Samplinglib
Lean gate not recorded for this source state main · 0e31a3cda412
ASTIS mathematical exposition

Strongly convex gradient descent has rational and inverse-power rates

AutoSamplingTheory.TechnicalLemmas.Analysis.GradientDescentRates.strongly_convex_value_le · theorem · Teaching coverage

Statement

E is a complete real inner-product space and f:E→R is C1. The gradient is the genuine Riesz gradient of f. For all x,y, f(y)<=f(x)+<gradient f(x),y-x>+(beta/2)||y-x||². The step satisfies h>0 and beta*h<=1; N is a positive natural number. x0 and z are arbitrary points; X_N is exactly N iterations of x ↦ x-h gradient f(x) starting at x0. No minimizer is required for the comparator bound. f is alpha-strongly convex on the whole space with normalization alpha/2; alpha>0 and alpha*h<=1. The rational bound includes q=1-alpha*h=0; the second, conditional inverse-power bound additionally requires alpha*h<1. The following bound holds for the actual final iterate.

\[\begin{gathered}q=1-\alpha h\in[0,1),\qquad f(X_N)-f(z)\le\frac{\alpha q^N\|x_0-z\|^2}{2(1-q^N)},\\q>0\Longrightarrow f(X_N)-f(z)\le\frac{\alpha}{2(q^{-N}-1)}\|x_0-z\|^2.\end{gathered}\]

All objects and hypotheses

  • E is a complete real inner-product space and f:E→R is C1. The gradient is the genuine Riesz gradient of f.
  • For all x,y, f(y)<=f(x)+<gradient f(x),y-x>+(beta/2)||y-x||². The step satisfies h>0 and beta*h<=1; N is a positive natural number.
  • x0 and z are arbitrary points; X_N is exactly N iterations of x ↦ x-h gradient f(x) starting at x0. No minimizer is required for the comparator bound.
  • f is alpha-strongly convex on the whole space with normalization alpha/2; alpha>0 and alpha*h<=1.
  • The rational bound includes q=1-alpha*h=0; the second, conditional inverse-power bound additionally requires alpha*h<1.

Mathematical proof

1. Reuse the actual-iterate energy estimate

Write q=1-alpha h, R=||x0-z|| and e_N=f(X_N)-f(z). The existing weighted theorem already derives objective descent and the forced recurrence for the actual gradient iterates. Invoke it directly; its conclusion also allows negative comparator gaps.

\[2h\Bigl(\sum_{k=0}^{N-1}q^k\Bigr)e_N\le q^N R^2.\]
Corresponding Lean step

GradientDescentValue.gradient_descent_weighted_value_bound.

2. Normalize the geometric sum without inverting q

Positive alpha and h with alpha h<=1 give 0<=q<1. For N>0, q^N<1. The finite geometric identity, multiplied by 2, yields 2alpha h sum(q^k)=2(1-q^N). Multiply the weighted estimate by positive alpha and divide by positive 2(1-q^N). This rational form remains valid at q=0.

\[2\alpha h\sum_{k=0}^{N-1}q^k=2(1-q^N)>0,\qquad e_N\le\frac{\alpha q^N R^2}{2(1-q^N)}.\]
Corresponding Lean step

geom_sum_mul_neg, pow_lt_one₀, mul_le_mul_of_nonneg_left and le_div_iff₀.

3. Recover the source inverse-power expression

Under the additional strict inequality alpha h<1, q>0 and q^N>0. Integer negative powers equal inverse positive powers. Multiplying numerator and denominator by q^N proves the exact displayed equality. At q=0 only the preceding rational conclusion applies; the negative-power formula is undefined in ordinary real arithmetic.

\[0<q<1:\quad\frac{\alpha q^N R^2}{2(1-q^N)}=\frac{\alpha}{2(q^{-N}-1)}R^2.\]
Corresponding Lean step

zpow_neg, zpow_natCast, pow_pos and field_simp. The positive q^N fact discharges inverse cancellation.

Lean statement · strongly_convex_value_le

Strongly convex gradient descent has rational and inverse-power rates.

Braces mark parameters Lean can infer; square brackets request structures such as a measurable space or probability measure. Named hypotheses are mathematical premises, not facts established by this declaration. Section parameters are described in the mathematical hypotheses above; the module link retains their exact source context.

theorem strongly_convex_value_le {f : E → ℝ} {α β h : ℝ} (hf : ContDiff ℝ 1 f)
    (hsc : StrongConvexOn univ α f) (hα : 0 < α) (hh : 0 < h) (hstep : β * h ≤ 1)
    (hcoeff : α * h ≤ 1)
    (hu : ∀ x y, f y ≤ f x + inner ℝ (gradient f x) (y - x) + β / 2 * ‖y - x‖ ^ 2)
    (x₀ z : E) {N : ℕ} (hN : 0 < N) :
    f ((fun x => x - h • gradient f x)^[N] x₀) - f z ≤
      α * (1 - α * h) ^ N * ‖x₀ - z‖ ^ 2 / (2 * (1 - (1 - α * h) ^ N)) ∧
    (α * h < 1 → f ((fun x => x - h • gradient f x)^[N] x₀) - f z ≤
      α / (2 * ((1 - α * h) ^ (-(N : ℤ)) - 1)) * ‖x₀ - z‖ ^ 2)

Exact module and namespace context

Lean proof · strongly_convex_value_le

Write q=1-alpha h, R=||x0-z|| and e_N=f(X_N)-f(z). The existing weighted theorem already derives objective descent and the forced recurrence for the actual gradient iterates. Invoke it directly; its conclusion also allows negative comparator gaps. Positive alpha and h with alpha h<=1 give 0<=q<1. For N>0, q^N<1. The finite geometric identity, multiplied by 2, yields 2alpha h sum(q^k)=2(1-q^N). Multiply the weighted estimate by positive alpha and divide by positive 2(1-q^N). This rational form remains valid at q=0. Under the additional strict inequality alpha h<1, q>0 and q^N>0. Integer negative powers equal inverse positive powers. Multiplying numerator and denominator by q^N proves the exact displayed equality. At q=0 only the preceding rational conclusion applies; the negative-power formula is undefined in ordinary real arithmetic.

Braces mark parameters Lean can infer; square brackets request structures such as a measurable space or probability measure. Named hypotheses are mathematical premises, not facts established by this declaration. Section parameters are described in the mathematical hypotheses above; the module link retains their exact source context.

theorem strongly_convex_value_le {f : E → ℝ} {α β h : ℝ} (hf : ContDiff ℝ 1 f)
    (hsc : StrongConvexOn univ α f) (hα : 0 < α) (hh : 0 < h) (hstep : β * h ≤ 1)
    (hcoeff : α * h ≤ 1)
    (hu : ∀ x y, f y ≤ f x + inner ℝ (gradient f x) (y - x) + β / 2 * ‖y - x‖ ^ 2)
    (x₀ z : E) {N : ℕ} (hN : 0 < N) :
    f ((fun x => x - h • gradient f x)^[N] x₀) - f z ≤
      α * (1 - α * h) ^ N * ‖x₀ - z‖ ^ 2 / (2 * (1 - (1 - α * h) ^ N)) ∧
    (α * h < 1 → f ((fun x => x - h • gradient f x)^[N] x₀) - f z ≤
      α / (2 * ((1 - α * h) ^ (-(N : ℤ)) - 1)) * ‖x₀ - z‖ ^ 2) := by
  have hq : 0 ≤ 1 - α * h := by linarith
  have hqlt : 1 - α * h < 1 := by nlinarith
  have he := gradient_descent_weighted_value_bound hf hsc hh.le hstep (by linarith) hu x₀ z N
  have hs := geom_sum_mul_neg (1 - α * h) N
  have hp : (1 - α * h) ^ N < 1 := pow_lt_one₀ hq hqlt (Nat.ne_of_gt hN)
  have hr : f ((fun x => x - h • gradient f x)^[N] x₀) - f z ≤
      α * (1 - α * h) ^ N * ‖x₀ - z‖ ^ 2 / (2 * (1 - (1 - α * h) ^ N)) := by
    apply (le_div_iff₀ (by positivity : 0 < 2 * (1 - (1 - α * h) ^ N))).mpr
    have hem := mul_le_mul_of_nonneg_left he hα.le
    have hid : α * (2 * h * ∑ k ∈ range N, (1 - α * h) ^ k) =
        2 * (1 - (1 - α * h) ^ N) := by nlinarith [hs]
    rw [← mul_assoc, hid] at hem
    nlinarith [hem]
  refine ⟨hr, ?_⟩
  intro hstrict
  have hqp : 0 < (1 - α * h) ^ N := pow_pos (by linarith) N
  have heq : α * (1 - α * h) ^ N * ‖x₀ - z‖ ^ 2 /
      (2 * (1 - (1 - α * h) ^ N)) =
      α / (2 * ((1 - α * h) ^ (-(N : ℤ)) - 1)) * ‖x₀ - z‖ ^ 2 := by
    rw [zpow_neg, zpow_natCast]
    field_simp
  rwa [heq] at hr

end AutoSamplingTheory.TechnicalLemmas.Analysis.GradientDescentRates

Exact module and namespace context

Scope and omitted-condition boundaries

  • These are public integrations of the existing weighted theorem and previously compiled test normalizations. The new representation edge is the exact inverse-power equality; no new descent or recurrence proof is claimed.
  • C1 on a complete real Hilbert space and arbitrary comparator generalize the C2 Euclidean minimizer-based source rate. Source smoothness is represented by its global quadratic upper model. The condition beta*h<=1 agrees with h<=1/beta when beta>0.
  • Finite normalized bounds require h>0 and N>0. No real-valued normalized h=0 or N=0 assertion, analytic alpha-to-zero limit, iteration-complexity theorem, minimum existence, Riemannian or stochastic result is claimed.
  • The rational coefficient equals zero at q=0 and N>0. With an actual minimizing comparator it forces exact objective optimality. This does not make the source inverse-power expression meaningful at zero.

Source and reuse

ASTIS parents called

Mathlib API called (external library)

  • geom_sum_mul_neg
  • pow_lt_one₀
  • pow_pos
  • zpow_neg
  • zpow_natCast
  • le_div_iff₀

Mathematical sources

ASTIS prose is not a quotation or a source-equivalence certificate. Definitions and aliases are explained as constructions, not counted as new mathematical proofs.