DROPS

Document

Extended Abstract

DOI: 10.4230/LIPIcs.FORC.2025.18

Differentially Private Sequential Learning (Extended Abstract)

Authors: Yuxin Liu and M. Amin Rahimian

Published in: LIPIcs, Volume 329, 6th Symposium on Foundations of Responsible Computing (FORC 2025)

Abstract

In a differentially private sequential learning setting, agents introduce endogenous noise into their public actions to limit information leakage about their private signals. The impact of this privacy noise varies depending on whether the signals are continuous or binary. For continuous signals and a finite privacy budget ε > 0, we propose a smooth randomized response mechanism that adapts the noise level based on the distance to a decision threshold, in contrast to the standard randomized response with uniform noise. This allows agents’ actions to better reflect both their private signals and public history, achieving an accelerated convergence rate of Θ_ε(log n), surpassing the rate of Θ(√{log n}) in the non-private regime. In this case, privacy noise helps to amplify the log-likelihood ratio over time, improving information aggregation. For binary signals, differential privacy consistently degrades learning performance by reducing the probability of correct cascades compared to the non-private baseline. In this case, agents tend to use a constant randomized response strategy before the information cascade occurs. This constant privacy noise reduces the informativeness of their actions and hinders effective learning until an information cascade occurs. However, even for binary signals, the probability of correct cascades does not vary monotonically with the privacy budget ε. There are values of ε where the probability of a correct cascade increases as the privacy budget decreases because the threshold for initiating an information cascade increases by one when the privacy budget crosses below those values.

Cite as

Yuxin Liu and M. Amin Rahimian. Differentially Private Sequential Learning (Extended Abstract). In 6th Symposium on Foundations of Responsible Computing (FORC 2025). Leibniz International Proceedings in Informatics (LIPIcs), Volume 329, pp. 18:1-18:6, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@InProceedings{liu_et_al:LIPIcs.FORC.2025.18,
  author =	{Liu, Yuxin and Rahimian, M. Amin},
  title =	{{Differentially Private Sequential Learning}},
  booktitle =	{6th Symposium on Foundations of Responsible Computing (FORC 2025)},
  pages =	{18:1--18:6},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-367-6},
  ISSN =	{1868-8969},
  year =	{2025},
  volume =	{329},
  editor =	{Bun, Mark},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.FORC.2025.18},
  URN =		{urn:nbn:de:0030-drops-231450},
  doi =		{10.4230/LIPIcs.FORC.2025.18},
  annote =	{Keywords: Differential Privacy, Sequential Learning, Randomized Response, Learning Efficiency}
}

Document

DOI: 10.4230/LIPIcs.STACS.2025.50

Designing Exploration Contracts

Authors: Martin Hoefer, Conrad Schecker, and Kevin Schewior

Published in: LIPIcs, Volume 327, 42nd International Symposium on Theoretical Aspects of Computer Science (STACS 2025)

Abstract

We study a natural application of contract design in the context of sequential exploration problems. In our principal-agent setting, a search task is delegated to an agent. The agent performs a sequential exploration of n boxes, suffers the exploration cost for each inspected box, and selects the content (called the prize) of one inspected box as outcome. Agent and principal obtain an individual value based on the selected prize. To influence the search, the principal a-priori designs a contract with a non-negative payment to the agent for each potential prize. The goal of the principal is to maximize her expected reward, i.e., value minus payment. Interestingly, this natural contract scenario shares close relations with the Pandora’s Box problem. We show how to compute optimal contracts for the principal in several scenarios. A popular and important subclass is that of linear contracts, and we show how to compute optimal linear contracts in polynomial time. For general contracts, we obtain optimal contracts under the standard assumption that the agent suffers cost but obtains value only from the transfers by the principal. More generally, for general contracts with non-zero agent values for outcomes we show how to compute an optimal contract in two cases: (1) when each box has only one prize with non-zero value for principal and agent, (2) for i.i.d. boxes with a single prize with positive value for the principal.

Cite as

Martin Hoefer, Conrad Schecker, and Kevin Schewior. Designing Exploration Contracts. In 42nd International Symposium on Theoretical Aspects of Computer Science (STACS 2025). Leibniz International Proceedings in Informatics (LIPIcs), Volume 327, pp. 50:1-50:19, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@InProceedings{hoefer_et_al:LIPIcs.STACS.2025.50,
  author =	{Hoefer, Martin and Schecker, Conrad and Schewior, Kevin},
  title =	{{Designing Exploration Contracts}},
  booktitle =	{42nd International Symposium on Theoretical Aspects of Computer Science (STACS 2025)},
  pages =	{50:1--50:19},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-365-2},
  ISSN =	{1868-8969},
  year =	{2025},
  volume =	{327},
  editor =	{Beyersdorff, Olaf and Pilipczuk, Micha{\l} and Pimentel, Elaine and Thắng, Nguy\~{ê}n Kim},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.STACS.2025.50},
  URN =		{urn:nbn:de:0030-drops-228755},
  doi =		{10.4230/LIPIcs.STACS.2025.50},
  annote =	{Keywords: Exploration, Contract Design, Pandora’s Box Problem}
}

Document

DOI: 10.4230/LIPIcs.ITCS.2025.84

Quantum Communication Complexity of Classical Auctions

Authors: Aviad Rubinstein and Zixin Zhou

Published in: LIPIcs, Volume 325, 16th Innovations in Theoretical Computer Science Conference (ITCS 2025)

Abstract

We study the fundamental, classical mechanism design problem of single-buyer multi-item Bayesian revenue-maximizing auctions under the lens of communication complexity between the buyer and the seller. Specifically, we ask whether using quantum communication can be more efficient than classical communication. We have two sets of results, revealing a surprisingly rich landscape - which looks quite different from both quantum communication in non-strategic parties, and classical communication in mechanism design. We first study the expected communication complexity of approximately optimal auctions. We give quantum auction protocols for buyers with unit-demand or combinatorial valuations that obtain an arbitrarily good approximation of the optimal revenue while running in exponentially more efficient communication compared to classical approximately optimal auctions. However, these auctions come with the caveat that they may require the seller to charge exponentially large payments from a deviating buyer. We show that this caveat is necessary - we give an exponential lower bound on the product of the expected quantum communication and the maximum payment. We then study the worst-case communication complexity of exactly optimal auctions in an extremely simple setting: additive buyer’s valuations over two items. We show the following separations: - There exists a prior where the optimal classical auction protocol requires infinitely many bits, but a one-way message of 1 qubit and 2 classical bits suffices. - There exists a prior where no finite one-way quantum auction protocol can obtain the optimal revenue. However, there is a barely-interactive revenue-optimal quantum auction protocol with the following simple structure: the seller prepares a pair of qubits in the EPR state, sends one of them to the buyer, and then the buyer sends 1 qubit and 2 classical bits. - There exists a prior where no multi-round quantum auction protocol with a finite bound on communication complexity can obtain the optimal revenue.

Cite as

Aviad Rubinstein and Zixin Zhou. Quantum Communication Complexity of Classical Auctions. In 16th Innovations in Theoretical Computer Science Conference (ITCS 2025). Leibniz International Proceedings in Informatics (LIPIcs), Volume 325, pp. 84:1-84:27, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2025)

Copy BibTex To Clipboard

@InProceedings{rubinstein_et_al:LIPIcs.ITCS.2025.84,
  author =	{Rubinstein, Aviad and Zhou, Zixin},
  title =	{{Quantum Communication Complexity of Classical Auctions}},
  booktitle =	{16th Innovations in Theoretical Computer Science Conference (ITCS 2025)},
  pages =	{84:1--84:27},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-361-4},
  ISSN =	{1868-8969},
  year =	{2025},
  volume =	{325},
  editor =	{Meka, Raghu},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ITCS.2025.84},
  URN =		{urn:nbn:de:0030-drops-227124},
  doi =		{10.4230/LIPIcs.ITCS.2025.84},
  annote =	{Keywords: Mechanism design, Communication complexity, Quantum computing}
}

Document

DOI: 10.4230/LIPIcs.ITCS.2022.11

Multi-Channel Bayesian Persuasion

Authors: Yakov Babichenko, Inbal Talgam-Cohen, Haifeng Xu, and Konstantin Zabarnyi

Published in: LIPIcs, Volume 215, 13th Innovations in Theoretical Computer Science Conference (ITCS 2022)

Abstract

The celebrated Bayesian persuasion model considers strategic communication between an informed agent (the sender) and uninformed decision makers (the receivers). The current rapidly-growing literature assumes a dichotomy: either the sender is powerful enough to communicate separately with each receiver (a.k.a. private persuasion), or she cannot communicate separately at all (a.k.a. public persuasion). We propose a model that smoothly interpolates between the two, by introducing a natural multi-channel communication structure in which each receiver observes a subset of the sender’s communication channels. This captures, e.g., receivers on a network, where information spillover is almost inevitable. Our main result is a complete characterization specifying when one communication structure is better for the sender than another, in the sense of yielding higher optimal expected utility universally over all prior distributions and utility functions. The characterization is based on a simple pairwise relation among receivers - one receiver information-dominates another if he observes at least the same channels. We prove that a communication structure M₁ is (weakly) better than M₂ if and only if every information-dominating pair of receivers in M₁ is also such in M₂. This result holds in the most general model of Bayesian persuasion in which receivers may have externalities - that is, the receivers' actions affect each other. The proof is cryptographic-inspired and it has a close conceptual connection to secret sharing protocols. As a surprising consequence of the main result, the sender can implement private Bayesian persuasion (which is the best communication structure for the sender) for k receivers using only O(log k) communication channels, rather than k channels in the naive implementation. We provide an implementation that matches the information-theoretical lower bound on the number of channels - not only asymptotically, but exactly. Moreover, the main result immediately implies some results of [Kerman and Tenev, 2021] on persuading receivers arranged in a network such that each receiver observes both the signals sent to him and to his neighbours in the network. We further provide an additive FPTAS for an optimal sender’s signaling scheme when the number of states of nature is constant, the sender has an additive utility function and the graph of the information-dominating pairs of receivers is a directed forest. We focus on a constant number of states, as even for the special case of public persuasion and additive sender’s utility, it was shown by [Shaddin Dughmi and Haifeng Xu, 2017] that one can achieve neither an additive PTAS nor a polynomial-time constant-factor optimal sender’s utility approximation (unless P=NP). We leave for future research studying exact tractability of forest communication structures, as well as generalizing our result to more families of sender’s utility functions and communication structures. Finally, we prove that finding an optimal signaling scheme under multi-channel persuasion is computationally hard for a general family of sender’s utility functions - separable supermajority functions, which are specified by choosing a partition of the set of receivers and summing supermajority functions corresponding to different elements of the partition, multiplied by some non-negative constants. Note that one can easily deduce from [Emir Kamenica and Matthew Gentzkow, 2011] and [Itai Arieli and Yakov Babichenko, 2019] that finding an optimal signaling scheme for such utility functions is computationally tractable for both public and private persuasion. This difference illustrates both the conceptual and the computational hardness of general multi-channel persuasion.

Cite as

Yakov Babichenko, Inbal Talgam-Cohen, Haifeng Xu, and Konstantin Zabarnyi. Multi-Channel Bayesian Persuasion. In 13th Innovations in Theoretical Computer Science Conference (ITCS 2022). Leibniz International Proceedings in Informatics (LIPIcs), Volume 215, pp. 11:1-11:2, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)

Copy BibTex To Clipboard

@InProceedings{babichenko_et_al:LIPIcs.ITCS.2022.11,
  author =	{Babichenko, Yakov and Talgam-Cohen, Inbal and Xu, Haifeng and Zabarnyi, Konstantin},
  title =	{{Multi-Channel Bayesian Persuasion}},
  booktitle =	{13th Innovations in Theoretical Computer Science Conference (ITCS 2022)},
  pages =	{11:1--11:2},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-217-4},
  ISSN =	{1868-8969},
  year =	{2022},
  volume =	{215},
  editor =	{Braverman, Mark},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ITCS.2022.11},
  URN =		{urn:nbn:de:0030-drops-156072},
  doi =		{10.4230/LIPIcs.ITCS.2022.11},
  annote =	{Keywords: Algorithmic game theory, Bayesian persuasion, Private Bayesian persuasion, Public Bayesian persuasion, Secret sharing, Networks}
}

Document

DOI: 10.4230/LIPIcs.ITCS.2017.34

Algorithmic Aspects of Private Bayesian Persuasion

Authors: Yakov Babichenko and Siddharth Barman

Published in: LIPIcs, Volume 67, 8th Innovations in Theoretical Computer Science Conference (ITCS 2017)

Abstract

We consider a multi-receivers Bayesian persuasion model where an informed sender tries to persuade a group of receivers to take a certain action. The state of nature is known to the sender, but it is unknown to the receivers. The sender is allowed to commit to a signaling policy where she sends a private signal to every receiver. This work studies the computation aspects of finding a signaling policy that maximizes the sender's revenue. We show that if the sender's utility is a submodular function of the set of receivers that take the desired action, then we can efficiently find a signaling policy whose revenue is at least (1-1/e) times the optimal. We also prove that approximating the sender's optimal revenue by a factor better than (1-1/e) is NP-hard and, hence, the developed approximation guarantee is essentially tight. When the sender's utility is a function of the number of receivers that take the desired action (i.e., the utility function is anonymous), we show that an optimal signaling policy can be computed in polynomial time. Our results are based on an interesting connection between the Bayesian persuasion problem and the evaluation of the concave closure of a set function.

Cite as

Yakov Babichenko and Siddharth Barman. Algorithmic Aspects of Private Bayesian Persuasion. In 8th Innovations in Theoretical Computer Science Conference (ITCS 2017). Leibniz International Proceedings in Informatics (LIPIcs), Volume 67, pp. 34:1-34:16, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2017)

Copy BibTex To Clipboard

@InProceedings{babichenko_et_al:LIPIcs.ITCS.2017.34,
  author =	{Babichenko, Yakov and Barman, Siddharth},
  title =	{{Algorithmic Aspects of Private Bayesian Persuasion}},
  booktitle =	{8th Innovations in Theoretical Computer Science Conference (ITCS 2017)},
  pages =	{34:1--34:16},
  series =	{Leibniz International Proceedings in Informatics (LIPIcs)},
  ISBN =	{978-3-95977-029-3},
  ISSN =	{1868-8969},
  year =	{2017},
  volume =	{67},
  editor =	{Papadimitriou, Christos H.},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ITCS.2017.34},
  URN =		{urn:nbn:de:0030-drops-81502},
  doi =		{10.4230/LIPIcs.ITCS.2017.34},
  annote =	{Keywords: Economics of Information, Bayesian Persuasion, Signaling, Concave Closure}
}

5 Search Results for "Babichenko, Yakov"

Differentially Private Sequential Learning (Extended Abstract)

Abstract

Cite as

Designing Exploration Contracts

Abstract

Cite as

Quantum Communication Complexity of Classical Auctions

Abstract

Cite as

Multi-Channel Bayesian Persuasion

Abstract

Cite as

Algorithmic Aspects of Private Bayesian Persuasion

Abstract

Cite as

Thanks for your feedback!

Could not send message