4 Search Results for "Goldberg, Halley"

Document
DOI: 10.4230/LIPIcs.CCC.2023.12
Improved Learning from Kolmogorov Complexity

Authors: Halley Goldberg and Valentine Kabanets

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

Abstract
Carmosino, Impagliazzo, Kabanets, and Kolokolova (CCC, 2016) showed that the existence of natural properties in the sense of Razborov and Rudich (JCSS, 1997) implies PAC learning algorithms in the sense of Valiant (Comm. ACM, 1984), for boolean functions in P/poly, under the uniform distribution and with membership queries. It is still an open problem to get from natural properties learning algorithms that do not rely on membership queries but rather use randomly drawn labeled examples. Natural properties may be understood as an average-case version of MCSP, the problem of deciding the minimum size of a circuit computing a given truth-table. Problems related to MCSP include those concerning time-bounded Kolmogorov complexity. MKTP, for example, asks for the KT-complexity of a given string. KT-complexity is a relaxation of circuit size, as it does away with the requirement that a short description of a string be interpreted as a boolean circuit. In this work, under assumptions of MKTP and the related problem MK^tP being easy on average, we get learning algorithms for boolean functions in P/poly that - work over any distribution D samplable by a family of polynomial-size circuits (given explicitly in the case of MKTP), - only use randomly drawn labeled examples from D, and - are agnostic (do not require the target function to belong to the hypothesis class). Our results build upon the recent work of Hirahara and Nanashima (FOCS, 2021) who showed similar learning consequences but under a stronger assumption that NP is easy on average.
Cite as

Halley Goldberg and Valentine Kabanets. Improved Learning from Kolmogorov Complexity. In 38th Computational Complexity Conference (CCC 2023). Leibniz International Proceedings in Informatics (LIPIcs), Volume 264, pp. 12:1-12:29, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)

Copy BibTex To Clipboard

@InProceedings{goldberg_et_al:LIPIcs.CCC.2023.12,
  author =	{Goldberg, Halley and Kabanets, Valentine},
  title =	{{Improved Learning from Kolmogorov Complexity}},
  booktitle =	{38th Computational Complexity Conference (CCC 2023)},
  pages =	{12:1--12:29},
  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-dev.dagstuhl.de/entities/document/10.4230/LIPIcs.CCC.2023.12},
  URN =		{urn:nbn:de:0030-drops-182825},
  doi =		{10.4230/LIPIcs.CCC.2023.12},
  annote =	{Keywords: learning, Kolmogorov complexity, meta-complexity, average-case complexity}
}
Document
DOI: 10.4230/LIPIcs.CCC.2023.35
An Algorithmic Approach to Uniform Lower Bounds

Authors: Rahul Santhanam

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

Abstract
We propose a new family of circuit-based sampling tasks, such that non-trivial algorithmic solutions to certain tasks from this family imply frontier uniform lower bounds such as "NP is not in uniform ACC⁰" and "NP does not have uniform polynomial-size depth-two threshold circuits". Indeed, the most general versions of our sampling tasks have implications for central open problems such as NP vs P and PSPACE vs P. We argue the soundness of our approach by showing that the non-trivial algorithmic solutions we require do follow from standard cryptographic assumptions. In addition, we give evidence that a version of our approach for uniform circuits is necessary in order to separate NP from P or PSPACE from P. We give an algorithmic characterization for the PSPACE vs P question: PSPACE ≠ P iff either E has sub-exponential time non-uniform algorithms infinitely often or there are non-trivial space-efficient solutions to our sampling tasks for uniform Boolean circuits. We show how to use our framework to capture uniform versions of known non-uniform lower bounds, as well as classical uniform lower bounds such as the space hierarchy theorem and Allender’s uniform lower bound for the Permanent. We also apply our framework to prove new lower bounds: NP does not have polynomial-size uniform AC⁰ circuits with a bottom layer of MOD 6 gates, nor does it have polynomial-size uniform AC⁰ circuits with a bottom layer of threshold gates. Our proofs exploit recently defined probabilistic time-bounded variants of Kolmogorov complexity [Zhenjian Lu et al., 2022; Halley Goldberg et al., 2022; Halley Goldberg et al., 2022].
Cite as

Rahul Santhanam. An Algorithmic Approach to Uniform Lower Bounds. In 38th Computational Complexity Conference (CCC 2023). Leibniz International Proceedings in Informatics (LIPIcs), Volume 264, pp. 35:1-35:26, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)

Copy BibTex To Clipboard

@InProceedings{santhanam:LIPIcs.CCC.2023.35,
  author =	{Santhanam, Rahul},
  title =	{{An Algorithmic Approach to Uniform Lower Bounds}},
  booktitle =	{38th Computational Complexity Conference (CCC 2023)},
  pages =	{35:1--35:26},
  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-dev.dagstuhl.de/entities/document/10.4230/LIPIcs.CCC.2023.35},
  URN =		{urn:nbn:de:0030-drops-183053},
  doi =		{10.4230/LIPIcs.CCC.2023.35},
  annote =	{Keywords: Probabilistic Kolmogorov complexity, sampling algorithms, uniform lower bounds}
}
Document
DOI: 10.4230/LIPIcs.CCC.2022.16
Probabilistic Kolmogorov Complexity with Applications to Average-Case Complexity

Authors: Halley Goldberg, Valentine Kabanets, Zhenjian Lu, and Igor C. Oliveira

Published in: LIPIcs, Volume 234, 37th Computational Complexity Conference (CCC 2022)

Abstract
Understanding the relationship between the worst-case and average-case complexities of NP and of other subclasses of PH is a long-standing problem in complexity theory. Over the last few years, much progress has been achieved in this front through the investigation of meta-complexity: the complexity of problems that refer to the complexity of the input string x (e.g., given a string x, estimate its time-bounded Kolmogorov complexity). In particular, [Shuichi Hirahara, 2021] employed techniques from meta-complexity to show that if DistNP ⊆ AvgP then UP ⊆ DTIME[2^{O(n/log n)}]. While this and related results [Shuichi Hirahara and Mikito Nanashima, 2021; Lijie Chen et al., 2022] offer exciting progress after a long gap, they do not survive in the setting of randomized computations: roughly speaking, "randomness" is the opposite of "structure", and upper bounding the amount of structure (time-bounded Kolmogorov complexity) of different objects is crucial in recent applications of meta-complexity. This limitation is significant, since randomized computations are ubiquitous in algorithm design and give rise to a more robust theory of average-case complexity [Russell Impagliazzo and Leonid A. Levin, 1990]. In this work, we develop a probabilistic theory of meta-complexity, by incorporating randomness into the notion of complexity of a string x. This is achieved through a new probabilistic variant of time-bounded Kolmogorov complexity that we call pK^t complexity. Informally, pK^t(x) measures the complexity of x when shared randomness is available to all parties involved in a computation. By porting key results from meta-complexity to the probabilistic domain of pK^t complexity and its variants, we are able to establish new connections between worst-case and average-case complexity in the important setting of probabilistic computations: - If DistNP ⊆ AvgBPP, then UP ⊆ RTIME[2^O(n/log n)]. - If DistΣ^P_2 ⊆ AvgBPP, then AM ⊆ BPTIME[2^O(n/log n)]. - In the fine-grained setting [Lijie Chen et al., 2022], we get UTIME[2^O(√{nlog n})] ⊆ RTIME[2^O(√{nlog n})] and AMTIME[2^O(√{nlog n})] ⊆ BPTIME[2^O(√{nlog n})] from stronger average-case assumptions. - If DistPH ⊆ AvgBPP, then PH ⊆ BPTIME[2^O(n/log n)]. Specifically, for any 𝓁 ≥ 0, if DistΣ_{𝓁+2}^P ⊆ AvgBPP then Σ_𝓁^{P} ⊆ BPTIME[2^O(n/log n)]. - Strengthening a result from [Shuichi Hirahara and Mikito Nanashima, 2021], we show that if DistNP ⊆ AvgBPP then polynomial size Boolean circuits can be agnostically PAC learned under any unknown 𝖯/poly-samplable distribution in polynomial time. In some cases, our framework allows us to significantly simplify existing proofs, or to extend results to the more challenging probabilistic setting with little to no extra effort.
Cite as

Halley Goldberg, Valentine Kabanets, Zhenjian Lu, and Igor C. Oliveira. Probabilistic Kolmogorov Complexity with Applications to Average-Case Complexity. In 37th Computational Complexity Conference (CCC 2022). Leibniz International Proceedings in Informatics (LIPIcs), Volume 234, pp. 16:1-16:60, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)

Copy BibTex To Clipboard

@InProceedings{goldberg_et_al:LIPIcs.CCC.2022.16,
  author =	{Goldberg, Halley and Kabanets, Valentine and Lu, Zhenjian and Oliveira, Igor C.},
  title =	{{Probabilistic Kolmogorov Complexity with Applications to Average-Case Complexity}},
  booktitle =	{37th Computational Complexity Conference (CCC 2022)},
  pages =	{16:1--16:60},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-241-9},
  ISSN =	{1868-8969},
  year =	{2022},
  volume =	{234},
  editor =	{Lovett, Shachar},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/LIPIcs.CCC.2022.16},
  URN =		{urn:nbn:de:0030-drops-165785},
  doi =		{10.4230/LIPIcs.CCC.2022.16},
  annote =	{Keywords: average-case complexity, Kolmogorov complexity, meta-complexity, worst-case to average-case reductions, learning}
}
Document
Track A: Algorithms, Complexity and Games
DOI: 10.4230/LIPIcs.ICALP.2022.92
Optimal Coding Theorems in Time-Bounded Kolmogorov Complexity

Authors: Zhenjian Lu, Igor C. Oliveira, and Marius Zimand

Published in: LIPIcs, Volume 229, 49th International Colloquium on Automata, Languages, and Programming (ICALP 2022)

Abstract
The classical coding theorem in Kolmogorov complexity states that if an n-bit string x is sampled with probability δ by an algorithm with prefix-free domain then 𝖪(x) ≤ log(1/δ) + O(1). In a recent work, Lu and Oliveira [Zhenjian Lu and Igor C. Oliveira, 2021] established an unconditional time-bounded version of this result, by showing that if x can be efficiently sampled with probability δ then rKt(x) = O(log(1/δ)) + O(log n), where rKt denotes the randomized analogue of Levin’s Kt complexity. Unfortunately, this result is often insufficient when transferring applications of the classical coding theorem to the time-bounded setting, as it achieves a O(log(1/δ)) bound instead of the information-theoretic optimal log(1/δ). Motivated by this discrepancy, we investigate optimal coding theorems in the time-bounded setting. Our main contributions can be summarised as follows. • Efficient coding theorem for rKt with a factor of 2. Addressing a question from [Zhenjian Lu and Igor C. Oliveira, 2021], we show that if x can be efficiently sampled with probability at least δ then rKt(x) ≤ (2 + o(1)) ⋅ log(1/δ) + O(log n). As in previous work, our coding theorem is efficient in the sense that it provides a polynomial-time probabilistic algorithm that, when given x, the code of the sampler, and δ, it outputs, with probability ≥ 0.99, a probabilistic representation of x that certifies this rKt complexity bound. • Optimality under a cryptographic assumption. Under a hypothesis about the security of cryptographic pseudorandom generators, we show that no efficient coding theorem can achieve a bound of the form rKt(x) ≤ (2 - o(1)) ⋅ log(1/δ) + poly(log n). Under a weaker assumption, we exhibit a gap between efficient coding theorems and existential coding theorems with near-optimal parameters. • Optimal coding theorem for pK^t and unconditional Antunes-Fortnow. We consider pK^t complexity [Halley Goldberg et al., 2022], a variant of rKt where the randomness is public and the time bound is fixed. We observe the existence of an optimal coding theorem for pK^t, and employ this result to establish an unconditional version of a theorem of Antunes and Fortnow [Luis Filipe Coelho Antunes and Lance Fortnow, 2009] which characterizes the worst-case running times of languages that are in average polynomial-time over all 𝖯-samplable distributions.
Cite as

Zhenjian Lu, Igor C. Oliveira, and Marius Zimand. Optimal Coding Theorems in Time-Bounded Kolmogorov Complexity. In 49th International Colloquium on Automata, Languages, and Programming (ICALP 2022). Leibniz International Proceedings in Informatics (LIPIcs), Volume 229, pp. 92:1-92:14, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)

Copy BibTex To Clipboard

@InProceedings{lu_et_al:LIPIcs.ICALP.2022.92,
  author =	{Lu, Zhenjian and Oliveira, Igor C. and Zimand, Marius},
  title =	{{Optimal Coding Theorems in Time-Bounded Kolmogorov Complexity}},
  booktitle =	{49th International Colloquium on Automata, Languages, and Programming (ICALP 2022)},
  pages =	{92:1--92:14},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-235-8},
  ISSN =	{1868-8969},
  year =	{2022},
  volume =	{229},
  editor =	{Boja\'{n}czyk, Miko{\l}aj and Merelli, Emanuela and Woodruff, David P.},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops-dev.dagstuhl.de/entities/document/10.4230/LIPIcs.ICALP.2022.92},
  URN =		{urn:nbn:de:0030-drops-164331},
  doi =		{10.4230/LIPIcs.ICALP.2022.92},
  annote =	{Keywords: computational complexity, randomized algorithms, Kolmogorov complexity}
}
  • Refine by Author
  • 2 Goldberg, Halley
  • 2 Kabanets, Valentine
  • 2 Lu, Zhenjian
  • 2 Oliveira, Igor C.
  • 1 Santhanam, Rahul
  • Show More...

  • Refine by Classification
  • 2 Theory of computation → Computational complexity and cryptography
  • 1 Theory of computation
  • 1 Theory of computation → Circuit complexity
  • 1 Theory of computation → Complexity classes

  • Refine by Keyword
  • 3 Kolmogorov complexity
  • 2 average-case complexity
  • 2 learning
  • 2 meta-complexity
  • 1 Probabilistic Kolmogorov complexity
  • Show More...

  • Refine by Type
  • 4 document

  • Refine by Publication Year
  • 2 2022
  • 2 2023

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
© 2023-2024 Schloss Dagstuhl – LZI GmbH Imprint Privacy Contact