betaFeedback

WorksComputer Science

Regret Bounds for Profit Maximization in Bilateral Trade: Learning the Best Posted-Price Mechanism

Abstract

Bilateral trade models the task of intermediating between two strategic agents, a seller and a buyer, willing to trade a good for which they hold private valuations. We study this problem from the perspective of a profit-maximizing broker in a regret minimization framework. At each time step, a new seller and buyer arrive and the broker proposes a trading price to each agent. The trade happens if both agents accept, and the profit of the broker is the difference between the price received from the buyer and the one paid to the seller. At the end of each interaction, the learner only observes whether the trade occurred, and its goal is to achieve sublinear regret relative to the best fixed pair of prices in hindsight. We start by investigating the adversarial version of the problem, where buyer and seller valuations are generated by an adversary. In this setting, we construct a polynomial-time learning algorithm with a O~(T23)\tilde O(T^{\frac 23}) regret rate, which is nearly tight even if the valuations are drawn i.i.d. from independent distributions, thus matching the rate for one-sided pricing. Our adversarial algorithm combines a localized estimation procedure with an information-based minimax construction. We then consider valuations drawn i.i.d. from independent distributions satisfying the monotone-hazard-rate (MHR) property and provide a learning algorithm with nearly tight O~(T)\tilde{O}(\sqrt{T}) regret. The algorithm combines localized estimation with a stochastic convex bandit routine applied to the negative logarithm of expected profit. Finally, we complement this result by showing a separation between MHR and regular distributions, proving that the minimax regret rate in the latter setting is Θ~(T35)\tilde Θ(T^{\frac 35}). This last result contrasts with the O~(T)\tilde{O}(\sqrt{T}) regret bound that can be obtained for one-sided pricing with regular distributions.

Introduction

Bilateral trade studies the interaction of two agents—a seller and a buyer—interested in trading a good [e.g., 38]. Each agent holds a private valuation for the good, and they strive to maximize their own utility. Designing “good” mechanisms for bilateral trade is a fundamental problem in economics and has been studied extensively in the computer science community [e.g., 16, 9, 4, 8, 22, 18, 29, 35, 10, 6, 25]. There are two natural objectives that a broker tasked with designing a mechanism for bilateral trade may be interested in maximizing: social welfare, often measured in terms of its increase, the gains from trade, and profit. The predominant approach considered in prior work is Bayesian, as it assumes that both agents’ valuations are drawn from known and typically independent distributions. In many practical applications, however, knowledge of these distributions is a non-trivial assumption, and valuations may not be independent.

In this work, we study profit maximization in repeated bilateral trade through the lens of online learning [e.g., 7, 31, 13]. While a substantial literature studies social welfare maximization [e.g., 14, 15, 3, 6, 36], only recently has the literature started investigating profit from a regret-minimizing perspective, with Di Gregorio et al. [19, 20] providing a complete characterization of the minimax regret regimes for profit maximization when the learner is allowed to post any mechanism which ensures dominant-strategy incentive compatibility and individual rationality. While these general mechanisms for bilateral trade are very expressive, they may be fairly complex and, crucially, require agents to submit their actual valuations to the learner.

In this work, we focus on the important and natural family of posted-price mechanisms. In a posted-price mechanism, the broker just posts two prices, one for the seller and one for the buyer, and the trade happens if and only if both agents agree to trade for the proposed price. These simple mechanisms are specified by two numbers and require each agent only to accept or reject an offer.

We consider two families of data-generation models for the online valuations: the adversarial model, where an oblivious adversary fixes the agents’ valuations before play, and the stochastic model, where valuation pairs are drawn i.i.d. from a fixed unknown distribution. Our benchmark is the best fixed pair of prices, evaluated on the input sequence in the adversarial setting and in expectation in the stochastic setting. We seek algorithms whose expected cumulative profit falls short of this benchmark by a quantity sublinear in the time horizon TT.

Our Results

We characterize the minimax regret rates for the data-generation models below, up to polylogarithmic factors. See Table 1 for a summary. All upper bounds use one-bit feedback (whether both offers were accepted), whereas the lower bounds hold even with two-bit feedback (the seller’s and buyer’s acceptance decisions observed separately).

  • For an oblivious adversary, our algorithm guarantees O(T2/3log⁡7/3T)O(T^{2/3}\log^{7/3} T) regret (Thm. 4.1). Given the lower bound of Ω(T2/3)\Omega(T^{2/3}) for one-sided pricing [31], our algorithm is nearly tight even when the agents’ valuations are drawn i.i.d. from generic independent distributions. Indeed, setting the seller’s value identically to zero embeds one-sided pricing: the seller always accepts, and a positive seller price only reduces profit without providing additional information.

  • For valuations drawn i.i.d. from independent regular distributions, we obtain O(T3/5log⁡5T)O(T^{3/5}\log^5 T) regret (Thm. 6.1), complemented by a matching Ω(T3/5)\Omega(T^{3/5}) lower bound, up to logarithmic factors (Thm. 7.1).

  • For independent MHR valuations we get O(Tlog⁡5/2T)O(\sqrt{T}\log^{5/2} T) regret (Thm. 5.1), which is nearly tight [34].2

First, it is interesting to compare the bilateral trade regret rates with those for the one-dimensional problem of (one-sided) pricing [31], where the learner only interacts with the buyer. There, the adversarial rate is the same, but when it comes to regularity there is a clear differentiation: regularity and MHR yield the same T\sqrt{T} rate in one-sided pricing [40, 34], while bilateral trade exhibits two intriguing rates, i.e., T\sqrt{T} for MHR and the novel (and surprising) rate of T3/5T^{3/5} for regular distributions.

SettingDistribution assumptionsMinimax regret
Adversarial—O~(T2/3)\widetilde{O}(T^{2/3}) – Thm. 4.1
Stochastic SettingGeneric
Stochastic SettingIndependentΩ(T2/3)\Omega(T^{2/3}) – [31]
Stochastic SettingIndependent & RegularΘ~(T3/5)\widetilde{\Theta}(T^{3/5}) – Thms. 6.1 & 7.1
Stochastic SettingIndependent & MHRΘ~(T)\widetilde{\Theta}(\sqrt{T}) – Thms. 5.1 & [34]

Table 1. Minimax regret rates for profit maximization with posted prices in bilateral trade. Entries with the same color share the same minimax rate. The adversarial positive result applies to all other settings, while the lower bound for i.i.d. distributions with independent marginals also applies to the generic stochastic setting and the adversarial one.

Second, a comparison with previous work on regret minimization in bilateral trade is also instructive. While for gain-from-trade maximization (and profit maximization with generic mechanisms) there is typically a separation between the adversarial and the stochastic settings, where the former allows for no-regret only under additional assumptions (such as σ\sigma-smoothness) [5, 19, 20], this does not happen for our problem. In particular, faster rates are here allowed by classical mechanism design concepts, namely regularity and monotone hazard rate. This is partly due to an exciting and novel connection between online bilateral trade and online convex optimization: MHR makes the negative logarithm of expected profit convex, while regularity yields a family of auxiliary profit functions with convex reciprocals.

Challenges

Finding profit-maximizing posted prices poses two challenges: exploiting the structure of the profit function and learning from one-bit feedback. Two generic approaches illustrate why additional ideas are needed.

Structure of Profit. The profit function exhibits a convenient one-sided Lipschitzness property: raising the seller’s price and lowering the buyer’s price preserves every previously accepted trade while lowering the profit proportionally to the displacement. Therefore, we can effectively discretize the action space [0,1]2[0,1]^2: restricting the algorithm’s attention to the uniform grid GKG_K of mesh 1/K1/K, with Θ(K2)\Theta(K^2) pairs of prices, induces a discretization error of at most ≈T/K\approx T/K (more on this in Lemma A.6). Treating these pairs as unrelated arms and running a finite-armed bandit algorithm yields

RT≲K2T+2TK≈T3/4,R_T \lesssim\sqrt{K^2T}+\frac{2T}{K}\approx T^{3/4},

for the right tuning of K≈T1/4K\approx T^{1/4}. This is the generic argument for Lipschitz bandits in R2\mathbb{R}^2 [30]. This “naive” approach of using a uniform grid and then treating each point independently is tight for (adversarial) one-sided pricing but can be improved for certain classes of objectives using more refined notions of dimension, both in the stochastic and adversarial worlds [30, 39]. Unfortunately, these off-the-shelf approaches do not help for bilateral trade, since the zooming dimension of our problem is still 2 (see Appendix § 11).

One-Bit Feedback. The one-bit feedback is at least as informative as the bandit feedback (if you know the outcome of the trade and the prices posted, you can reconstruct exactly your profit), but is also somehow richer, as the prices are not isolated arms but share an underlying structure (so that agents accepting price (p,q)(p,q) allow you to reconstruct the profit for any (p′,q′)(p',q') with p′≥pp'\ge p). This idea is exploited in a recent work of Castiglioni et al. [12] for the stochastic version of our problem. There, they show how to uniformly ϵ\epsilon-estimate the two-dimensional CDF, and thus the profit, of the underlying distribution on the uniform grid of mesh 1/ϵ1/\epsilon, using as few as O~(1/ϵ3)\widetilde{O}(1/\epsilon^3) pricing queries (which are equivalent to our one-bit feedback). For context, estimating the reward of 1/ϵ21/\epsilon^2 independent arms in the stochastic multi-armed bandit problem requires Ω(1/ϵ4)\Omega(1/\epsilon^4) queries. It follows directly from Castiglioni et al. [12] that an explore-then-commit approach for our problem would satisfy:

RT≲1/ϵ3exploration+ϵTexploitation≈T3/4,R_T \lesssim\underset{\text{exploration}}{1/\epsilon^3}+\underset{\text{exploitation}}{\epsilon T}\approx T^{3/4},

by fine-tuning the precision ε≈T−1/4\varepsilon\approx T^{-1/4}. Although the query complexity of Castiglioni et al. [12] is optimal up to logarithmic factors, this does not imply a T3/4T^{3/4} lower bound in the online setting. Indeed, it may be possible to quickly rule out prices that are clearly suboptimal and focus the exploration on “good” candidate prices. Indeed, we show that such fine-grained estimation is possible: we propose a localized estimation procedure which allows us to acquire useful information on possibly optimal prices by only querying prices which are not “too” suboptimal.

Related work

Learning in bilateral trade. Regret minimization for bilateral trade has largely focused on gains from trade, with a range of feedback models, stochastic assumptions, and budget constraints [14, 15, 3, 6, 36]. Profit differs from gains from trade both in its objective and in the useful action space, since a broker benefits from a positive spread between the buyer and seller prices. Recent work studies profit maximization over general dominant-strategy incentive-compatible and individually rational mechanisms [19, 20], with these mechanisms having a much richer allocation rule and a different benchmark; moreover, their learning protocols can use reported valuations. We instead focus on fixed pairs of posted prices and on the single bit that reports whether the proposed trade succeeds. Accordingly, the rates are not directly comparable across these mechanism and feedback classes. For more details on online learning and bilateral trade, we refer to the survey by Bernasconi and Fusco [5].

Learning Posted Prices in Bilateral Trade. Castiglioni et al. [12] study uniform approximation of multidimensional CDFs on finite uniform grids from one-bit queries, and are the first to explicitly mention online learning of posted prices for bilateral trade as a direct application of their results, although with a non-tight O(T3/4)O(T^{3/4}) rate. We build on their use of monotonicity and shared probability estimates, but manage to achieve nearly optimal rates by localizing the one-bit queries needed to estimate profit. In subsequent work, Castiglioni et al. [11] obtain O~(T7/10)\widetilde{O}(T^{7/10}) regret for a class of stochastic i.i.d. CDF-based objectives that includes posted prices in bilateral trade. Their approach is based on an initial coarse pruning phase, complemented by ideas from the feedback graph literature [1]. Both Castiglioni et al. [12] and Castiglioni et al. [11] only study the stochastic i.i.d. setting with possibly correlated seller and buyer valuations, and do not investigate the adversarial setting or MHR and regular distributions.

Pricing and distributional structure. One-sided online pricing is a classical connection between online learning and economics [7, 31, 13]; see also Slivkins [41] for the bandit perspective. Pricing-query complexity studies how much can be learned when values are accessible only through acceptance decisions [34]. For regular distributions, Singla and Wang [40] exploit half-concavity to obtain square-root regret up to logarithmic factors for sequential posted pricing. Our separation shows that applying this intuition independently on the two sides of a market is insufficient. Our MHR algorithm instead uses concavity of the logarithm of expected bilateral profit as a function of both prices.

The Learning Model

In this paper, we study profit maximization in bilateral trade in an online learning setting. In particular, we focus our attention on the family of posted-price mechanisms. At each time step tt, a new seller and buyer arrive with private valuations (st,bt)∈[0,1]2(s_t,b_t) \in[0,1]^2. The learner posts prices (pt,qt)∈[0,1]2(p_t,q_t) \in[0,1]^2, offering ptp_t to the seller and charging qtq_t to the buyer. Trade occurs if st≤pts_t \leq p_t and qt≤btq_t \leq b_t, with ties resolved in favor of acceptance. The learner receives profit

Profit⁡t(pt,qt)=(qt−pt)⋅1{st≤pt}1{qt≤bt}.\operatorname{Profit}_t(p_t,q_t) = (q_t-p_t) \cdot\mathbf{1}_{\{s_t\leq p_t\}}\mathbf{1}_{\{q_t\leq b_t\}}.

We consider two data-generation models: the adversarial setting, where an oblivious adversary fixes an arbitrary sequence (s1,b1),…,(sT,bT)(s_1,b_1),\ldots,(s_T,b_T) before play, and the stochastic setting, where the pairs (st,bt)(s_t,b_t) are sampled i.i.d. from a fixed unknown joint distribution D\mathcal{D}. Note that, in the latter model, independence across rounds does not require independence between the two agents in a round.

Learning Protocol for Repeated Bilateral Trade

for t=1,2,…t = 1, 2, \ldots do The environment supplies the next private valuation pair (st,bt)∈[0,1]2(s_t, b_t) \in[0,1]^2 The learner posts prices (pt,qt)∈[0,1]2(p_t, q_t) \in[0,1]^2 The learner observes zt=1{st≤pt}⋅1{qt≤bt}z_t = \mathbf{1}_{\{s_t \le p_t\}} \cdot\mathbf{1}_{\{q_t \le b_t\}} and is awarded Profit⁡t(pt,qt)∈[−1,1]\operatorname{Profit}_t(p_t, q_t) \in[-1,1]

In each round, the learner receives only the trade bit zt=1{st≤pt}1{qt≤bt}z_t = \mathbf{1}_{\{s_t \le p_t\}}\mathbf{1}_{\{q_t \le b_t\}}. Its future prices may depend on its past prices, observed bits, and private randomness. We allow all pairs in [0,1]2[0,1]^2, including pt>qtp_t > q_t, which may produce negative profit. Given an algorithm A\mathcal{A} and a valuation-generating environment S\mathcal{S}, the corresponding regret is defined as

RT(A,S)=sup⁡(p,q)∈[0,1]2∑t=1TE[Profit⁡t(p,q)−Profit⁡t(pt,qt)].R_T(\mathcal{A}, \mathcal{S}) = \sup_{(p,q)\in[0,1]^2} \sum_{t=1}^{T} \mathbb{E}\left[\operatorname{Profit}_t(p,q) - \operatorname{Profit}_t(p_t,q_t)\right].

Note that the expectation is over the learner’s randomness and, in the stochastic setting, the sampled valuations. An optimal comparator can always be chosen in the compact triangle T={(p,q)∈[0,1]2:p≤q}\mathcal{T} = \{(p,q) \in[0,1]^2 : p \le q\}. Outside T\mathcal{T}, profit is nonpositive, while diagonal prices yield zero. On T\mathcal{T}, each realized profit function is bounded, nonnegative, and upper semicontinuous, so the comparator objective attains a maximum (p⋆,q⋆)(p^\star,q^\star) on T\mathcal{T}. For a class S\mathcal{S} of environments, the worst-case regret is sup⁡S∈SRT(A,S)\sup_{\mathcal{S}\in\mathcal{S}} R_T(\mathcal{A},\mathcal{S}), and the minimax regret is its infimum over learning algorithms. The learning goal is no regret: a worst-case regret bound o(T)o(T), so the expected shortfall from the benchmark, divided by TT, vanishes.

Expected profit and distributional assumptions. In the stochastic setting, we denote by μ\mu the expected profit function, so that μ(p,q)=E[Profit⁡(p,q)]\mu(p,q) = \mathbb{E}[\operatorname{Profit}(p,q)], where Profit⁡\operatorname{Profit} is the profit function when the underlying valuations are drawn according to D\mathcal{D}. Let P(p,q)=P(s,b)∼D(s≤p,b≥q)P(p,q) = \mathbb{P}_{(s,b)\sim\mathcal{D}}(s \le p, b \ge q) be the trade probability and μ⋆=μ(p⋆,q⋆)\mu^\star= \mu(p^\star,q^\star) the optimal expected profit. Then μ(p,q)=(q−p)⋅P(p,q)\mu(p,q) = (q-p) \cdot P(p,q). In particular, the regret in the stochastic setting can equivalently be written as

RT(A,D)=Tμ⋆−∑t=1TE[μ(pt,qt)].R_T(\mathcal{A},\mathcal{D}) = T\mu^\star- \sum_{t=1}^{T}\mathbb{E}[\mu(p_t,q_t)].

Our improved stochastic guarantees concern independent seller and buyer distributions, D=Ds×Db\mathcal{D} = \mathcal{D}_s \times\mathcal{D}_b, satisfying regularity or the monotone-hazard-rate property [37, 38, 26]. For these two classes, assume strictly positive probability densities fsf_s and fbf_b on [0,1][0,1], and let FsF_s and FbF_b denote their cumulative distribution functions.

Definition 2.1 (Virtual Valuations). The seller’s virtual cost ψ\psi and the buyer’s virtual value ϕ\phi are

ϕ(b)=b−1−Fb(b)fb(b), ∀b∈[0,1],ψ(s)=s+Fs(s)fs(s), ∀s∈[0,1].\phi(b) = b - \frac{1-F_b(b)}{f_b(b)}, \ \forall b \in[0,1], \qquad\psi(s) = s + \frac{F_s(s)}{f_s(s)}, \ \forall s \in[0,1].

Definition 2.2 (Regular Distribution). A seller, respectively buyer, distribution is regular if ψ\psi, respectively ϕ\phi, is nondecreasing on [0,1][0,1].

Definition 2.3 (MHR). A seller distribution satisfies the monotone hazard rate (MHR) property if its hazard rate fs/Fsf_s/F_s is nonincreasing on (0,1](0,1]. A buyer distribution satisfies MHR if its hazard rate fb/(1−Fb)f_b/(1-F_b) is nondecreasing on [0,1)[0,1).

References

  1. [1]N. Alon, N. Cesa-Bianchi, O. Dekel, and T. Koren. Online learning with feedback graphs: Beyond bandits. In COLT, volume 40 of JMLR Workshop and Conference Proceedings, pages 23–35. JMLR.org, 2015.arxiv.org/abs/1502.07617
  2. [2]S. Arora, E. Hazan, and S. Kale. The multiplicative weights update method: a meta-algorithm and applications. Theory Comput., 8(1):121–164, 2012.
  3. [3]Y. Azar, A. Fiat, and F. Fusco. An α-regret analysis of adversarial bilateral trade. Artif. Intell., 337:104231, 2024.DOI
  4. [5]M. Bernasconi and F. Fusco. An online learning perspective on bilateral trade. ACM SIGecom Exchanges, 24(1):99–122, June 2026.
  5. [6]M. Bernasconi, M. Castiglioni, A. Celli, and F. Fusco. No-regret learning in bilateral trade via global budget balance. In STOC, pages 247–258. ACM, 2024.DOI
  6. [7]A. Blum, V. Kumar, A. Rudra, and F. Wu. Online learning in online auctions. In SODA 2003, pages 202–204. ACM-SIAM, 2003.
  7. [11]M. Castiglioni, A. Lunghi, and A. Marchesi. Breaking the t³⁄⁴ barrier for regret minimization with bi-dimensional cdfs. CoRR, abs/2607.20258, 2026.arxiv.org/abs/2607.20258
  8. [12]M. Castiglioni, A. Lunghi, and A. Marchesi. The sample complexity of uniform approximation for multi-dimensional cdfs and fixed-price mechanisms. In STOC, pages 1353–1364. ACM, 2026.
  9. [13]N. Cesa-Bianchi, C. Gentile, and Y. Mansour. Regret minimization for reserve prices in second-price auctions. IEEE Trans. Inf. Theory, 61(1):549–564, 2015.
  10. [14]N. Cesa-Bianchi, T. Cesari, R. Colomboni, F. Fusco, and S. Leonardi. Bilateral trade: A regret minimization perspective. Math. Oper. Res., 49(1):171–203, 2024.
  11. [15]N. Cesa-Bianchi, T. Cesari, R. Colomboni, F. Fusco, and S. Leonardi. Regret analysis of bilateral trade with a smoothed adversary. J. Mach. Learn. Res., 25:2341–234:36, 2024.
  12. [17]M. H. DeGroot. Unbiased sequential estimation for binomial populations. The Annals of Mathematical Statistics, 30(1):80–101, 1959.DOI
  13. [19]S. Di Gregorio, P. Dütting, F. Fusco, and C. Schwiegelshohn. Nearly tight regret bounds for profit maximization in bilateral trade. In FOCS, pages 1570–1594. IEEE, 2025.DOI
  14. [20]S. Di Gregorio, P. Dütting, F. Fusco, and C. Schwiegelshohn. Profit maximization in bilateral trade against a smooth adversary. In NeurIPS, pages To appear, preprint on the arXiv abs/2605.12664, 2026.arxiv.org/abs/2605.12664
  15. [21]D. P. Dubhashi and A. Panconesi. Concentration of Measure for the Analysis of Randomized Algorithms. Cambridge University Press, 2009.DOI
  16. [23]D. J. Foster, A. Rakhlin, A. Sekhari, and K. Sridharan. On the complexity of adversarial decision making. In NeurIPS, 2022.arxiv.org/abs/2206.13063
  17. [24]W. Guo, M. I. Jordan, and E. Zampetakis. Robust learning of optimal auctions. In NeurIPS, pages 21273–21284, 2021.arxiv.org/abs/2107.06259
  18. [26]J. D. Hartline and T. Roughgarden. Simple versus optimal mechanisms. In EC, pages 225–234. ACM, 2009.
  19. [27]M. Huber. Nearly optimal bernoulli factories for linear functions. Comb. Probab. Comput., 25(4): 577–591, 2016.DOI
  20. [28]F. John. Extremum problems with inequalities as subsidiary conditions. In Studies and Essays Presented to R. Courant on His 60th Birthday, January 8, 1948, pages 187–204. Interscience Publishers, New York, 1948.
  21. [30]R. Kleinberg, A. Slivkins, and E. Upfal. Bandits and experts in metric spaces. J. ACM, 66(4):30:1–30:77, 2019.
  22. [31]R. D. Kleinberg and F. T. Leighton. The value of knowing a demand curve: Bounds on regret for online posted-price auctions. In FOCS 2003, pages 594–605. IEEE, 2003.DOI
  23. [32]T. Lattimore and A. György. Improved regret for zeroth-order stochastic convex bandits. In COLT, volume 134 of Proceedings of Machine Learning Research, pages 2938–2964. PMLR, 2021.
  24. [33]A. Lee, A. Doucet, and K. Latuszyński. Perfect simulation using atomic regeneration with application to Sequential Monte Carlo. arXiv:1407.5770, 2014.arxiv.org/abs/1407.5770
  25. [34]R. P. Leme, B. Sivan, Y. Teng, and P. Worah. Pricing query complexity of revenue maximization. In SODA, pages 399–415. SIAM, 2023.arxiv.org/abs/2111.03158
  26. [36]A. Lunghi, M. Castiglioni, and A. Marchesi. Better regret rates in bilateral trade via sublinear budget violation. In SODA, pages 6494–6536. SIAM, 2026.arxiv.org/abs/2507.11419
  27. [37]R. Myerson. Optimal auction design. Math. Oper. Res., 6(1):58–73, 1981.DOI
  28. [38]R. B. Myerson and M. A. Satterthwaite. Efficient mechanisms for bilateral trading. J. Econ. Theory, 29(2):265–281, 1983.DOI
  29. [39]C. Podimata and A. Slivkins. Adaptive discretization for adversarial lipschitz bandits. In COLT, volume 134 of Proceedings of Machine Learning Research, pages 3788–3805. PMLR, 2021.
  30. [40]S. Singla and Y. Wang. Bandit sequential posted pricing via half-concavity. In EC, pages 922–939. ACM, 2024.arxiv.org/abs/2312.12794
  31. [41]A. Slivkins. Introduction to multi-armed bandits. Found. Trends Mach. Learn., 12(1-2):1–286, 2019.arxiv.org/abs/1904.07272
  32. [42]R. Vershynin. High-Dimensional Probability: An Introduction with Applications in Data Science, volume 58 of Cambridge Series in Statistical and Probabilistic Mathematics. Cambridge University Press, 2 edition, 2026.
  33. [43]D. Williams. Probability with Martingales. Cambridge University Press, 1991.DOI
  34. [44]Y. Xu and A. Zeevi. Bayesian design principles for frequentist sequential learning. J. ACM, 72(5): 37:1–37:65, 2025.arxiv.org/abs/2310.00806

Paper details

vlnc:W_xdzte9t9
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
CC BY 4.0
Usage

views · 12

downloads · 2

A view counts once per browser per day, a download each time the PDF is requested.

  • Computer Science

ChatGPT 6 Astra, LLM assistance

View statement
Looking for related papers…
Contents