6 Search Results for "Hatami, Hamed"


Document
Separation of the Factorization Norm and Randomized Communication Complexity

Authors: Tsun-Ming Cheung, Hamed Hatami, Kaave Hosseini, and Morgan Shirley

Published in: LIPIcs, Volume 264, 38th Computational Complexity Conference (CCC 2023)


Abstract
In an influential paper, Linial and Shraibman (STOC '07) introduced the factorization norm as a powerful tool for proving lower bounds against randomized and quantum communication complexities. They showed that the logarithm of the approximate γ₂-factorization norm is a lower bound for these parameters and asked whether a stronger lower bound that replaces approximate γ₂ norm with the γ₂ norm holds. We answer the question of Linial and Shraibman in the negative by exhibiting a 2ⁿ×2ⁿ Boolean matrix with γ₂ norm 2^Ω(n) and randomized communication complexity O(log n). As a corollary, we recover the recent result of Chattopadhyay, Lovett, and Vinyals (CCC '19) that deterministic protocols with access to an Equality oracle are exponentially weaker than (one-sided error) randomized protocols. In fact, as a stronger consequence, our result implies an exponential separation between the power of unambiguous nondeterministic protocols with access to Equality oracle and (one-sided error) randomized protocols, which answers a question of Pitassi, Shirley, and Shraibman (ITSC '23). Our result also implies a conjecture of Sherif (Ph.D. thesis) that the γ₂ norm of the Integer Inner Product function (IIP) in dimension 3 or higher is exponential in its input size.

Cite as

Tsun-Ming Cheung, Hamed Hatami, Kaave Hosseini, and Morgan Shirley. Separation of the Factorization Norm and Randomized Communication Complexity. In 38th Computational Complexity Conference (CCC 2023). Leibniz International Proceedings in Informatics (LIPIcs), Volume 264, pp. 1:1-1:16, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)


Copy BibTex To Clipboard

@InProceedings{cheung_et_al:LIPIcs.CCC.2023.1,
  author =	{Cheung, Tsun-Ming and Hatami, Hamed and Hosseini, Kaave and Shirley, Morgan},
  title =	{{Separation of the Factorization Norm and Randomized Communication Complexity}},
  booktitle =	{38th Computational Complexity Conference (CCC 2023)},
  pages =	{1:1--1:16},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-282-2},
  ISSN =	{1868-8969},
  year =	{2023},
  volume =	{264},
  editor =	{Ta-Shma, Amnon},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.CCC.2023.1},
  URN =		{urn:nbn:de:0030-drops-182714},
  doi =		{10.4230/LIPIcs.CCC.2023.1},
  annote =	{Keywords: Factorization norms, randomized communication complexity}
}
Document
Track A: Algorithms, Complexity and Games
Online Learning and Disambiguations of Partial Concept Classes

Authors: Tsun-Ming Cheung, Hamed Hatami, Pooya Hatami, and Kaave Hosseini

Published in: LIPIcs, Volume 261, 50th International Colloquium on Automata, Languages, and Programming (ICALP 2023)


Abstract
In a recent article, Alon, Hanneke, Holzman, and Moran (FOCS '21) introduced a unifying framework to study the learnability of classes of partial concepts. One of the central questions studied in their work is whether the learnability of a partial concept class is always inherited from the learnability of some "extension" of it to a total concept class. They showed this is not the case for PAC learning but left the problem open for the stronger notion of online learnability. We resolve this problem by constructing a class of partial concepts that is online learnable, but no extension of it to a class of total concepts is online learnable (or even PAC learnable).

Cite as

Tsun-Ming Cheung, Hamed Hatami, Pooya Hatami, and Kaave Hosseini. Online Learning and Disambiguations of Partial Concept Classes. In 50th International Colloquium on Automata, Languages, and Programming (ICALP 2023). Leibniz International Proceedings in Informatics (LIPIcs), Volume 261, pp. 42:1-42:13, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)


Copy BibTex To Clipboard

@InProceedings{cheung_et_al:LIPIcs.ICALP.2023.42,
  author =	{Cheung, Tsun-Ming and Hatami, Hamed and Hatami, Pooya and Hosseini, Kaave},
  title =	{{Online Learning and Disambiguations of Partial Concept Classes}},
  booktitle =	{50th International Colloquium on Automata, Languages, and Programming (ICALP 2023)},
  pages =	{42:1--42:13},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-278-5},
  ISSN =	{1868-8969},
  year =	{2023},
  volume =	{261},
  editor =	{Etessami, Kousha and Feige, Uriel and Puppis, Gabriele},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ICALP.2023.42},
  URN =		{urn:nbn:de:0030-drops-180946},
  doi =		{10.4230/LIPIcs.ICALP.2023.42},
  annote =	{Keywords: Online learning, Littlestone dimension, VC dimension, partial concept class, clique vs independent set, Alon-Saks-Seymour conjecture, Standard Optimal Algorithm, PAC learning}
}
Document
RANDOM
Lower Bound Methods for Sign-Rank and Their Limitations

Authors: Hamed Hatami, Pooya Hatami, William Pires, Ran Tao, and Rosie Zhao

Published in: LIPIcs, Volume 245, Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2022)


Abstract
The sign-rank of a matrix A with ±1 entries is the smallest rank of a real matrix with the same sign pattern as A. To the best of our knowledge, there are only three known methods for proving lower bounds on the sign-rank of explicit matrices: (i) Sign-rank is at least the VC-dimension; (ii) Forster’s method, which states that sign-rank is at least the inverse of the largest possible average margin among the representations of the matrix by points and half-spaces; (iii) Sign-rank is at least a logarithmic function of the density of the largest monochromatic rectangle. We prove several results regarding the limitations of these methods. - We prove that, qualitatively, the monochromatic rectangle density is the strongest of these three lower bounds. If it fails to provide a super-constant lower bound for the sign-rank of a matrix, then the other two methods will fail as well. - We show that there exist n × n matrices with sign-rank n^Ω(1) for which none of these methods can provide a super-constant lower bound. - We show that sign-rank is at most an exponential function of the deterministic communication complexity with access to an equality oracle. We combine this result with Green and Sanders' quantitative version of Cohen’s idempotent theorem to show that for a large class of sign matrices (e.g., xor-lifts), sign-rank is at most an exponential function of the γ₂ norm of the matrix. We conjecture that this holds for all sign matrices. - Towards answering a question of Linial, Mendelson, Schechtman, and Shraibman regarding the relation between sign-rank and discrepancy, we conjecture that sign-ranks of the ±1 adjacency matrices of hypercube graphs can be arbitrarily large. We prove that none of the three lower bound techniques can resolve this conjecture in the affirmative.

Cite as

Hamed Hatami, Pooya Hatami, William Pires, Ran Tao, and Rosie Zhao. Lower Bound Methods for Sign-Rank and Their Limitations. In Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2022). Leibniz International Proceedings in Informatics (LIPIcs), Volume 245, pp. 22:1-22:24, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)


Copy BibTex To Clipboard

@InProceedings{hatami_et_al:LIPIcs.APPROX/RANDOM.2022.22,
  author =	{Hatami, Hamed and Hatami, Pooya and Pires, William and Tao, Ran and Zhao, Rosie},
  title =	{{Lower Bound Methods for Sign-Rank and Their Limitations}},
  booktitle =	{Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2022)},
  pages =	{22:1--22:24},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-249-5},
  ISSN =	{1868-8969},
  year =	{2022},
  volume =	{245},
  editor =	{Chakrabarti, Amit and Swamy, Chaitanya},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.APPROX/RANDOM.2022.22},
  URN =		{urn:nbn:de:0030-drops-171445},
  doi =		{10.4230/LIPIcs.APPROX/RANDOM.2022.22},
  annote =	{Keywords: Average Margin, Communication complexity, margin complexity, monochromatic rectangle, Sign-rank, Unbounded-error communication complexity, VC-dimension}
}
Document
Sign Rank vs Discrepancy

Authors: Hamed Hatami, Kaave Hosseini, and Shachar Lovett

Published in: LIPIcs, Volume 169, 35th Computational Complexity Conference (CCC 2020)


Abstract
Sign-rank and discrepancy are two central notions in communication complexity. The seminal work of Babai, Frankl, and Simon from 1986 initiated an active line of research that investigates the gap between these two notions. In this article, we establish the strongest possible separation by constructing a boolean matrix whose sign-rank is only 3, and yet its discrepancy is 2^{-Ω(n)}. We note that every matrix of sign-rank 2 has discrepancy n^{-O(1)}. Our result in particular implies that there are boolean functions with O(1) unbounded error randomized communication complexity while having Ω(n) weakly unbounded error randomized communication complexity.

Cite as

Hamed Hatami, Kaave Hosseini, and Shachar Lovett. Sign Rank vs Discrepancy. In 35th Computational Complexity Conference (CCC 2020). Leibniz International Proceedings in Informatics (LIPIcs), Volume 169, pp. 18:1-18:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2020)


Copy BibTex To Clipboard

@InProceedings{hatami_et_al:LIPIcs.CCC.2020.18,
  author =	{Hatami, Hamed and Hosseini, Kaave and Lovett, Shachar},
  title =	{{Sign Rank vs Discrepancy}},
  booktitle =	{35th Computational Complexity Conference (CCC 2020)},
  pages =	{18:1--18:14},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-156-6},
  ISSN =	{1868-8969},
  year =	{2020},
  volume =	{169},
  editor =	{Saraf, Shubhangi},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.CCC.2020.18},
  URN =		{urn:nbn:de:0030-drops-125700},
  doi =		{10.4230/LIPIcs.CCC.2020.18},
  annote =	{Keywords: Discrepancy, sign rank, Unbounded-error communication complexity, weakly unbounded error communication complexity}
}
Document
Track A: Algorithms, Complexity and Games
Biasing Boolean Functions and Collective Coin-Flipping Protocols over Arbitrary Product Distributions

Authors: Yuval Filmus, Lianna Hambardzumyan, Hamed Hatami, Pooya Hatami, and David Zuckerman

Published in: LIPIcs, Volume 132, 46th International Colloquium on Automata, Languages, and Programming (ICALP 2019)


Abstract
The seminal result of Kahn, Kalai and Linial shows that a coalition of O(n/(log n)) players can bias the outcome of any Boolean function {0,1}^n -> {0,1} with respect to the uniform measure. We extend their result to arbitrary product measures on {0,1}^n, by combining their argument with a completely different argument that handles very biased input bits. We view this result as a step towards proving a conjecture of Friedgut, which states that Boolean functions on the continuous cube [0,1]^n (or, equivalently, on {1,...,n}^n) can be biased using coalitions of o(n) players. This is the first step taken in this direction since Friedgut proposed the conjecture in 2004. Russell, Saks and Zuckerman extended the result of Kahn, Kalai and Linial to multi-round protocols, showing that when the number of rounds is o(log^* n), a coalition of o(n) players can bias the outcome with respect to the uniform measure. We extend this result as well to arbitrary product measures on {0,1}^n. The argument of Russell et al. relies on the fact that a coalition of o(n) players can boost the expectation of any Boolean function from epsilon to 1-epsilon with respect to the uniform measure. This fails for general product distributions, as the example of the AND function with respect to mu_{1-1/n} shows. Instead, we use a novel boosting argument alongside a generalization of our first result to arbitrary finite ranges.

Cite as

Yuval Filmus, Lianna Hambardzumyan, Hamed Hatami, Pooya Hatami, and David Zuckerman. Biasing Boolean Functions and Collective Coin-Flipping Protocols over Arbitrary Product Distributions. In 46th International Colloquium on Automata, Languages, and Programming (ICALP 2019). Leibniz International Proceedings in Informatics (LIPIcs), Volume 132, pp. 58:1-58:13, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2019)


Copy BibTex To Clipboard

@InProceedings{filmus_et_al:LIPIcs.ICALP.2019.58,
  author =	{Filmus, Yuval and Hambardzumyan, Lianna and Hatami, Hamed and Hatami, Pooya and Zuckerman, David},
  title =	{{Biasing Boolean Functions and Collective Coin-Flipping Protocols over Arbitrary Product Distributions}},
  booktitle =	{46th International Colloquium on Automata, Languages, and Programming (ICALP 2019)},
  pages =	{58:1--58:13},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-109-2},
  ISSN =	{1868-8969},
  year =	{2019},
  volume =	{132},
  editor =	{Baier, Christel and Chatzigiannakis, Ioannis and Flocchini, Paola and Leonardi, Stefano},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ICALP.2019.58},
  URN =		{urn:nbn:de:0030-drops-106340},
  doi =		{10.4230/LIPIcs.ICALP.2019.58},
  annote =	{Keywords: Boolean function analysis, coin flipping}
}
Document
Trading Information Complexity for Error

Authors: Yuval Dagan, Yuval Filmus, Hamed Hatami, and Yaqiao Li

Published in: LIPIcs, Volume 79, 32nd Computational Complexity Conference (CCC 2017)


Abstract
We consider the standard two-party communication model. The central problem studied in this article is how much can one save in information complexity by allowing a certain error. * For arbitrary functions, we obtain lower bounds and upper bounds indicating a gain that is of order Omega(h(epsilon)) and O(h(sqrt{epsilon})). Here h denotes the binary entropy function. * We analyze the case of the two-bit AND function in detail to show that for this function the gain is Theta(h(epsilon)). This answers a question of Braverman et al. [Braverman, STOC 2013]. * We obtain sharp bounds for the set disjointness function of order n. For the case of the distributional error, we introduce a new protocol that achieves a gain of Theta(sqrt{h(epsilon)}) provided that n is sufficiently large. We apply these results to answer another of question of Braverman et al. regarding the randomized communication complexity of the set disjointness function. * Answering a question of Braverman [Braverman, STOC 2012], we apply our analysis of the set disjointness function to establish a gap between the two different notions of the prior-free information cost. In light of [Braverman, STOC 2012], this implies that amortized randomized communication complexity is not necessarily equal to the amortized distributional communication complexity with respect to the hardest distribution. As a consequence, we show that the epsilon-error randomized communication complexity of the set disjointness function of order n is n[C_{DISJ} - Theta(h(epsilon))] + o(n), where C_{DISJ} ~ 0.4827$ is the constant found by Braverman et al. [Braverman, STOC 2012].

Cite as

Yuval Dagan, Yuval Filmus, Hamed Hatami, and Yaqiao Li. Trading Information Complexity for Error. In 32nd Computational Complexity Conference (CCC 2017). Leibniz International Proceedings in Informatics (LIPIcs), Volume 79, pp. 16:1-16:59, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2017)


Copy BibTex To Clipboard

@InProceedings{dagan_et_al:LIPIcs.CCC.2017.16,
  author =	{Dagan, Yuval and Filmus, Yuval and Hatami, Hamed and Li, Yaqiao},
  title =	{{Trading Information Complexity for Error}},
  booktitle =	{32nd Computational Complexity Conference (CCC 2017)},
  pages =	{16:1--16:59},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-040-8},
  ISSN =	{1868-8969},
  year =	{2017},
  volume =	{79},
  editor =	{O'Donnell, Ryan},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.CCC.2017.16},
  URN =		{urn:nbn:de:0030-drops-75179},
  doi =		{10.4230/LIPIcs.CCC.2017.16},
  annote =	{Keywords: communication complexity, information complexity}
}
  • Refine by Author
  • 6 Hatami, Hamed
  • 3 Hatami, Pooya
  • 3 Hosseini, Kaave
  • 2 Cheung, Tsun-Ming
  • 2 Filmus, Yuval
  • Show More...

  • Refine by Classification
  • 3 Theory of computation → Communication complexity
  • 1 Theory of computation
  • 1 Theory of computation → Boolean function learning
  • 1 Theory of computation → Online learning theory

  • Refine by Keyword
  • 2 Unbounded-error communication complexity
  • 1 Alon-Saks-Seymour conjecture
  • 1 Average Margin
  • 1 Boolean function analysis
  • 1 Communication complexity
  • Show More...

  • Refine by Type
  • 6 document

  • Refine by Publication Year
  • 2 2023
  • 1 2017
  • 1 2019
  • 1 2020
  • 1 2022

Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail