finite search expansion or discretized gradient-flow step.Both procedures ask how far they may move while preserving their defining guarantee.
From heuristic admissibility to belief-space admissibility: In belief space, admissibility asks whether the update map remains contractive in the geometry natural to probability distributions.This replaces graph-search optimality as the protected invariant.
From heuristic admissibility to belief-space admissibility: KL divergence and the negative-entropy Bregman geometry provide the identity needed to analyze projected updates on the simplex.The identity exposes the curvature term used in the contraction proof.
From heuristic admissibility to belief-space admissibility: The admissibility condition is 2µ −ηL2 > 0, balancing strong-convexity contraction against smoothness penalties for overly large steps.Cross-entropy supplies the original-scale endpoint 2µ/L2, while an entropy backoff can retreat from that endpoint.

2 Setup

The setup models belief states as points on the probability simplex and updates them with a projected Euler step. Cross-entropy has state-dependent simplex curvature, while MSE is treated as a distinct normalized comparison geometry.

Setup: A belief state is a normalized distribution over C labels, so the state space is a constrained statistical domain rather than unconstrained Euclidean space.The normalization constraint removes one degree of freedom and motivates simplex-native geometry.
Setup: The local update takes an Euler step of size η on energy E and projects the result back to the simplex.Admissibility asks for the largest step allowed by E's local geometry before entropy backoff.
Setup: Cross-entropy curvature depends on the current belief coordinates, so its admissible step changes with the distribution.The target distribution q enters the cross-entropy geometry.
Setup: MSE is included only as a comparison case, with a normalized Euclidean compensation path whose endpoint is 1.Its endpoint should not be collapsed into the cross-entropy bound because the loss geometries differ.
Setup: The local curvature proxy is used to read strong-convexity and smoothness constants from the belief state rather than treating them as free learning-rate parameters.This makes the bound state-dependent under the paper's proxy.

4 The KL contraction proof

The KL contraction proof combines projected-gradient optimality with local strong convexity and smoothness. These terms produce a positive gap whose preservation yields the admissible step interval.

The KL contraction proof: The projected forward map is defined before entropy backoff as a simplex projection of p −η∇E(p).The proof analyzes this map's contraction under the simplex's KL/Bregman geometry.
The KL contraction proof: Negative entropy generates KL divergence, whose three-point identity bridges points before and after projection.This identity exposes the inner-product term where the curvature of E enters.
The KL contraction proof: Projected-gradient optimality controls the inner-product term through the gradient difference of E.The resulting analysis uses local strong-convexity and smoothness inequalities.
The KL contraction proof: Strong convexity contributes 2µ, while smoothness contributes −ηL2, producing the gap 2µ −ηL2.Admissibility requires this gap to remain positive.
The KL contraction proof: KL-to-Euclidean local equivalence converts the contraction estimate into an admissible upper bound on η.The proof therefore links the natural simplex geometry to a usable step-size condition.

5 Closed-form cross-entropy bound and entropy backoff

The paper isolates a closed-form cross-entropy endpoint from local curvature and then applies entropy as a multiplicative backoff. On a binary slice, the endpoint shrinks near simplex boundaries, while entropy further narrows the certified region.

5 Closed-form cross-entropy bound and entropy backoff: Equation (15) gives the admissible upper bound from the KL contraction proof.The bound is determined by the current belief distribution through local curvature.
5 Closed-form cross-entropy bound and entropy backoff: Figure 2 uses the binary belief slice p = (x, 1 −x) to visualize the raw curvature endpoint and the entropy-restricted admissible region.The figure is a diagnostic visualization of the theorem rather than a separate experiment.
5 Closed-form cross-entropy bound and entropy backoff: The cross-entropy curvature endpoint shrinks rapidly as the belief approaches the simplex boundary.On the binary slice, this reflects stiff local curvature when a coordinate is close to zero.
5 Closed-form cross-entropy bound and entropy backoff: The entropy barrier backs off from the cross-entropy endpoint rather than replacing it.The backoff factor is defined using α(B) = −log(1 −B) and 1/(1 + α(B)).
5 Closed-form cross-entropy bound and entropy backoff: As B →1, α(B) →∞ and the entropy-aware step goes to 0; as B →0, it approaches the cross-entropy upper bound 2µ/L2.Uncertainty therefore carves out a stricter certified region below the curvature endpoint.

6 Fixed point statement

The fixed-point argument links contractive belief updates to a stable destination, with the empirical label distribution serving as the anchor. The bound 0 < η < 2µ/L2 permits this local fixed-point statement, while ADS adds an entropy-dependent brake without changing the anchor.

6 Fixed point statement: Contractive repeated updates are pulled toward a stable fixed point in the relevant belief region.The fixed-point argument frames admissibility as the condition preventing indefinite wandering.
6 Fixed point statement: The stable point for the empirical cross-entropy energy is the training-distribution anchor, namely the empirical label distribution.
6 Fixed point statement: 0 < η < 2µ/L2 is the condition that makes the local fixed-point statement valid.
6 Fixed point statement: ADS adds a local entropy brake that affects approach speed and safety without changing the energy-determined anchor.

7 The MSE case: normalized quadratic compensation

The MSE comparison uses a normalized Euclidean compensation path whose quadratic endpoint is η = 1. ADS applies entropy backoff from that loss-geometry endpoint rather than replacing it or making it equivalent to the cross-entropy bound.

7 The MSE case: normalized quadratic compensation: The normalized MSE path pη = (1 −η)p + ηy reaches the target at η = 1.At this endpoint, the local compensation satisfies pη = y.
7 The MSE case: normalized quadratic compensation: MSE is quadratic in the compensation step, so its maximal normalized admissible compensation step is 1.
7 The MSE case: normalized quadratic compensation: The MSE result applies only to the normalized Euclidean path and should not be interpreted as the cross-entropy classification bound.
7 The MSE case: normalized quadratic compensation: Figure 3 separates the shared ADS entropy backoff from the loss-specific endpoint: MSE has normalized upper bound 1, while cross-entropy gives 2µ/L2.
7 The MSE case: normalized quadratic compensation: ADS backs off from the MSE endpoint through the factor 1/(1 + α(B)).Because the MSE endpoint is 1, the normalized backoff itself is the MSE step.

9 Related work

The paper situates its contribution between parameter-space learning-rate methods and contraction-based Bregman analyses. It applies these ingredients narrowly to a closed-form admissibility bound for projected belief-space updates.

9 Related work: Prior work on Adam, AdamW, adaptive learning rates, momentum, and problem-adaptive schedules primarily treats step adaptation in parameter space.
9 Related work: Contraction theory, fixed-step analysis, and mirror-descent work provide the proof and geometric ingredients closest to this paper.
9 Related work: The paper combines KL Bregman geometry, projected simplex updates, local strong convexity and smoothness, and the condition 2µ −ηL2 > 0 to isolate a closed-form upper bound.

12 Training-inference duality: Euler steps and gradient descent

The paper distinguishes inference as Euler dynamics in hidden-state space from training as gradient descent in parameter space, while identifying softmax as their shared contact with the probability simplex. A belief-space admissibility bound therefore constrains effective motion across both coordinate frames.

Training versus inference: Training reshapes the layer velocity fields through parameter-space gradient descent, whereas inference executes the resulting discrete orbit.The two processes use different state spaces and roles: training updates parameters, while inference applies the learned dynamics.
Euler-step inference: The forward pass executes L Euler steps in hidden-state space before softmax projects the result onto the probability simplex.Each transfer has the form h_k = h_{k−1} + v_k, with velocity supplied by the layer architecture and parameters.
Shared simplex interface: Training and inference intersect at the softmax projection, while training otherwise remains in parameter space and inference remains in hidden-state space.This separates optimization from forward execution without denying their shared output geometry.
Admissibility across coordinate frames: The belief-space bound induces a parameter-space constraint through the forward-map Jacobian: exceeding 2µ/L^2 loses the contraction guarantee.The same entropy barrier measures uncertainty in the output belief during both training forward evaluations and inference.
Admissibility across coordinate frames: Curvature and entropy encode distinct risks: curvature sets the largest locally legal step, while entropy backs off from it as beliefs become diffuse.The resulting condition is presented as a shared stability requirement for training updates and inference dynamics.
Stability consequence: Violating the admissible bound can make belief dynamics overshoot, collapse to a simplex boundary, and diverge rather than track the target stably.The reported high-step case uses η = 2.0, approximately 70× the post-convergence admissible limit.

13 Discussion

The discussion frames the contribution as a narrow geometric admissibility calculation rather than a new optimizer, and interprets the formula as a local safety certificate. It also limits the claim: stable contraction approaches the training-distribution anchor but does not ensure semantic correctness or solve full parameter-space optimization.

Contribution: The paper isolates whether a projected simplex update remains contractive under the KL/Bregman geometry natural to probability distributions.Its stated contribution is deliberately narrower than introducing an optimizer or pursuing benchmark gains.
Geometric interpretation: The loss geometry supplies the cross-entropy endpoint 2µ/L^2, while the ADS entropy factor backs off from that endpoint under uncertainty.Under the stated curvature proxy, the endpoint becomes 2 min_i(p_i)^2 / max_i(p_i).
Geometric interpretation: Near the simplex boundary, small coordinates make the admissible cross-entropy step shrink quadratically because local curvature becomes stiff.Entropy measures global diffuseness, whereas curvature captures local geometric fragility.
Practical scope: The formula is closer to a safety certificate or instrumentation layer than a complete training algorithm because it diagnoses aggressive belief-space motion without solving parameter-space optimization.Using it in a neural model requires a pullback from output beliefs to parameters.
Limitation: Contraction guarantees approach to the fixed point of the local energy landscape, whose empirical cross-entropy anchor is determined by the training distribution rather than semantic truth.A stable update controls motion toward the anchor, not whether the anchor is the correct answer.

14 Open questions

The paper identifies open questions around exact curvature, boundary behavior, parameter-space translation, stochastic gradients, empirical validation, and alternative divergence–barrier pairs. These questions define the limits of the current local, deterministic belief-space analysis.

Exact cross-entropy curvature: A sharper cross-entropy analysis should replace the local proxy with the target-dependent Hessian on the simplex tangent space.The paper leaves open whether the same qualitative bound survives this more exact treatment.
Boundary behavior and projection: The proof is local to the simplex interior, leaving clipping, smoothing, and boundary-approaching projected steps for future analysis.A complete theory should determine how these operations change the admissible interval.
Pullback to parameter space: Translating the belief-space bound into a neural-network learning-rate rule requires combining belief-space curvature with the model output Jacobian.The current result therefore does not directly specify a parameter-space step size.
Stochastic gradients: The present admissibility statement is deterministic and local, whereas minibatch gradients perturb both the update direction and curvature estimates.The proposed next step is a high-probability bound using stochastic or empirical estimates of µ and L.
Empirical role of the bound: Empirical work could test whether admissible-gap violations predict instability or collapse and compare entropy-only with curvature-plus-entropy backoff.The paper frames these as suggested experiments rather than reported benchmark findings.
Alternative divergences and barriers: Which divergence–barrier pairs preserve contraction remains an open structural question beyond the KL geometry and logarithmic ADS barrier used here.Alternative Bregman divergences may produce different admissible intervals.
Anchors, correctness, and escape: Stability and correctness may diverge if contraction drives dynamics toward a biased empirical-prior anchor.The paper leaves open when object-level evidence can move the effective anchor.

15 Conclusion

The paper transfers admissibility from heuristic search to projected belief-space dynamics, deriving a KL/Bregman contraction condition for the step size. Substituting local curvature yields explicit cross-entropy and MSE endpoints, while ADS entropy supplies a backoff from those geometry-dependent limits.

15 Conclusion: In belief space, admissibility means preserving contraction of a projected forward step under KL/Bregman geometry.The three-point identity exposes the local step condition 0 < η < 2µ/L^2.
15 Conclusion: For cross-entropy classification, substituting the local curvature proxy produces a closed-form upper bound before entropy backoff.The conclusion identifies this substitution as the paper’s isolated calculation.
15 Conclusion: max_i(p_i) · 1/(1 + α(B)), with α(B) = −log(1 − B), is the ADS entropy-backed cross-entropy endpoint.The entropy barrier retreats from the curvature-derived endpoint according to normalized entropy B.
15 Conclusion: The bound replaces heuristic guessing with an explicit geometric upper bound for belief-space steps under the stated local model.It does not eliminate learning-rate tuning or constitute a complete parameter-space training algorithm.