Upload
others
View
3
Download
0
Embed Size (px)
Citation preview
The Exponential Formula for the Wasserstein Metric.Katy CraigUCLA
SIAM Annual Meeting, ChicagoJuly 8, 2014
1 / 22
Plan.
• Gradient flow
• Discrete gradient flow
• Euler-Lagrange equation
• Exponential formula
2 / 22
Plan.
• Gradient flow
• Discrete gradient flow
• Euler-Lagrange equation
• Exponential formula
3 / 22
Gradient Flow.∂u(t)
∂t= −∇E(u(t)), u(0) = u
4 / 22
Gradient Flow.∂u(t)
∂t= −∇E(u(t)), u(0) = u
Heat Equation as Gradient Flow on L2(Rd)
4 / 22
Gradient Flow.∂u(t)
∂t= −∇E(u(t)), u(0) = u
Heat Equation as Gradient Flow on L2(Rd)L2(Rd) gradient:
(∇L2E(u), v)L2 = limh→0
E(u+ hv)− E(u)h
for all v ∈ L2(Rd)
4 / 22
Gradient Flow.∂u(t)
∂t= −∇E(u(t)), u(0) = u
Heat Equation as Gradient Flow on L2(Rd)L2(Rd) gradient:
(∇L2E(u), v)L2 = limh→0
E(u+ hv)− E(u)h
for all v ∈ L2(Rd)
Thus, for E(u) = 12∫|∇u|2,
(∇L2E(u), v)L2 = limh→0
1
2
∫|∇(u+ hv)|2 −
∫|∇u|2
h= (∇u,∇v)L2 = (−∆u, v)L2 .
4 / 22
Gradient Flow.∂u(t)
∂t= −∇E(u(t)), u(0) = u
Heat Equation as Gradient Flow on L2(Rd)L2(Rd) gradient:
(∇L2E(u), v)L2 = limh→0
E(u+ hv)− E(u)h
for all v ∈ L2(Rd)
Thus, for E(u) = 12∫|∇u|2,
(∇L2E(u), v)L2 = limh→0
1
2
∫|∇(u+ hv)|2 −
∫|∇u|2
h= (∇u,∇v)L2 = (−∆u, v)L2 .
Hence, the L2 gradient flow of E is
∂u/∂t = −∇L2E(u) = −(−∆u) = ∆u .
4 / 22
Gradient Flow.∂u(t)
∂t= −∇E(u(t)), u(0) = u
Heat Equation as Gradient Flow on L2(Rd)L2(Rd) gradient:
(∇L2E(u), v)L2 = limh→0
E(u+ hv)− E(u)h
for all v ∈ L2(Rd)
Thus, for E(u) = 12∫|∇u|2,
(∇L2E(u), v)L2 = limh→0
1
2
∫|∇(u+ hv)|2 −
∫|∇u|2
h= (∇u,∇v)L2 = (−∆u, v)L2 .
Hence, the L2 gradient flow of E is
∂u/∂t = −∇L2E(u) = −(−∆u) = ∆u .
Note: ∇L2E(u) = δEδu4 / 22
Examples of Hilbert Space Gradient Flow.
PDE Energy Functional MetricAllen-Cahn d
dtu = ∆u− F ′(u) E(u) = 1
2
∫ [|∇u|2 + F (u)
]L2
Cahn-Hilliard ddtu = ∆(∆u− F ′(u)) E(u) = 1
2
∫ [|∇u|2 + F (u)
]H−1
Porous Media / ddtu = ∆um E(u) = 1
m+1
∫um+1 H−1
Fast Diffusion
5 / 22
Examples of Hilbert Space Gradient Flow.
PDE Energy Functional MetricAllen-Cahn d
dtu = ∆u− F ′(u) E(u) = 1
2
∫ [|∇u|2 + F (u)
]L2
Cahn-Hilliard ddtu = ∆(∆u− F ′(u)) E(u) = 1
2
∫ [|∇u|2 + F (u)
]H−1
Porous Media / ddtu = ∆um E(u) = 1
m+1
∫um+1 H−1
Fast Diffusion
Why gradient flow?• Free estimates, e.g. |u(t)− v(t)| ≤ e−λt|u(0)− v(0)|• Method to construct and approximate solutions (discrete gradient flow)
5 / 22
Wasserstein Gradient Flow.∂µ(t)
∂t= −∇W2E(µ(t)), µ(0) = µ
6 / 22
Wasserstein Gradient Flow.∂µ(t)
∂t= −∇W2E(µ(t)), µ(0) = µ
Simplifying assumptions:∫|x|2dµ < +∞, µ
Wasserstein Gradient Flow.∂µ(t)
∂t= −∇W2E(µ(t)), µ(0) = µ
Simplifying assumptions:∫|x|2dµ < +∞, µ
Wasserstein Gradient Flow.∂µ(t)
∂t= −∇W2E(µ(t)), µ(0) = µ
Simplifying assumptions:∫|x|2dµ < +∞, µ
Wasserstein Gradient Flow.∂µ(t)
∂t= −∇W2E(µ(t)), µ(0) = µ
Simplifying assumptions:∫|x|2dµ < +∞, µ
Geodesics and Convexity.Geodesics:
µ(α) = (αtνµ + (1− α)id)#µ is the geodesic from µ to ν at time α,
W2(µ(α), µ(β)) = |α− β|W2(µ, ν) .
7 / 22
Geodesics and Convexity.Geodesics:
µ(α) = (αtνµ + (1− α)id)#µ is the geodesic from µ to ν at time α,
W2(µ(α), µ(β)) = |α− β|W2(µ, ν) .
Convexity:
E is convex in case
E(µ(α)) ≤ (1− α)E(µ(0)) + αE(µ(1)) .
7 / 22
Geodesics and Convexity.Geodesics:
µ(α) = (αtνµ + (1− α)id)#µ is the geodesic from µ to ν at time α,
W2(µ(α), µ(β)) = |α− β|W2(µ, ν) .
Convexity:
E is convex in case
E(µ(α)) ≤ (1− α)E(µ(0)) + αE(µ(1)) .
7 / 22
Geodesics and Convexity.Geodesics:
µ(α) = (αtνµ + (1− α)id)#µ is the geodesic from µ to ν at time α,
W2(µ(α), µ(β)) = |α− β|W2(µ, ν) .
Convexity:
E is convex in case
E(µ(α)) ≤ (1− α)E(µ(0)) + αE(µ(1)) .
Assumption: E is lower semicontinuous and convex.
7 / 22
The Wasserstein Metric's ``Gradient''.
By a similar computation as in the L2 case,(∇W2E(µ),
∂µ
∂t
∣∣∣∣t=0
)µ
= limt→0
E(µ(t))− E(µ)t
for all ∂µ∂t
,
implies∇W2E(µ) = −∇ ·
(µ∇δE
δµ
).
8 / 22
The Wasserstein Metric's ``Gradient''.
By a similar computation as in the L2 case,(∇W2E(µ),
∂µ
∂t
∣∣∣∣t=0
)µ
= limt→0
E(µ(t))− E(µ)t
for all ∂µ∂t
,
implies∇W2E(µ) = −∇ ·
(µ∇δE
δµ
).
Therefore,
∂µ(t)
∂t= −∇W2E(µ(t)) ⇐⇒
∂µ(t)
∂t= ∇ ·
(µ∇δE
δµ
).
8 / 22
Examples of Wasserstein Gradient Flow.
PDE Energy FunctionalPorous Media / ∂
∂tµ = ∆µm E(µ) = 1
m−1
∫ρ(x)mdx
Fast DiffusionFokker Planck ∂
∂tµ = ∆µ+∇ · (µ∇V ) E(µ) =
∫ρ(x) log ρ(x) + V (x)ρ(x)dx
Aggregation ∂∂tu = ∇ · (µ∇K ∗ µ) E(µ) = 1
2
∫ ∫ρ(x)K(x− y)ρ(y)dxdy
9 / 22
Examples of Wasserstein Gradient Flow.
PDE Energy FunctionalPorous Media / ∂
∂tµ = ∆µm E(µ) = 1
m−1
∫ρ(x)mdx
Fast DiffusionFokker Planck ∂
∂tµ = ∆µ+∇ · (µ∇V ) E(µ) =
∫ρ(x) log ρ(x) + V (x)ρ(x)dx
Aggregation ∂∂tu = ∇ · (µ∇K ∗ µ) E(µ) = 1
2
∫ ∫ρ(x)K(x− y)ρ(y)dxdy
Why gradient flow?• Free estimates, e.g. W2(µ(t), ν(t)) ≤ e−λtW2(µ(0), ν(0))• Method to construct and approximate solutions (discrete gradient flow)
9 / 22
Plan.
• Gradient flow
• Discrete gradient flow
• Euler-Lagrange equation
• Exponential formula
10 / 22
Discrete Gradient Flow: Euclidean Space.Gradient flow:
du(t)
dt= −∇E(u(t)), u(0) = u ∈ Rd
11 / 22
Discrete Gradient Flow: Euclidean Space.Gradient flow:
du(t)
dt= −∇E(u(t)), u(0) = u ∈ Rd
Implicit Euler method:
un − un−1τ
= −∇E(un), u0 = u
11 / 22
Discrete Gradient Flow: Euclidean Space.Gradient flow:
du(t)
dt= −∇E(u(t)), u(0) = u ∈ Rd
Implicit Euler method:
un − un−1τ
+∇E(un) = 0, u0 = u
11 / 22
Discrete Gradient Flow: Euclidean Space.Gradient flow:
du(t)
dt= −∇E(u(t)), u(0) = u ∈ Rd
Implicit Euler method:
un − un−1τ
+∇E(un) = 0, u0 = u
Given un−1, compute un using that it is a critical point of
Φ(v) =1
2τ|v − un−1|2 + E(v) .
11 / 22
Discrete Gradient Flow: Euclidean Space.Gradient flow:
du(t)
dt= −∇E(u(t)), u(0) = u ∈ Rd
Implicit Euler method:
un − un−1τ
+∇E(un) = 0, u0 = u
Given un−1, compute un using that it is a critical point the unique minimizer of
Φ(v) =1
2τ|v − un−1|2 + E(v) .
11 / 22
Discrete Gradient Flow: Euclidean Space.Gradient flow:
du(t)
dt= −∇E(u(t)), u(0) = u ∈ Rd
Implicit Euler method:
un − un−1τ
+∇E(un) = 0, u0 = u
Given un−1, compute un using that it is a critical point the unique minimizer of
Φ(v) =1
2τ|v − un−1|2 + E(v) .
Theorem (Exponential Formula)Let τ = t/n. Then limn→∞ un = u(t).
11 / 22
Discrete Gradient Flow: Wasserstein Metric.Want to say... given µn−1, let µn be the unique minimizer of
Φ(v) =1
2τW 22 (ν, µn−1) + E(ν) .
12 / 22
Discrete Gradient Flow: Wasserstein Metric.Want to say... given µn−1, let µn be the unique minimizer of
Φ(v) =1
2τW 22 (ν, µn−1) + E(ν) .
Problem: ν 7→W 22 (ν, µn−1) is not convex, so Φ may not have a uniqueminimum.
12 / 22
Discrete Gradient Flow: Wasserstein Metric.Want to say... given µn−1, let µn be the unique minimizer of
Φ(v) =1
2τW 22 (ν, µn−1) + E(ν) .
Problem: ν 7→W 22 (ν, µn−1) is not convex, so Φ may not have a uniqueminimum.
Need additional assumptions on E:• coercive• convex along generalized geodesics
12 / 22
Discrete Gradient Flow: Wasserstein Metric.Want to say... given µn−1, let µn be the unique minimizer of
Φ(v) =1
2τW 22 (ν, µn−1) + E(ν) .
Problem: ν 7→W 22 (ν, µn−1) is not convex, so Φ may not have a uniqueminimum.
Need additional assumptions on E:• coercive• convex along generalized geodesics
Proposition (AGS)For all τ > 0, there exists a unique minimizer of Φ(ν), so the discrete gradientflow is well defined.
12 / 22
Plan.
• Gradient flow
• Discrete gradient flow
• Euler-Lagrange equation
• Exponential formula
13 / 22
Euler-Lagrange Equation.In the Euclidean case,
un = argminv
{1
2τ|v − un−1|2 + E(v)
}⇐⇒ un − un−1
τ= −∇E(un) .
14 / 22
Euler-Lagrange Equation.In the Euclidean case,
un = argminv
{1
2τ|v − un−1|2 + E(v)
}⇐⇒ un − un−1
τ= −∇E(un) .
In the Wasserstein case,
Proposition (AGS, C.)
µn = argminν
{1
2τW 22 (ν, µn−1) + E(ν)
}⇐⇒ 1
τ(tµn−1µn − id) ∈ ∂sE(µn) .
14 / 22
Euler-Lagrange Equation.In the Euclidean case,
un = argminv
{1
2τ|v − un−1|2 + E(v)
}⇐⇒ un − un−1
τ= −∇E(un) .
In the Wasserstein case,
Proposition (AGS, C.)
µn = argminν
{1
2τW 22 (ν, µn−1) + E(ν)
}⇐⇒ 1
τ(tµn−1µn − id) ∈ ∂sE(µn) .
Key property of subdifferential: for E convex, 0 ∈ ∂E(µ) ⇐⇒ µ minimizes E.
14 / 22
Sketch of Proof: Euler-Lagrange Equation.Proposition (AGS, C.)
µn = argminν
{1
2τW 22 (ν, µn−1) + E(ν)
}⇐⇒ 1
τ(tµn−1µn − id) ∈ ∂sE(µn) .
15 / 22
Sketch of Proof: Euler-Lagrange Equation.Proposition (AGS, C.)
µn = argminν
{1
2τW 22 (ν, µn−1) + E(ν)
}⇐⇒ 1
τ(tµn−1µn − id) ∈ ∂sE(µn) .
Proof:Let Φ(ν) = 12τW 22 (ν, µn−1) + E(ν).
15 / 22
Sketch of Proof: Euler-Lagrange Equation.Proposition (AGS, C.)
µn = argminν
{1
2τW 22 (ν, µn−1) + E(ν)
}⇐⇒ 1
τ(tµn−1µn − id) ∈ ∂sE(µn) .
Proof:Let Φ(ν) = 12τW 22 (ν, µn−1) + E(ν).
=⇒ [AGS, Otto]: minimality implies Φ(t#µn) ≥ Φ(µn); expand both sides.
15 / 22
Sketch of Proof: Euler-Lagrange Equation.Proposition (AGS, C.)
µn = argminν
{1
2τW 22 (ν, µn−1) + E(ν)
}⇐⇒ 1
τ(tµn−1µn − id) ∈ ∂sE(µn) .
Proof:Let Φ(ν) = 12τW 22 (ν, µn−1) + E(ν).
=⇒ [AGS, Otto]: minimality implies Φ(t#µn) ≥ Φ(µn); expand both sides.
⇐= want to say...• 1
τ (tµn−1µn − id) ∈ ∂sE(µn)
• hence 0 ∈ ∂Φ(µn)• hence by key property, µn minimizes Φ
15 / 22
Sketch of Proof: Euler-Lagrange Equation.Proposition (AGS, C.)
µn = argminν
{1
2τW 22 (ν, µn−1) + E(ν)
}⇐⇒ 1
τ(tµn−1µn − id) ∈ ∂sE(µn) .
Proof:Let Φ(ν) = 12τW 22 (ν, µn−1) + E(ν).
=⇒ [AGS, Otto]: minimality implies Φ(t#µn) ≥ Φ(µn); expand both sides.
⇐= want to say...• 1
τ (tµn−1µn − id) ∈ ∂sE(µn)
• hence 0 ∈ ∂Φ(µn)• hence by key property, µn minimizes Φ
Problem: ν 7→W 22 (ν, µn−1) is not convex, so Φ may not be convex.
15 / 22
Sketch of Proof: Euler-Lagrange Equation.Solution: generalized geodesics and transport metrics
• [AGS] ν 7→W 22 (ν, µ) is not convex (along all geodesics)• [AGS] ν 7→W 22 (ν, µ) is convex along generalized geodesics with base µ• [C.] the generalized geodesics with base µ are not arbitrary curves: they are
exactly the geodesics of the transport metric with base µ
16 / 22
Sketch of Proof: Euler-Lagrange Equation.Solution: generalized geodesics and transport metrics
• [AGS] ν 7→W 22 (ν, µ) is not convex (along all geodesics)• [AGS] ν 7→W 22 (ν, µ) is convex along generalized geodesics with base µ• [C.] the generalized geodesics with base µ are not arbitrary curves: they are
exactly the geodesics of the transport metric with base µ
WassersteinMetric: W2(µ, ν) =(∫
|tνµ − id|2dµ)1/2
TransportMetric: W2,ω(µ, ν) =(∫
|tµω − tνω|2dω)1/2
• ν 7→W 22,ω(ν, µ) is convex• W2(µ, ν) ≤W2,ω(µ, ν)
16 / 22
Plan.
• Gradient flow
• Discrete gradient flow
• Euler-Lagrange equation
• Exponential formula
17 / 22
Exponential Formula.Theorem (AGS)Let τ = t/n. Then limn→∞ µn = µ(t).
18 / 22
Exponential Formula.Theorem (AGS)Let τ = t/n. Then limn→∞ µn = µ(t).
• the limit exists• the limit is a solution to the gradient flow
18 / 22
Exponential Formula.Theorem (AGS)Let τ = t/n. Then limn→∞ µn = µ(t).
• the limit exists• the limit is a solution to the gradient flow
SketchofProof, alaCrandallandLiggett:
18 / 22
Exponential Formula.Theorem (AGS)Let τ = t/n. Then limn→∞ µn = µ(t).
• the limit exists• the limit is a solution to the gradient flow
SketchofProof, alaCrandallandLiggett:Let Jτ be the function Jτu = argminv
{12τ |v − u|
2 + E(v)}
=⇒ Jnτ u0 = un.
18 / 22
Exponential Formula.Theorem (AGS)Let τ = t/n. Then limn→∞ µn = µ(t).
• the limit exists• the limit is a solution to the gradient flow
SketchofProof, alaCrandallandLiggett:Let Jτ be the function Jτu = argminv
{12τ |v − u|
2 + E(v)}
=⇒ Jnτ u0 = un.
..1 Contractioninequality
18 / 22
Exponential Formula.Theorem (AGS)Let τ = t/n. Then limn→∞ µn = µ(t).
• the limit exists• the limit is a solution to the gradient flow
SketchofProof, alaCrandallandLiggett:Let Jτ be the function Jτu = argminv
{12τ |v − u|
2 + E(v)}
=⇒ Jnτ u0 = un.
..1 ContractioninequalityBanach space: ∥Jτu− Jτv∥ ≤ ∥u− v∥
18 / 22
Exponential Formula.Theorem (AGS)Let τ = t/n. Then limn→∞ µn = µ(t).
• the limit exists• the limit is a solution to the gradient flow
SketchofProof, alaCrandallandLiggett:Let Jτ be the function Jτu = argminv
{12τ |v − u|
2 + E(v)}
=⇒ Jnτ u0 = un.
..1 ContractioninequalityBanach space: ∥Jτu− Jτv∥ ≤ ∥u− v∥
18 / 22
Exponential Formula.Theorem (AGS)Let τ = t/n. Then limn→∞ µn = µ(t).
• the limit exists• the limit is a solution to the gradient flow
SketchofProof, alaCrandallandLiggett:Let Jτ be the function Jτu = argminv
{12τ |v − u|
2 + E(v)}
=⇒ Jnτ u0 = un.
..1 ContractioninequalityBanach space: ∥Jτu− Jτv∥ ≤ ∥u− v∥
Theorem (Carlen, C.)W 22 (Jτµ, Jτν) ≤W 22 (µ, ν) +O(τ2)
18 / 22
Exponential Formula...2 Largevssmalltimesteps, 0 < h ≤ τ
19 / 22
Exponential Formula...2 Largevssmalltimesteps, 0 < h ≤ τ
Banach space: Jτu = Jh[τ−hτ Jτu+
hτ u]
19 / 22
Exponential Formula...2 Largevssmalltimesteps, 0 < h ≤ τ
Banach space: Jτu = Jh[τ−hτ Jτu+
hτ u]
Lemma (Jost, Mayer, C.)Jτµ = Jh
[(τ−hτ t
Jτµµ +
hτ id)
#µ]
19 / 22
Exponential Formula...2 Largevssmalltimesteps, 0 < h ≤ τ
Banach space: Jτu = Jh[τ−hτ Jτu+
hτ u]
Lemma (Jost, Mayer, C.)Jτµ = Jh
[(τ−hτ t
Jτµµ +
hτ id)
#µ]
19 / 22
Exponential Formula...3 Recursiveinequality:
20 / 22
Exponential Formula...3 Recursiveinequality:Let µn = Jnτ µ and µm = Jmh µ.
20 / 22
Exponential Formula...3 Recursiveinequality:Let µn = Jnτ µ and µm = Jmh µ.
W 22 (µn, µm) =W22
Jhν︷ ︸︸ ︷[(
τ − hτ
tµnµn−1 +h
τid)
#µn−1], Jhµm−1
20 / 22
Exponential Formula...3 Recursiveinequality:Let µn = Jnτ µ and µm = Jmh µ.
W 22 (µn, µm) =W22
Jhν︷ ︸︸ ︷[(
τ − hτ
tµnµn−1 +h
τid)
#µn−1], Jhµm−1
≤W 22 (ν, µm−1) +O(h2)
20 / 22
Exponential Formula...3 Recursiveinequality:Let µn = Jnτ µ and µm = Jmh µ.
W 22 (µn, µm) =W22
Jhν︷ ︸︸ ︷[(
τ − hτ
tµnµn−1 +h
τid)
#µn−1], Jhµm−1
≤W 22 (ν, µm−1) +O(h2)
≤W 22,µn−1(ν, µm−1) +O(h2)
20 / 22
Exponential Formula...3 Recursiveinequality:Let µn = Jnτ µ and µm = Jmh µ.
W 22 (µn, µm) =W22
Jhν︷ ︸︸ ︷[(
τ − hτ
tµnµn−1 +h
τid)
#µn−1], Jhµm−1
≤W 22 (ν, µm−1) +O(h2)
≤W 22,µn−1(ν, µm−1) +O(h2)
≤ τ − hτ
W 22,µn−1(µn, µm−1) +h
τW 22,µn−1(µn−1, µm−1) +O(h
2)
20 / 22
Exponential Formula...3 Recursiveinequality:Let µn = Jnτ µ and µm = Jmh µ.
W 22 (µn, µm) =W22
Jhν︷ ︸︸ ︷[(
τ − hτ
tµnµn−1 +h
τid)
#µn−1], Jhµm−1
≤W 22 (ν, µm−1) +O(h2)
≤W 22,µn−1(ν, µm−1) +O(h2)
≤ τ − hτ
W 22,µn−1(µn, µm−1) +h
τW 22,µn−1(µn−1, µm−1) +O(h
2)
≤ τ − hτ
W 22 (µn, µm−1) +h
τW 22 (µn−1, µm−1) +O(h2)
20 / 22
Exponential Formula...3 Recursiveinequality:Let µn = Jnτ µ and µm = Jmh µ.
W 22 (µn, µm) =W22
Jhν︷ ︸︸ ︷[(
τ − hτ
tµnµn−1 +h
τid)
#µn−1], Jhµm−1
≤W 22 (ν, µm−1) +O(h2)
≤W 22,µn−1(ν, µm−1) +O(h2)
≤ τ − hτ
W 22,µn−1(µn, µm−1) +h
τW 22,µn−1(µn−1, µm−1) +O(h
2)
≤ τ − hτ
W 22 (µn, µm−1) +h
τW 22 (µn−1, µm−1) +O(h2)
W 22 (µn, µm) ≤τ − hτ
W 22 (µn, µm−1) +h
τW 22 (µn−1, µm−1) +O(h2)
20 / 22
Exponential Formula...3 Recursiveinequality:Let µn = Jnτ µ and µm = Jmh µ.
W 22 (µn, µm) ≤τ − hτ
W 22 (µn, µm−1) +h
τW 22 (µn−1, µm−1) +O(h2)
20 / 22
Exponential Formula...3 Recursiveinequality:Let µn = Jnτ µ and µm = Jmh µ.
W 22 (µn, µm) ≤τ − hτ
W 22 (µn, µm−1) +h
τW 22 (µn−1, µm−1) +O(h2)
20 / 22
Exponential Formula.Iterating
W 22 (µn, µm) ≤τ − hτ
W 22 (µn, µm−1) +h
τW 22 (µn−1, µm−1) +O(h2)
with τ = t/n and h = t/m for n ≤ m gives
W2(µn, µm) ≤ O(1√n)
n,m→∞−−−−−→ 0 .
Therefore, the limit exists.
21 / 22
Thank you!
22 / 22
Backup
23 / 22
Wasserstein Gradient Flow.∂µ(t)
∂t= −∇W2E(µ(t)), µ(0) = µ
Wasserstein Metric as ``Riemannian Manifold''*The Wasserstein metric is induced by this inner product (Benamou-Brenier):
W2(µ0, µ1) =
inf{∫ 1
0
∥∇ψ(t)∥µ(t)dt : µ(0) = µ0, µ(1) = µ1,∂µ
∂t+∇ · (∇ψµ) = 0
}.
24 / 22
The Wasserstein Metric's ``Inner Product''* [Otto].
25 / 22
The Wasserstein Metric's ``Inner Product''* [Otto].*DISCLAIMER: "given sufficient regularity," "in the limit", ...
25 / 22
The Wasserstein Metric's ``Inner Product''* [Otto].*DISCLAIMER: "given sufficient regularity," "in the limit", ...
Given µ(t), there exists a velocity field v(x, t) = ∇ψ(x, t) so that
∂µ
∂t+∇ · (∇ψµ) = 0 .
25 / 22
The Wasserstein Metric's ``Inner Product''* [Otto].*DISCLAIMER: "given sufficient regularity," "in the limit", ...
Given µ(t), there exists a velocity field v(x, t) = ∇ψ(x, t) so that
∂µ
∂t+∇ · (∇ψµ) = 0 .
The tangent space at a measure µ is{∂µ
∂t
∣∣∣∣t=0
: µ(0) = µ
}={∇ψ : ψ ∈ C∞c (Rd)
}.
25 / 22
The Wasserstein Metric's ``Inner Product''* [Otto].*DISCLAIMER: "given sufficient regularity," "in the limit", ...
Given µ(t), there exists a velocity field v(x, t) = ∇ψ(x, t) so that
∂µ
∂t+∇ · (∇ψµ) = 0 .
The tangent space at a measure µ is{∂µ
∂t
∣∣∣∣t=0
: µ(0) = µ
}={∇ψ : ψ ∈ C∞c (Rd)
}.
The inner product is(∂µ
∂t,∂̃µ
∂t
)µ
:=
∫∇ψ(x) · ∇ψ̃(x)dµ .
25 / 22
Wasserstein Subdifferential.Wasserstein subdifferential of convex function:
• ξ ∈ ∂E(µ) in case E(ν)− E(µ) ≥∫⟨ξ, tνµ − id⟩dµ for all ν
• ξ ∈ ∂sE(µ) in case E(ν)− E(µ) ≥∫⟨ξ, t − id⟩dµ for all ν and all t#µ = ν.
26 / 22
Generalized Geodesics.• µ(α) = (αtνµ + (1− α)id)#µ is the geodesic from µ to ν• µ(α) = (αtµω + (1− α)tνω)#ω is the gen. geodesic from µ to ν with base ω
27 / 22
Generalized Geodesics.• µ(α) = (αtνµ + (1− α)id)#µ is the geodesic from µ to ν• µ(α) = (αtµω + (1− α)tνω)#ω is the gen. geodesic from µ to ν with base ω
Proposition (AGS)ν 7→W 22 (ν, µ) is convex along gen. geodesics with base µ.
27 / 22
Generalized Geodesics.• µ(α) = (αtνµ + (1− α)id)#µ is the geodesic from µ to ν• µ(α) = (αtµω + (1− α)tνω)#ω is the gen. geodesic from µ to ν with base ω
Proposition (AGS)ν 7→W 22 (ν, µ) is convex along gen. geodesics with base µ.
Thus, E convex along gen. geodesics =⇒Φ(ν) = 12τW
22 (ν, µn−1) + E(ν) convex along gen. geodesics with base µn−1.
27 / 22
Transport Metrics.The transport metric with base µ is W2,µ(ω, ν) :=
(∫|tωµ − tνµ|2dµ
)1/2.
28 / 22
Transport Metrics.The transport metric with base µ is W2,µ(ω, ν) :=
(∫|tωµ − tνµ|2dµ
)1/2.
Proposition (C.)..1 W2,µ is a metric
28 / 22
Transport Metrics.The transport metric with base µ is W2,µ(ω, ν) :=
(∫|tωµ − tνµ|2dµ
)1/2.
Proposition (C.)..1 W2,µ is a metric..2 W2(ω, ν) ≤W2,µ(ω, ν) with equality if µ = ω or µ = ν
28 / 22
Transport Metrics.The transport metric with base µ is W2,µ(ω, ν) :=
(∫|tωµ − tνµ|2dµ
)1/2.
Proposition (C.)..1 W2,µ is a metric..2 W2(ω, ν) ≤W2,µ(ω, ν) with equality if µ = ω or µ = ν..3 the geodesics of W2,µ are the gen. geodesics with base µ
28 / 22
Transport Metrics.The transport metric with base µ is W2,µ(ω, ν) :=
(∫|tωµ − tνµ|2dµ
)1/2.
Proposition (C.)..1 W2,µ is a metric..2 W2(ω, ν) ≤W2,µ(ω, ν) with equality if µ = ω or µ = ν..3 the geodesics of W2,µ are the gen. geodesics with base µ..4 ω 7→W 22,µ(ω, ν) is convex
28 / 22
Transport Metrics.The transport metric with base µ is W2,µ(ω, ν) :=
(∫|tωµ − tνµ|2dµ
)1/2.
Proposition (C.)..1 W2,µ is a metric..2 W2(ω, ν) ≤W2,µ(ω, ν) with equality if µ = ω or µ = ν..3 the geodesics of W2,µ are the gen. geodesics with base µ..4 ω 7→W 22,µ(ω, ν) is convex..5 ξ ∈ ∂sE(ν) =⇒ ξ ◦ tνµ ∈ ∂2,µE(ν)
28 / 22
Transport Metrics.The transport metric with base µ is W2,µ(ω, ν) :=
(∫|tωµ − tνµ|2dµ
)1/2.
Proposition (C.)..1 W2,µ is a metric..2 W2(ω, ν) ≤W2,µ(ω, ν) with equality if µ = ω or µ = ν..3 the geodesics of W2,µ are the gen. geodesics with base µ..4 ω 7→W 22,µ(ω, ν) is convex..5 ξ ∈ ∂sE(ν) =⇒ ξ ◦ tνµ ∈ ∂2,µE(ν)
Proof of Euler-Lagrange equation:1τ (t
µn−1µn − id) ∈ ∂sE(µn) =⇒ µn = argminν
{12τW
22 (ν, µn−1) + E(ν)
}.
28 / 22
Transport Metrics.The transport metric with base µ is W2,µ(ω, ν) :=
(∫|tωµ − tνµ|2dµ
)1/2.
Proposition (C.)..1 W2,µ is a metric..2 W2(ω, ν) ≤W2,µ(ω, ν) with equality if µ = ω or µ = ν..3 the geodesics of W2,µ are the gen. geodesics with base µ..4 ω 7→W 22,µ(ω, ν) is convex..5 ξ ∈ ∂sE(ν) =⇒ ξ ◦ tνµ ∈ ∂2,µE(ν)
Proof of Euler-Lagrange equation:1τ (t
µn−1µn − id) ∈ ∂sE(µn) =⇒ µn = argminν
{12τW
22 (ν, µn−1) + E(ν)
}.
• E convex along gen. geodesics =⇒ convex in W2,µn−1
28 / 22
Transport Metrics.The transport metric with base µ is W2,µ(ω, ν) :=
(∫|tωµ − tνµ|2dµ
)1/2.
Proposition (C.)..1 W2,µ is a metric..2 W2(ω, ν) ≤W2,µ(ω, ν) with equality if µ = ω or µ = ν..3 the geodesics of W2,µ are the gen. geodesics with base µ..4 ω 7→W 22,µ(ω, ν) is convex..5 ξ ∈ ∂sE(ν) =⇒ ξ ◦ tνµ ∈ ∂2,µE(ν)
Proof of Euler-Lagrange equation:1τ (t
µn−1µn − id) ∈ ∂sE(µn) =⇒ µn = argminν
{12τW
22 (ν, µn−1) + E(ν)
}.
• E convex along gen. geodesics =⇒ convex in W2,µn−1• Φ(ν) = 12τW
22 (ν, µn−1) + E(ν) convex in W2,µn−1
28 / 22
Transport Metrics.The transport metric with base µ is W2,µ(ω, ν) :=
(∫|tωµ − tνµ|2dµ
)1/2.
Proposition (C.)..1 W2,µ is a metric..2 W2(ω, ν) ≤W2,µ(ω, ν) with equality if µ = ω or µ = ν..3 the geodesics of W2,µ are the gen. geodesics with base µ..4 ω 7→W 22,µ(ω, ν) is convex..5 ξ ∈ ∂sE(ν) =⇒ ξ ◦ tνµ ∈ ∂2,µE(ν)
Proof of Euler-Lagrange equation:1τ (t
µn−1µn − id) ∈ ∂sE(µn) =⇒ µn = argminν
{12τW
22 (ν, µn−1) + E(ν)
}.
• E convex along gen. geodesics =⇒ convex in W2,µn−1• Φ(ν) = 12τW
22 (ν, µn−1) + E(ν) convex in W2,µn−1
• Since 1τ (tµn−1µn − id) ∈ ∂sE(µn), a computation shows 0 ∈ ∂2,µn−1Φ(µn)
28 / 22
Transport Metrics.The transport metric with base µ is W2,µ(ω, ν) :=
(∫|tωµ − tνµ|2dµ
)1/2.
Proposition (C.)..1 W2,µ is a metric..2 W2(ω, ν) ≤W2,µ(ω, ν) with equality if µ = ω or µ = ν..3 the geodesics of W2,µ are the gen. geodesics with base µ..4 ω 7→W 22,µ(ω, ν) is convex..5 ξ ∈ ∂sE(ν) =⇒ ξ ◦ tνµ ∈ ∂2,µE(ν)
Proof of Euler-Lagrange equation:1τ (t
µn−1µn − id) ∈ ∂sE(µn) =⇒ µn = argminν
{12τW
22 (ν, µn−1) + E(ν)
}.
• E convex along gen. geodesics =⇒ convex in W2,µn−1• Φ(ν) = 12τW
22 (ν, µn−1) + E(ν) convex in W2,µn−1
• Since 1τ (tµn−1µn − id) ∈ ∂sE(µn), a computation shows 0 ∈ ∂2,µn−1Φ(µn)
• Therefore, µn minimizes Φ.28 / 22