---
title: Krasnoselskii-Mann Iteration
url: https://www.emergentmind.com/topics/krasnoselskii-mann-iteration
type: topic
---

# Krasnoselskii-Mann Iteration

The Krasnoselskii-Mann (KM) iteration is a foundational iterative scheme for finding fixed points of nonexpansive operators in linear and nonlinear settings. It underpins a wide range of algorithms in monotone operator theory, convex optimization, game theory, stochastic approximation, and reinforcement learning. KM-type schemes balance contraction (relaxation) with inertia and are robust to perturbations, variable step sizes, and stochastic noise. Their convergence properties, rate bounds, and generalizations have been the subject of intensive analysis, leading to sharp characterizations in Hilbert, Banach, CAT(0), and even general normed spaces.

## 1. Definition, Origin, and Operator-Theoretic Formulation

The Krasnoselskii-Mann iteration is defined by
\[
x_{n+1} = (1-\alpha_n)x_n + \alpha_n T(x_n)
\]
where $T:X\to X$ is a nonexpansive operator ($\|T x - T y\|\le\|x - y\|$), $(X,\|\cdot\|)$ is typically a Hilbert or Banach space, and $\{\alpha_n\}_{n\ge0}\subset[0,1]$ is a sequence of relaxation parameters.

Classically, convergence is guaranteed if $\sum_{n=0}^\infty \alpha_n(1-\alpha_n)=+\infty$, a condition ensuring the scheme does not stagnate [1206.4195]. Equivalently, the KM iteration can be interpreted in terms of averaged operators: $T$ is $\theta$-averaged if $T = (1-\theta)\mathrm{Id} + \theta R$ for a nonexpansive $R$. The iteration generalizes Banach-Picard, Krasnoselskiĭ, and Mann schemes, and subsumes the Halpern iteration as a limiting case [2206.09462].

For linear $T$, and in multi-agent systems and game theory, the KM iteration connects fundamentally to the concept of strict pseudocontractiveness, which underpins necessary and sufficient conditions for convergence [1803.10469].

## 2. Convergence Theorems and Rate Analysis

### Weak and Strong Convergence

KM iterations converge weakly to a fixed point under nonexpansive $T$ and the divergent-series step-size condition $\sum \alpha_n(1-\alpha_n)=\infty$ [1206.4195].
For linear nonexpansive $T$, this iteration converges \emph{strongly} (in norm) to the metric projection of $x_0$ onto $\operatorname{Fix} T$, requiring only the divergent-series condition, without uniform positive lower/upper bounds on $\alpha_n$ [2512.22817]. This generalizes the Baillon–Bruck–Reich theorem and later results by Bauschke–Combettes.

In uniformly convex Banach spaces, asymptotic regularity and convergence rates can be quantified using "proof mining" techniques; for constant $\alpha_n=\alpha\in(0,1)$, the quadratic rate $\|x_n-Tx_n\|=O(1/n)$ is attainable in Hilbert spaces and under suitable regularity conditions [2501.09523].

### Rate Bounds and Optimality

The sharp universal upper bound for the fixed-point residual is
\[
\|x_n - T x_n\| \le \frac{ \operatorname{diam}(C) }{ \sqrt{ \sum_{i=1}^n \alpha_i(1-\alpha_i) } }
\]
and this rate $O(1/\sqrt{n})$ is optimal for general normed spaces [1206.4195, 2108.10969], with Halpern-type iterations attaining $O(1/n)$, which KM cannot generally match. The residual decay rates for various schemes are summarized below.

| Scheme                   | Typical Rate                     | Source(s)                |
|--------------------------|----------------------------------|--------------------------|
| Classical KM             | $O(1/\sqrt{n})$                  | [1206.4195], [2108.10969] |
| Halpern (linear/firm)    | $O(1/n)$                         | [2108.10969]             |
| Generalized stochastic   | Linear & Quadratic ($O(1/n)$, $O(1/n^2)$) | [2411.04845]            |
| Fast/Nesterov-KM         | $o(1/k)$ (momentum, accelerated) | [2206.09462], [2510.24544]    |
| AdaGrad-regret-KM        | $O(1/\sqrt{T})$, data-adaptive   | [2509.21653]             |

## 3. Extensions: Inertia, Perturbation, and Generalized Schemes

### Inertial Krasnoselskii-Mann (IKM)

IKM iterations inject momentum:
\[
w_k = x_k + \beta_k(x_k - x_{k-1}), \quad x_{k+1} = (1-\alpha_k) w_k + \alpha_k T(w_k)
\]
with $\beta_k$ controlling inertia [1908.11029, 2210.03791]. Provided parameter sequences and error terms are summable, weak (and under quasi-contractive maps, strong/linear) convergence is established, along with $O(1/k)$ nonasymptotic bounds on the best residual [1908.11029].

The practical advantage is acceleration, observable in primal-dual splitting and multi-operator monotone inclusions. Inertia allows faster empirical convergence at modest risk of divergence, necessitating careful parameter selection [2210.03791].

### Stochastic and Inexact Iterations

Noise-resilient versions (with martingale-difference or arbitrary perturbations) admit almost sure convergence and explicit nonasymptotic residual bounds. Under bounded variance or summable errors, rates mirror deterministic $O(1/\sqrt{n})$ decay, with minor log or step-size corrections [1705.09340, 2208.04193, 2506.08031].

The general proof architecture for stochastic variants relies on the Robbins–Siegmund supermartingale lemma, and Fejér-type monotonicity, which extends to adaptive Bregman geometries and heavy-tailed noise models [2506.08031].

## 4. Advanced Schemes and Algorithmic Accelerations

### Nesterov-Type and Adaptive-Momentum Variants

Momentum-accelerated KM algorithms, such as Fast KM and TKMA, utilize Nesterov's extrapolation or adaptive local geometry, blending information from $T^2$ (Picard) and momentum steps, with analytically derived or geometrically motivated momentum parameters [2206.09462, 2510.24544]. The resulting schemes achieve $o(1/k)$ or $o(1/k^{1/2})$ rates on iterate differences and often outperform classical and Halpern algorithms in image denoising and matrix completion applications [2510.24544].

### Tikhonov Regularization and Forward-Backward Splitting

Tikhonov regularization augments KM with shrinking steps:
\[
x_{n+1} = (1-\lambda_n) \beta_n x_n + \lambda_n T_n(\beta_n x_n)
\]
where $\beta_n \to 1$ and $\lambda_n$ control regularization and relaxation, respectively [1911.11656]. This yields strong convergence to the minimal-norm solution for countable families of operators and in monotone inclusion settings, especially when coupled with variable step sizes (forward-backward algorithms).

The framework robustly accommodates errors and variable steps, directly translating into accelerated splits for convex optimization and signal processing [1911.11656].

## 5. Geometric, Nonlinear, and Game-Theoretic Generalizations

### Nonlinear (CAT(0), Hyperbolic) KM Iterations

KM extends to metric and geodesic spaces (CAT(0)), traditionally formulated as:
\[
x_{n+1} = (1-\alpha_{n+1}) x_n \oplus \alpha_{n+1} T(x_n)
\]
where $\oplus$ denotes the geodesic convex combination [2510.25363]. Asymptotic regularity is preserved, and the same $O(1/\sqrt{n})$ rate applies. Convergence to a fixed point (in the sense of $\Delta$-convergence) is proved under mild control on step sizes.

Halpern iteration in metric settings further accelerates rates ($O(1/n)$) and motivates hyperbolic variants for deep learning optimizers [2510.25363].

### Consensus, Equilibrium, and Relative KM Iteration in Games

In multi-agent consensus problems, KM iteration finds equilibria even when network topology is only partially known. Convergence is guaranteed iff the underlying operator is strictly pseudocontractive, connectable to spectral and LMI criteria [1803.10469].

In stochastic mean-payoff and entropy games, "relative" KM schemes leverage normalized operators under Hilbert seminorms, exploiting the additive homogeneity of Shapley operators to achieve $O(|\log \epsilon|)$ complexity for $\epsilon$-approximation, significantly improving upon prior bounds [2305.02458].

## 6. Practical Implementations and Application Domains

KM-type iterations and their variants (stochastic, inertial, adaptive, Tikhonov-regularized) underpin algorithms in:
- Convex optimization (proximal point, forward-backward, Douglas-Rachford)
- Signal and image processing (deblurring, inpainting, denoising) [2510.24544]
- Matrix completion (low-rank recovery) [2510.24544]
- Reinforcement learning (Q-learning with monotone updates, policy iteration) [1911.11656, 2208.04193, 2411.04845]
- Distributed consensus [1803.10469]
- Zero-sum games and variational inequalities [2305.02458]

Empirical comparisons show that momentum-enhanced and adaptive-KM variants consistently outperform classical schemes in both computational speed and convergence rate, but can exhibit oscillatory or spiraling behavior typical of momentum methods [2206.09462, 2510.24544].

## 7. Parameter Tuning, Rate Explicitness, and Theoretical Implications

Quantitative bounds on asymptotic regularity and convergence rates are now explicit due to advances in proof mining and optimal transport analysis [2501.09523]. This enables detailed complexity planning for practical implementations, for instance, explicit oracle complexity $O(\varepsilon^{-5})$ for minibatch KM in stochastic environments [2411.04845]. Parameter dependencies on the relaxation and inertia sequences, convexity moduli, and problem geometry guide optimal algorithm design.

KM-type schemes are robust to perturbations, approximation, and stochastic deviations, provided error terms are appropriately controlled (summable or diminishing), and inertia/momentum parameters are carefully chosen to avoid instability [2210.03791, 1908.11029].

## References

- [1206.4195] Cominetti, Soto, Vaisman: Rate of convergence, Bernoulli sum connection, explicit universal bounds.
- [2512.22817] Bartz, Bauschke, Gao: Strong convergence in linear case, Baillon–Bruck–Reich revisited.
- [1803.10469] Belgioioso et al.: Strict pseudocontractiveness, operator-theoretic characterizations.
- [2501.09523] Firmino, Leuștean: Proof mining, quadratic rates, explicit complexity.
- [2206.09462] Bot, Nguyen: Fast KM (Nesterov), $o(1/k)$ residual decay.
- [2510.24544] Bot et al.: Two-step KM with adaptive momentum, image/matrix experiments.
- [1911.11656] Bot, Csetnek, Meier: Tikhonov-KM, strong convergence with variable steps.
- [2210.03791] Combettes, Salzo: Inertial KM, weak/strong/linear variants.
- [1705.09340] Bravo, Cominetti, Pavez: Inexact KM, error bounds, continuous time.
- [1908.11029] Cui, Yang, Tang, Zhu: Inexact inertial KM, residual rates.
- [2108.10969] Bravo, Cominetti: Optimal residual bounds, Halpern iteration.
- [2509.21653] Hendrickx et al.: Regret minimization, AdaGrad-KM extension.
- [2506.08031] Erdinc, Salzo: Bregman SKM, adaptive geometries, stochastic stability.
- [2305.02458] Akian, Gaubert, Naepels, Terver: Relative KM for games, complexity bounds.
- [2411.04845] Pischke, Powell: Generalized stochastic Halpern-KM, oracle complexity.
- [2510.25363] Pinto, Pischke: CAT(0) KM iterations, hyperbolic optimization.

## Summary Table: Scheme Variants and Convergence Properties

| Iteration Variant           | Rate & Convergence             | Noise/Stability            | Parameter Control  |
|----------------------------|--------------------------------|----------------------------|--------------------|
| Classical KM               | $O(1/\sqrt{n})$, weak (linear: strong) | Robust to summable errors   | $\sum \alpha_n(1-\alpha_n)=\infty$ |
| Inertial KM                | $O(1/k)$–$o(1/k)$ best residual | Sensitive to inertia choice | Bounded/increasing $\beta_k$ |
| Tikhonov-KM                | Strong convergence, min-norm    | Variable step size, small Tikhonov | $\beta_n\to1$, decay $\lambda_n$ |
| Fast, Adaptive KM          | $o(1/k)$, $o(1/\sqrt{k})$      | Mildly oscillatory          | Momentum schedule, geometric |
| Stochastic/Bregman SKM     | $O(A_N^{-p})$ residual averages | Martingale/noise trimming   | $\sum \alpha_k^2 < \infty$  |
| Proof-mined Generalized    | Explicit $\Phi(k)$ rate, quadratic possible | Error modulus imposed       | Fejér, convexity modulus    |

The Krasnoselskii-Mann iteration remains a central tool in nonlinear analysis, monotone operator theory, and optimization. Its generalizations, inertial and regularized variants, stochastic extensions, and precise rate theory constitute a mature and versatile algorithmic arsenal with rigorous theoretical guarantees and broad practical impact across mathematical and computational sciences.

Source: https://www.emergentmind.com/topics/krasnoselskii-mann-iteration