1 / 27

Embedding Metric Spaces in Their Intrinsic Dimension

Embedding Metric Spaces in Their Intrinsic Dimension. Ittai Abraham , Yair Bartal*, Ofer Neiman The Hebrew University * also Caltech. Emebdding Metric Spaces. Metric spaces (X,d X ), (Y,d Y ) Embedding is a function f : X → Y Distortion is the minimal α such that

haines
Download Presentation

Embedding Metric Spaces in Their Intrinsic Dimension

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Embedding Metric Spaces in Their Intrinsic Dimension Ittai Abraham , Yair Bartal*, Ofer Neiman The Hebrew University * also Caltech

  2. Emebdding Metric Spaces • Metric spaces (X,dX), (Y,dY) • Embedding is a function f : X→Y • Distortion is the minimal α such that dX(x,y)≤dY(f(x),f(y))≤α·dX(x,y)

  3. Intrinsic Dimension • Doubling Constant : The minimal λ such any ball of radius r>0, can be covered by λ balls of radius r/2. • Doubling Dimension : dim(X) = log2λ. • The problem: Relation between metric dimension to intrinsic dimension.

  4. Previous Results • Given a λ-doubling finite metric space (X,d) and 0<γ<1, it’s snow-flake version (X,dγ) can be embedded into Lp with distortion and dimension depending only onλ[Assouad 83]. • Conjecture (Assouad) : This hold for γ=1. • Disproved by Semmes. • A lower bound on distortion of for L2, with a matching upper bound [GKL 03].

  5. Rephrasing the Question • Is there a low-distortion embedding for a finite metric space in its intrinsic dimension? Main result : Yes.

  6. Main Results • Any finite metric space (X,d) embeds into Lp: • With distortion O(log1+θn) and dimension O(dim(X)/θ), for any θ>0. • With constant average distortion and dimension O(dim(X)log(dim(X))).

  7. Additional Result • Any finite metric space (X,d) embeds into Lp: • With distortion and dimension . ( For all D≤ (log n)/dim(X) ). • In particular Õ(log2/3n) distortion and dimension into L2. • Matches best known distortion result [KLMN 03] for D=(log n)/dim(X) , with dimension O(log n log(dim(X))).

  8. Distance Oracles • Compact data structure that approximately answers distance queries. • For general n-point metrics: • [TZ 01]O(k) stretch with O(kn1/k) bits per label. • For a finite λ-doubling metric: • O(1) average stretch with Õ(log λ) bits per label. • O(k) stretch with Õ(λ1/k) bits per label. Follows from variation on “snow-flake” embedding (Assouad).

  9. First Result • Thm: For any finite λ-doubling metric space (X,d) on n points and any 0<θ<1 there exists an embedding of (X,d) into Lpwith distortion O(log1+θn) and dimension O((log λ)/θ).

  10. Probabilistic Partitions • P={S1,S2,…St} is a partition of Xif • P(x)is the cluster containing x. • Pis Δ-bounded if diam(Si)≤Δfor all i. • A probabilistic partitionP is a distribution over a set of partitions. • A Δ-bounded P is η-padded if for all xєX :

  11. η-padded Partitions • The parameter η determines the quality of the embedding. • [Bartal 96]:η=Ω(1/log n) for any metric space. • [CKR01+FRT03]:Improved partitions with η(x)=1/log(ρ(x,Δ)). • [GKL 03] :η=Ω(1/log λ) for λ-doubling metrics. • [KLMN 03]:Used to embed general + doubling metrics into Lp : distortion O((log λ)1-1/p(log n)1/p), dimension O(log2n). The local growth rate of x at radius r is:

  12. Uniform Local Padding Lemma • A local padding : padding probability for x is independent of the partition outside B(x,Δ). • A uniform padding : padding parameter η(x) is equal for all points in the same cluster. • There exists a Δ-bounded prob. partition with local uniform padding parameter η(x) : • η(x)>Ω(1/log λ) • η(x)> Ω(1/log(ρ(x,Δ))) C1 C2 v2 v1 v3 η(v1)  η(v3) 

  13. Plan: • A simpler result of: • Distortion O(log n). • Dimension O(loglog n·log λ). • Obtaining lower dimension of O(log λ). • Brief overview of: • Constant average distortion. • Distortion-dimension tradeoff.

  14. Embeddinginto one dimension • For each scale iєZ, create uniformly padded local probabilistic 8i-bounded partition Pi. • For each cluster choose σi(S)~Ber(½) i.i.d. fi(x)=σi(Pi(x))·min{ηi-1(x)·d(x,X\Pi(x)), 8i} • Deterministic upper bound : |f(x)-f(y)| ≤ O(logn·d(x,y)). using Pi x d(x,X\Pi(x)

  15. Lower Bound - Overview • Create a ri-net for all integers i. • Define success event for a pair (u,v) in the ri-net, d(u,v)≈8i : as having contribution >8i/4 , for many coordinates. • In every coordinate, a constant probability of having contribution for a net pair (u,v). • Use Lovasz Local Lemma. • Show lower bound for other pairs.

  16. Lower Bound – Other Pairs? • x,y some pair, d(x,y)≈8i. u,v the nearest in the ri-net to x,y. • Suppose that |f(u)-f(v)|>8i/4. • We want to choose the net such that |f(u)-f(x)|<8i/16, chooseri= 8i/(16·log n). • Using the upper bound |f(u)-f(x)| ≤ log n·d(u,x) ≤ 8i/16 • |f(x)-f(y)| ≥ |f(u)-f(v)|-|f(u)-f(x)|-|f(v)-f(y)| ≥ 8i/4-2·8i/16 = 8i/8. 8i/(16log n) v u x y

  17. Lower Bound: v u • ri-net pair (u,v). Can assume that 8i≈d(u,v)/4. • It must be that Pi(u)≠Pi(v) • With probability ½ :d(u,X\Pi(u))≥ηi8i • With probability ¼ : σi(Pi(u))=1 and σi(Pi(v))=0

  18. Lower Bound – Net Pairs • d(u,v)≈8i. Consider • If R<8i/2 : • With prob. 1/8 fi(u)-fi(v)≥ 8i. • If R≥ 8i/2 : • With prob. 1/4 fi(u)=fi(v)=0. • In any case • Lower scales do not matter The good event for pair in scale i depend on higher scales, but has constant probability given any outcome for them. Oblivious to lower scales. v u ηi(u) 8i

  19. Local Lemma • Lemma (Lovasz): Let A1,…Anbe “bad” events. G=(V,E) a directed graph with vertices corresponding to events with out-degree at most d. Let c:V→Nbe “rating” function of event such that (Ai,Aj)єE then c(Ai)≥c(Aj), if and then Rating = radius of scale.

  20. Lower Bound – Net Pairs • A success eventE(u,v) for a net pair u,v : there is contribution from at least 1/16 of the coordinates. • Locality of partition – the net pair depend only on “nearby” points, with distance < 8i. • Doubling constant λ, and ri≈8i/log n - there are at most λloglogn such points, so d=λloglogn. • Taking D=O(logλ·loglog n) coordinates will give roughly e-D= λ-loglogn failure probability. • By the local lemma, there is exists an embedding such that E(u,v) holds for all net pairs.

  21. Obtaining Lower Dimension • To use the LLL, probability to fail in more than 15/16 of the coordinates must be < λ-loglogn • Instead of taking more coordinates, increase the success probability in each coordinate. • If probability to obtain contribution in each coordinate >1-1/log n, it is enough to take O(log λ) coordinates. Similarly, if failure prob. in each coordinate < log-θn, enough to take O((log λ)/θ) coordinates

  22. Using Several Scales • Create nets only every θloglog n scales. • A pair (x,y) in scale i’ (i.e. d(x,y)≈8i’) will find a close net pair in nearest smaller scale i. • 8i’<logθn·8i, so lose a factor of logθn in the distortion. • Consider scales i-θloglog n,…,i. i+θloglog n i’ θloglog n > i i-θloglog n

  23. Using Several Scales • Take u,v in the net with d(u,v)≈8i. • A success in one of these scales will give contribution >8i-θloglog n = 8i/logθn. • The success for u,v in each scale is : • Unaffected by higher scales events • Independent of events “far away” in the same scale. • Oblivious to events in lower scales. • Probability that all scales failed<(7/8)θloglog n. • Take only D=O((log λ)/θ) coordinates. Lose a factor of logθn inthe distortion` i+θloglog n i i-θloglog n

  24. Constant Average Distortion • Scaling distortion– for every 0<ε<1 at most ε·n2 pairs with distortion > polylog(1/ε). • Upper bound of log(1/ε), by standard techniques. • Lower bound: • Define a net for any scale i>0and ε=exp{-8j}. • Every pair (x,y) needs contribution that depends on: • d(x,y). • Theε-value of x,y. • Sieve the nets to avoid dependencies between different scales and different values of ε. • Show that if a net pair succeeded, the points near it will also succeed.

  25. Constant Average Distortion • Lower bound cont… • The local Lemma graph depends on ε, use the general case of local Lemma. • For a net pair (u,v) in scale 8i– consider scales: 8i-loglog(1/ε),…,8i-loglog(1/ε)/2. • Requires dimension O(log λ·loglog λ). The net depends on λ.

  26. Distortion-Dimension Tradeoff • Distortion : • Dimension : • Instead of assigning all scales to a single coordinate: • For each point x: Divide the scales into D bunches of coordinates, in each • Create a hierarchical partition. D ≤ (log n)/log λ Upper bound needs the x,y scales to be in the same coordinates

  27. Conclusion • Main result: • Embedding metrics into their intrinsic dimension. • Open problem: • Best distortion in dimension O(log λ). • Dimension reduction in L2 : • For a doubling subset of L2 ,is there an embedding into L2 with O(1) distortion and dimension O(dim(X))? For p>2 there is a doubling metric space requiring dimension at least Ω(log n) for embedding into LPwith distortion O(log1/pn).

More Related