8 Search Results for "Koch, Caleb"

Document
DOI: 10.4230/LIPIcs.ITCS.2026.20
Samplability Makes Learning Easier

Authors: Guy Blanc, Caleb Koch, Jane Lange, Carmen Strassle, and Li-Yang Tan

Published in: LIPIcs, Volume 362, 17th Innovations in Theoretical Computer Science Conference (ITCS 2026)

Abstract
The standard definition of PAC learning (Valiant 1984) requires learners to succeed under all distributions - even ones that are intractable to sample from. This stands in contrast to samplable PAC learning (Blum, Furst, Kearns, and Lipton 1993), where learners only have to succeed under samplable distributions. We study this distinction and show that samplable PAC substantially expands the power of efficient learners. We first construct a concept class that requires exponential sample complexity in standard PAC but is learnable with polynomial sample complexity in samplable PAC. We then lift this statistical separation to the computational setting and obtain a separation relative to a random oracle. Our proofs center around a new complexity primitive, explicit evasive sets, that we introduce and study. These are sets for which membership is easy to determine but are extremely hard to sample from. Our results extend to the online setting to similarly show that its landscape changes when the adversary is assumed to be efficient instead of computationally unbounded.
Cite as

Guy Blanc, Caleb Koch, Jane Lange, Carmen Strassle, and Li-Yang Tan. Samplability Makes Learning Easier. In 17th Innovations in Theoretical Computer Science Conference (ITCS 2026). Leibniz International Proceedings in Informatics (LIPIcs), Volume 362, pp. 20:1-20:12, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2026)

Copy BibTex To Clipboard

@InProceedings{blanc_et_al:LIPIcs.ITCS.2026.20,
  author =	{Blanc, Guy and Koch, Caleb and Lange, Jane and Strassle, Carmen and Tan, Li-Yang},
  title =	{{Samplability Makes Learning Easier}},
  booktitle =	{17th Innovations in Theoretical Computer Science Conference (ITCS 2026)},
  pages =	{20:1--20:12},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-410-9},
  ISSN =	{1868-8969},
  year =	{2026},
  volume =	{362},
  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.ITCS.2026.20},
  URN =		{urn:nbn:de:0030-drops-253071},
  doi =		{10.4230/LIPIcs.ITCS.2026.20},
  annote =	{Keywords: PAC learning, Samplable distributions}
}
Document
RANDOM
DOI: 10.4230/LIPIcs.APPROX/RANDOM.2025.31
New Statistical and Computational Results for Learning Junta Distributions

Authors: Lorenzo Beretta

Published in: LIPIcs, Volume 353, Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2025)

Abstract
We study the problem of learning junta distributions on {±1}ⁿ, where a distribution is a k-junta if its probability mass function depends on a subset of at most k variables. We make two main contributions: - We show that learning k-junta distributions is computationally equivalent to learning k-parity functions with noise (LPN), a landmark problem in computational learning theory. - We design an algorithm for learning junta distributions whose statistical complexity is optimal, up to polylogarithmic factors. Computationally, our algorithm matches the complexity of previous (non-sample-optimal) algorithms. Combined, our two contributions imply that our algorithm cannot be significantly improved, statistically or computationally, barring a breakthrough for LPN.
Cite as

Lorenzo Beretta. New Statistical and Computational Results for Learning Junta Distributions. In Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2025). Leibniz International Proceedings in Informatics (LIPIcs), Volume 353, pp. 31:1-31:23, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@InProceedings{beretta:LIPIcs.APPROX/RANDOM.2025.31,
  author =	{Beretta, Lorenzo},
  title =	{{New Statistical and Computational Results for Learning Junta Distributions}},
  booktitle =	{Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2025)},
  pages =	{31:1--31:23},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-397-3},
  ISSN =	{1868-8969},
  year =	{2025},
  volume =	{353},
  editor =	{Ene, Alina and Chattopadhyay, Eshan},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.APPROX/RANDOM.2025.31},
  URN =		{urn:nbn:de:0030-drops-243978},
  doi =		{10.4230/LIPIcs.APPROX/RANDOM.2025.31},
  annote =	{Keywords: Junta Distributions, Learning Parities with Noise}
}
Document
DOI: 10.4230/LIPIcs.CCC.2025.16
Direct Sums for Parity Decision Trees

Authors: Tyler Besselman, Mika Göös, Siyao Guo, Gilbert Maystre, and Weiqiang Yuan

Published in: LIPIcs, Volume 339, 40th Computational Complexity Conference (CCC 2025)

Abstract
Direct sum theorems state that the cost of solving k instances of a problem is at least Ω(k) times the cost of solving a single instance. We prove the first such results in the randomised parity decision tree model. We show that a direct sum theorem holds whenever (1) the lower bound for parity decision trees is proved using the discrepancy method; or (2) the lower bound is proved relative to a product distribution.
Cite as

Tyler Besselman, Mika Göös, Siyao Guo, Gilbert Maystre, and Weiqiang Yuan. Direct Sums for Parity Decision Trees. In 40th Computational Complexity Conference (CCC 2025). Leibniz International Proceedings in Informatics (LIPIcs), Volume 339, pp. 16:1-16:38, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@InProceedings{besselman_et_al:LIPIcs.CCC.2025.16,
  author =	{Besselman, Tyler and G\"{o}\"{o}s, Mika and Guo, Siyao and Maystre, Gilbert and Yuan, Weiqiang},
  title =	{{Direct Sums for Parity Decision Trees}},
  booktitle =	{40th Computational Complexity Conference (CCC 2025)},
  pages =	{16:1--16:38},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-379-9},
  ISSN =	{1868-8969},
  year =	{2025},
  volume =	{339},
  editor =	{Srinivasan, Srikanth},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.CCC.2025.16},
  URN =		{urn:nbn:de:0030-drops-237105},
  doi =		{10.4230/LIPIcs.CCC.2025.16},
  annote =	{Keywords: direct sum, parity decision trees, query complexity}
}
Document
DOI: 10.4230/LIPIcs.CCC.2025.34
Witness Encryption and NP-Hardness of Learning

Authors: Halley Goldberg and Valentine Kabanets

Published in: LIPIcs, Volume 339, 40th Computational Complexity Conference (CCC 2025)

Abstract
We study connections between two fundamental questions from computer science theory. (1) Is witness encryption possible for NP [Sanjam Garg et al., 2013]? That is, given an instance x of an NP-complete language L, can one encrypt a secret message with security contingent on the ability to provide a witness for x ∈ L? (2) Is computational learning (in the sense of [Leslie G. Valiant, 1984; Michael J. Kearns et al., 1994]) hard for NP? That is, is there a polynomial-time reduction from instances of L to instances of learning? Our main contribution is that certain formulations of NP-hardness of learning characterize the existence of witness encryption for NP. More specifically, we show: - witness encryption for a language L ∈ NP is equivalent to a half-Levin reduction from L to the Computational Gap Learning problem (denoted CGL [Benny Applebaum et al., 2008]), where a half-Levin reduction is the same as a Levin reduction but only required to preserve witnesses in one direction, and CGL formalizes agnostic learning as a decision problem. We show versions of the statement above for witness encryption secure against non-uniform and uniform adversaries. We also show that witness encryption for NP with ciphertexts of logarithmic length, along with a circuit lower bound for E, are together equivalent to NP-hardness of a generalized promise version of MCSP. We complement the above with a number of unconditional NP-hardness results for agnostic PAC learning. Extending a result of [Shuichi Hirahara, 2022] to the standard setting of boolean circuits, we show NP-hardness of "semi-proper" learning. Namely: - for some polynomial s, it is NP-hard to agnostically learn circuits of size s(n) by circuits of size s(n)⋅ n^{1/(log log n)^O(1)}. Looking beyond the computational model of standard boolean circuits enables us to prove NP-hardness of improper learning (ie. without a restriction on the size of hypothesis returned by the learner). We obtain such results for: - learning circuits with oracle access to a given randomly sampled string, and - learning RAM programs. In particular, we show that a variant of MINLT [Ker-I Ko, 1991] for RAM programs is NP-hard with parameters corresponding to the setting of improper learning. We view these results as partial progress toward the ultimate goal of showing NP-hardness of learning boolean circuits in an improper setting. Lastly, we give some consequences of NP-hardness of learning for private- and public-key cryptography. Improving a main result of [Benny Applebaum et al., 2008], we show that if improper agnostic PAC learning is NP-hard under a randomized non-adaptive reduction (with some restrictions), then NP ⊈ BPP implies the existence of i.o. one-way functions. In contrast, if CGL is NP-hard under a half-Levin reduction, then NP ⊈ BPP implies the existence of i.o. public-key encryption.
Cite as

Halley Goldberg and Valentine Kabanets. Witness Encryption and NP-Hardness of Learning. In 40th Computational Complexity Conference (CCC 2025). Leibniz International Proceedings in Informatics (LIPIcs), Volume 339, pp. 34:1-34:43, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@InProceedings{goldberg_et_al:LIPIcs.CCC.2025.34,
  author =	{Goldberg, Halley and Kabanets, Valentine},
  title =	{{Witness Encryption and NP-Hardness of Learning}},
  booktitle =	{40th Computational Complexity Conference (CCC 2025)},
  pages =	{34:1--34:43},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-379-9},
  ISSN =	{1868-8969},
  year =	{2025},
  volume =	{339},
  editor =	{Srinivasan, Srikanth},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.CCC.2025.34},
  URN =		{urn:nbn:de:0030-drops-237281},
  doi =		{10.4230/LIPIcs.CCC.2025.34},
  annote =	{Keywords: agnostic PAC learning, witness encryption, NP-hardness}
}
Document
DOI: 10.4230/LIPIcs.CCC.2024.16
A Strong Direct Sum Theorem for Distributional Query Complexity

Authors: Guy Blanc, Caleb Koch, Carmen Strassle, and Li-Yang Tan

Published in: LIPIcs, Volume 300, 39th Computational Complexity Conference (CCC 2024)

Abstract
Consider the expected query complexity of computing the k-fold direct product f^{⊗ k} of a function f to error ε with respect to a distribution μ^k. One strategy is to sequentially compute each of the k copies to error ε/k with respect to μ and apply the union bound. We prove a strong direct sum theorem showing that this naive strategy is essentially optimal. In particular, computing a direct product necessitates a blowup in both query complexity and error. Strong direct sum theorems contrast with results that only show a blowup in query complexity or error but not both. There has been a long line of such results for distributional query complexity, dating back to (Impagliazzo, Raz, Wigderson 1994) and (Nisan, Rudich, Saks 1994), but a strong direct sum theorem that holds for all functions in the standard query model had been elusive. A key idea in our work is the first use of the Hardcore Theorem (Impagliazzo 1995) in the context of query complexity. We prove a new resilience lemma that accompanies it, showing that the hardcore of f^{⊗k} is likely to remain dense under arbitrary partitions of the input space.
Cite as

Guy Blanc, Caleb Koch, Carmen Strassle, and Li-Yang Tan. A Strong Direct Sum Theorem for Distributional Query Complexity. In 39th Computational Complexity Conference (CCC 2024). Leibniz International Proceedings in Informatics (LIPIcs), Volume 300, pp. 16:1-16:30, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2024)

Copy BibTex To Clipboard

@InProceedings{blanc_et_al:LIPIcs.CCC.2024.16,
  author =	{Blanc, Guy and Koch, Caleb and Strassle, Carmen and Tan, Li-Yang},
  title =	{{A Strong Direct Sum Theorem for Distributional Query Complexity}},
  booktitle =	{39th Computational Complexity Conference (CCC 2024)},
  pages =	{16:1--16:30},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-331-7},
  ISSN =	{1868-8969},
  year =	{2024},
  volume =	{300},
  editor =	{Santhanam, Rahul},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.CCC.2024.16},
  URN =		{urn:nbn:de:0030-drops-204123},
  doi =		{10.4230/LIPIcs.CCC.2024.16},
  annote =	{Keywords: Query complexity, direct product theorem, hardcore theorem}
}
Document
DOI: 10.4230/LIPIcs.ECOOP.2023.21
Automata Learning with an Incomplete Teacher

Authors: Mark Moeller, Thomas Wiener, Alaia Solko-Breslin, Caleb Koch, Nate Foster, and Alexandra Silva

Published in: LIPIcs, Volume 263, 37th European Conference on Object-Oriented Programming (ECOOP 2023)

Abstract
The preceding decade has seen significant interest in use of active learning to build models of programs and protocols. But existing algorithms assume the existence of an idealized oracle - a so-called Minimally Adequate Teacher (MAT) - that cannot be fully realized in practice and so is usually approximated with testing. This work proposes a new framework for active learning based on an incomplete teacher. This new formulation, called iMAT, neatly handles scenarios in which the teacher has access to only a finite number of tests or otherwise has gaps in its knowledge. We adapt Angluin’s L^⋆ algorithm for learning finite automata to incomplete teachers and we build a prototype implementation in OCaml that uses an SMT solver to help fill in information not supplied by the teacher. We demonstrate the behavior of our iMAT prototype on a variety of learning problems from a standard benchmark suite.
Cite as

Mark Moeller, Thomas Wiener, Alaia Solko-Breslin, Caleb Koch, Nate Foster, and Alexandra Silva. Automata Learning with an Incomplete Teacher. In 37th European Conference on Object-Oriented Programming (ECOOP 2023). Leibniz International Proceedings in Informatics (LIPIcs), Volume 263, pp. 21:1-21:30, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)

Copy BibTex To Clipboard

@InProceedings{moeller_et_al:LIPIcs.ECOOP.2023.21,
  author =	{Moeller, Mark and Wiener, Thomas and Solko-Breslin, Alaia and Koch, Caleb and Foster, Nate and Silva, Alexandra},
  title =	{{Automata Learning with an Incomplete Teacher}},
  booktitle =	{37th European Conference on Object-Oriented Programming (ECOOP 2023)},
  pages =	{21:1--21:30},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-281-5},
  ISSN =	{1868-8969},
  year =	{2023},
  volume =	{263},
  editor =	{Ali, Karim and Salvaneschi, Guido},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ECOOP.2023.21},
  URN =		{urn:nbn:de:0030-drops-182145},
  doi =		{10.4230/LIPIcs.ECOOP.2023.21},
  annote =	{Keywords: Finite Automata, Active Learning, SMT Solvers}
}
Document
Artifact
DOI: 10.4230/DARTS.9.2.21
Automata Learning with an Incomplete Teacher (Artifact)

Authors: Mark Moeller, Thomas Wiener, Alaia Solko-Breslin, Caleb Koch, Nate Foster, and Alexandra Silva

Published in: DARTS, Volume 9, Issue 2, Special Issue of the 37th European Conference on Object-Oriented Programming (ECOOP 2023)

Abstract
We provide an implementation of the automata learning software described in the associated ECOOP article. In particular, the artifact is a Docker image with the source code for nerode and nerode-learn, along with the scripts and benchmark inputs needed to reproduce the experiments described in the paper.
Cite as

Mark Moeller, Thomas Wiener, Alaia Solko-Breslin, Caleb Koch, Nate Foster, and Alexandra Silva. Automata Learning with an Incomplete Teacher (Artifact). In Special Issue of the 37th European Conference on Object-Oriented Programming (ECOOP 2023). Dagstuhl Artifacts Series (DARTS), Volume 9, Issue 2, pp. 21:1-21:3, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)

Copy BibTex To Clipboard

@Article{moeller_et_al:DARTS.9.2.21,
  author =	{Moeller, Mark and Wiener, Thomas and Solko-Breslin, Alaia and Koch, Caleb and Foster, Nate and Silva, Alexandra},
  title =	{{Automata Learning with an Incomplete Teacher (Artifact)}},
  pages =	{21:1--21:3},
  journal =	{Dagstuhl Artifacts Series},
  ISSN =	{2509-8195},
  year =	{2023},
  volume =	{9},
  number =	{2},
  editor =	{Moeller, Mark and Wiener, Thomas and Solko-Breslin, Alaia and Koch, Caleb and Foster, Nate and Silva, Alexandra},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/DARTS.9.2.21},
  URN =		{urn:nbn:de:0030-drops-182612},
  doi =		{10.4230/DARTS.9.2.21},
  annote =	{Keywords: Finite Automata, Active Learning, SMT Solvers}
}
Document
DOI: 10.4230/LIPIcs.ITCS.2023.18
Certification with an NP Oracle

Authors: Guy Blanc, Caleb Koch, Jane Lange, Carmen Strassle, and Li-Yang Tan

Published in: LIPIcs, Volume 251, 14th Innovations in Theoretical Computer Science Conference (ITCS 2023)

Abstract
In the certification problem, the algorithm is given a function f with certificate complexity k and an input x^⋆, and the goal is to find a certificate of size ≤ poly(k) for f’s value at x^⋆. This problem is in NP^NP, and assuming 𝖯 ≠ NP, is not in 𝖯. Prior works, dating back to Valiant in 1984, have therefore sought to design efficient algorithms by imposing assumptions on f such as monotonicity. Our first result is a BPP^NP algorithm for the general problem. The key ingredient is a new notion of the balanced influence of variables, a natural variant of influence that corrects for the bias of the function. Balanced influences can be accurately estimated via uniform generation, and classic BPP^NP algorithms are known for the latter task. We then consider certification with stricter instance-wise guarantees: for each x^⋆, find a certificate whose size scales with that of the smallest certificate for x^⋆. In sharp contrast with our first result, we show that this problem is NP^NP-hard even to approximate. We obtain an optimal inapproximability ratio, adding to a small handful of problems in the higher levels of the polynomial hierarchy for which optimal inapproximability is known. Our proof involves the novel use of bit-fixing dispersers for gap amplification.
Cite as

Guy Blanc, Caleb Koch, Jane Lange, Carmen Strassle, and Li-Yang Tan. Certification with an NP Oracle. In 14th Innovations in Theoretical Computer Science Conference (ITCS 2023). Leibniz International Proceedings in Informatics (LIPIcs), Volume 251, pp. 18:1-18:22, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)

Copy BibTex To Clipboard

@InProceedings{blanc_et_al:LIPIcs.ITCS.2023.18,
  author =	{Blanc, Guy and Koch, Caleb and Lange, Jane and Strassle, Carmen and Tan, Li-Yang},
  title =	{{Certification with an NP Oracle}},
  booktitle =	{14th Innovations in Theoretical Computer Science Conference (ITCS 2023)},
  pages =	{18:1--18:22},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-263-1},
  ISSN =	{1868-8969},
  year =	{2023},
  volume =	{251},
  editor =	{Tauman Kalai, Yael},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ITCS.2023.18},
  URN =		{urn:nbn:de:0030-drops-175217},
  doi =		{10.4230/LIPIcs.ITCS.2023.18},
  annote =	{Keywords: Certificate complexity, Boolean functions, polynomial hierarchy, hardness of approximation}
}
  • Refine by Type
  • 8 Document/PDF
  • 3 Document/HTML

  • Refine by Publication Year
  • 1 2026
  • 3 2025
  • 1 2024
  • 3 2023

  • Refine by Author
  • 5 Koch, Caleb
  • 3 Blanc, Guy
  • 3 Strassle, Carmen
  • 3 Tan, Li-Yang
  • 2 Foster, Nate
  • Show More...

  • Refine by Series/Journal
  • 7 LIPIcs
  • 1 DARTS

  • Refine by Classification
  • 3 Theory of computation → Computational complexity and cryptography
  • 2 Theory of computation → Active learning
  • 1 Theory of computation → Boolean function learning
  • 1 Theory of computation → Machine learning theory
  • 1 Theory of computation → Oracles and decision trees

  • Refine by Keyword
  • 2 Active Learning
  • 2 Finite Automata
  • 2 SMT Solvers
  • 1 Boolean functions
  • 1 Certificate complexity
  • Show More...

Any Issues?
X

Feedback on the Current Page

CAPTCHA

Thanks for your feedback!

Feedback submitted to Dagstuhl Publishing

Could not send message

Please try again later or send an E-mail
© 2023-2026 Schloss Dagstuhl – LZI GmbH Schloss Dagstuhl – LZI GmbH About DROPS Imprint Privacy Contact