communication
play

Communication Complexity David P. Woodruff IBM Almaden Talk - PowerPoint PPT Presentation

Information Theory for Communication Complexity David P. Woodruff IBM Almaden Talk Outline 1. Information Theory Concepts 2. Distances Between Distributions 3. An Example Communication Lower Bound Randomized 1-way Communication


  1. Information Theory for Communication Complexity David P. Woodruff IBM Almaden

  2. Talk Outline 1. Information Theory Concepts 2. Distances Between Distributions 3. An Example Communication Lower Bound – Randomized 1-way Communication Complexity of the INDEX problem 4. Communication Lower Bounds imply space lower bounds for data stream algorithms 5. Techniques for Multi-Player Communication

  3. Discrete Distributions

  4. Entropy (symmetric)

  5. Conditional and Joint Entropy

  6. Chain Rule for Entropy

  7. Conditioning Cannot Increase Entropy continuous

  8. Conditioning Cannot Increase Entropy

  9. Mutual Information • (Mutual Information) I(X ; Y) = H(X) – H(X | Y) = H(Y) – H(Y | X) = I(Y ; X) Note: I(X ; X) = H(X) – H(X | X) = H(X) • (Conditional Mutual Information) I(X ; Y | Z) = H(X | Z) – H(X | Y, Z)

  10. Chain Rule for Mutual Information

  11. Fano’s Inequality Here X -> Y - > X’ is a Markov Chain , meaning X’ and X are independent given Y. “Past and future are conditionally independent given the present” To prove Fano’s Inequality, we need the data processing inequality

  12. Data Processing Inequality • Suppose X -> Y -> Z is a Markov Chain. Then, 𝐽 𝑌 ; 𝑍 ≥ 𝐽(𝑌; 𝑎) • That is, no clever combination of the data can improve estimation • I(X ; Y, Z) = I(X ; Z) + I(X ; Y | Z) = I(X ; Y) + I(X ; Z | Y) • So, it suffices to show I(X ; Z | Y) = 0 • I(X ; Z | Y) = H(X | Y) – H(X | Y, Z) • But given Y, then X and Z are independent, so H(X | Y, Z) = H(X | Y). • Data Processing Inequality implies H(X | Y) ≤ 𝐼 𝑌 𝑎)

  13. Proof of Fano’s Inequality 𝑓 = Pr 𝑌 ≠ 𝑌 ′ , • For any estimator X’ such that X -> Y - > X’ with 𝑄 we have 𝐼 𝑌 𝑍) ≤ 𝐼 𝑄 𝑓 + 𝑄 𝑓 (log 2 𝑌 − 1) . Proof: Let E = 1 if X’ is not equal to X, and E = 0 otherwise. H(E, X | X’) = H(X | X’) + H(E | X, X’) = H(X | X’) H(E, X | X’) = H(E | X’) + H(X | E, X’) ≤ 𝐼 𝑄 𝑓 + H(X | E, X’) But H(X | E, X’) = Pr (E = 0)H(X | X’, E = 0) + Pr (E = 1)H(X | X’, E = 1) ≤ (1 − 𝑄 𝑓 ) ⋅ 0 + 𝑄 𝑓 ⋅ log 2 𝑌 − 1 Combining the above, H(X | X’) ≤ 𝐼 𝑄 𝑓 + 𝑄 𝑓 ⋅ log 2 𝑌 − 1 By Data Processing, H(X | Y) ≤ 𝐼 𝑌 𝑌′) ≤ 𝐼 𝑄 𝑓 + 𝑄 𝑓 ⋅ log 2 𝑌 − 1

  14. Tightness of Fano’s Inequality

  15. Talk Outline 1. Information Theory Concepts 2. Distances Between Distributions 3. An Example Communication Lower Bound – Randomized 1-way Communication Complexity of the INDEX problem 4. Communication Lower Bounds imply space lower bounds for data stream algorithms 5. Techniques for Multi-Player Communication

  16. Distances Between Distributions

  17. Why Hellinger Distance?

  18. Product Property of Hellinger Distance

  19. Jensen-Shannon Distance l

  20. Relations Between Distance Measures

  21. Talk Outline 1. Information Theory Concepts 2. Distances Between Distributions 3. An Example Communication Lower Bound – Randomized 1-way Communication Complexity of the INDEX problem 4. Communication Lower Bounds imply space lower bounds for data stream algorithms 5. Techniques for Multi-Player Communication

  22. Randomized 1-Way Communication Complexity INDEX PROBLEM x 2 {0,1} n j 2 {1, 2, 3, …, n}

  23. 1-Way Communication Complexity of Index • Consider a uniform distribution μ on X • Alice sends a single message M to Bob ′ 𝑢𝑝 𝑌 • We can think of Bob’s output as a guess 𝑌 𝑘 𝑘 ′ = 𝑌 2 • For all j, Pr 𝑌 𝑘 ≥ 𝑘 3 • By Fano’s inequality, for all j, 2 1 1 𝐼 𝑌 𝑘 𝑁) ≤ 𝐼 3 + 3 (log 2 2 − 1) = 𝐼( 3 )

  24. 1-Way Communication of Index Continued 1 So, 𝐽 𝑌 ; 𝑁 ≥ 𝑜 − 𝑗 𝐼 𝑌 𝑗 𝑁) ≥ 𝑜 − 𝐼 3 𝑜 So, 𝑁 ≥ 𝐼 𝑁 ≥ 𝐽 𝑌 ; 𝑁 = Ω 𝑜

  25. Talk Outline 1. Information Theory Concepts 2. Distances Between Distributions 3. An Example Communication Lower Bound – Randomized 1-way Communication Complexity of the INDEX problem 4. Communication Lower Bounds imply space lower bounds for data stream algorithms 5. Techniques for Multi-Player Communication

Recommend


More recommend