Optimal Rates for Learning with Monotone Adversaries

• URL: http://arxiv.org/abs/2608.06337v1
• Date: Thu, 06 Aug 2026 17:45:32 GMT
• Title: Optimal Rates for Learning with Monotone Adversaries
• Abstract summary: A monotone adversary observes an i.i.d. labeled sample and appends a finite number of further examples of its choice.<n>Every example is correctly labeled, but the insertions depend on the clean sample, so the combined sample is not exchangeable.<n>Larsen, Pabbaraju, and Shetty, who introduced this model, show that empirical risk minimization attains expected error $O((d/n)log(n/d))$ for classes of VC dimension $d$.
• Score: 7.053805156684374
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A monotone adversary observes an i.i.d. labeled sample and appends a finite number of further examples of its choice, every one of them labeled correctly by the target hypothesis. The learner sees a uniform shuffle of the combined sample and is scored on the original distribution. Every example is correctly labeled, but the insertions depend on the clean sample, so the combined sample is not exchangeable. Larsen, Pabbaraju, and Shetty, who introduced this model, showed that empirical risk minimization attains expected error $O((d/n)\log(n/d))$ for classes of VC dimension $d$, and that every known optimal learner can be pushed away from the $Θ(d/n)$ rate, optimal for PAC learning. They asked whether the extra logarithm is an artifact of those particular algorithms or an inherent consequence of the lack of exchangeability. We show that this additional cost is inherent beyond VC dimension one. In the worst case over classes of VC dimension $d$ and over known finite insertion budgets, the minimax expected error is $Θ(1/n)$ at $d=1$ and $Θ((d/n)\log(n/d))$ for $d\geq 2$. The same rates hold with Littlestone dimension $d_{\mathrm L}$ in place of $d$, so the clean online-to-batch rate $O(d_{\mathrm L}/n)$ is unattainable as well. Thus, somewhat counterintuitively, adding correctly labeled examples can make learning harder by a logarithmic factor, even for classes that admit finite mistake bounds in online learning. The dimension-one upper bound is achieved by a simple improper learner whose analysis adapts the leave-one-out argument underlying the one-inclusion graph. All of our lower bounds are elementary and come from a single construction: an explicit class and prior on which two target hypothesis, which differ a point of nonnegligible mass, produce the same sample.

Related papers

• Multiscale Reward Hedging from Correct Demonstrations [1.14219428942199]
  Existing reward-hedging guarantees assume a finite reward class.<n>Key is to hedge in one shared vote over tolerant optimality tests at every accuracy scale.
  arXiv  Detail & Related papers  (2026-08-07T05:36:22Z)
• Efficiently Learning Drifting Halfspaces with Massart Noise [50.4331323695175]
  We study the problem of learning a drifting concept in the presence of Massart noise.<n>In this framework, an online learner has access to a history of independent samples.<n>The goal is to output, in each round, a hypothesis with small prediction error.
  arXiv  Detail & Related papers  (2026-06-09T17:35:18Z)
• Hard labels sampled from sparse targets mislead rotation invariant algorithms [6.565070116874382]
  In binary logistic regression, the feedback can be either soft labels, corresponding to the true conditional probability of the data, or sampled hard labels.<n>We show that when the examples are labeled by hard labels $y_i$ sampled from the same conditional distribution $(mathbfx_itopmathbfwstar)$ and $mathbfwstar$ is $s$-sparse, then rotation-invariant algorithms are provably suboptimal.
  arXiv  Detail & Related papers  (2026-03-21T22:38:24Z)
• Reliable Abstention under Adversarial Injections: Tight Lower Bounds and New Upper Bounds [16.636823007179082]
  We study online learning in the adversarial injection model introduced by [Goel et al. 2017].<n>We prove a matching $(sqrtT)$ lower bound for VC dimension $1$, establishing a sharp separation between the two information regimes.<n>We introduce a potential-based framework driven by emphrobust witnesses, small subsets of labeled examples that certify predictions remaining resilient to adversarial contamination.
  arXiv  Detail & Related papers  (2026-02-23T18:30:48Z)
• Self-Directed Linear Classification [50.659479930171585]
  In online classification, a learner aims to predict their labels in an online fashion so as to minimize the total number of mistakes. Here we study the power of choosing the prediction order and establish the first strong separation between worst-order and random-order learning.
  arXiv  Detail & Related papers  (2023-08-06T15:38:44Z)
• Statistical Learning under Heterogeneous Distribution Shift [71.8393170225794]
  Ground-truth predictor is additive $mathbbE[mathbfz mid mathbfx,mathbfy] = f_star(mathbfx) +g_star(mathbfy)$.
  arXiv  Detail & Related papers  (2023-02-27T16:34:21Z)
• Horizon-Free and Variance-Dependent Reinforcement Learning for Latent Markov Decision Processes [62.90204655228324]
  We study regret minimization for reinforcement learning (RL) in Latent Markov Decision Processes (LMDPs) with context in hindsight. We design a novel model-based algorithmic framework which can be instantiated with both a model-optimistic and a value-optimistic solver.
  arXiv  Detail & Related papers  (2022-10-20T21:32:01Z)
• Tight Bounds on the Hardness of Learning Simple Nonparametric Mixtures [9.053430799456587]
  We study the problem of learning nonparametric distributions in a finite mixture. We establish tight bounds on the sample complexity for learning the component distributions in such models.
  arXiv  Detail & Related papers  (2022-03-28T23:53:48Z)
• Littlestone Classes are Privately Online Learnable [28.04975353867202]
  We consider the problem of online classification under a privacy constraint. In this setting a learner observes sequentially a stream of labelled examples $(x_t, y_t)$, for $1 leq t leq T$, and returns at each iteration a hypothesis $h_t$ which is used to predict the label of each new example $x_t$. The learner's performance is measured by her regret against a known hypothesis class $mathcalH$.
  arXiv  Detail & Related papers  (2021-06-25T09:08:33Z)
• Learning the optimal regularizer for inverse problems [1.763934678295407]
  We consider the linear inverse problem $y=Ax+epsilon$, where $Acolon Xto Y$ is a known linear operator between the separable Hilbert spaces $X$ and $Y$. This setting covers several inverse problems in imaging including denoising, deblurring, and X-ray tomography. Within the classical framework of regularization, we focus on the case where the regularization functional is not given a priori but learned from data.
  arXiv  Detail & Related papers  (2021-06-11T17:14:27Z)
• The Sample Complexity of Robust Covariance Testing [56.98280399449707]
  We are given i.i.d. samples from a distribution of the form $Z = (1-epsilon) X + epsilon B$, where $X$ is a zero-mean and unknown covariance Gaussian $mathcalN(0, Sigma)$. In the absence of contamination, prior work gave a simple tester for this hypothesis testing task that uses $O(d)$ samples. We prove a sample complexity lower bound of $Omega(d2)$ for $epsilon$ an arbitrarily small constant and $gamma
  arXiv  Detail & Related papers  (2020-12-31T18:24:41Z)
• Hardness of Learning Halfspaces with Massart Noise [56.98280399449707]
  We study the complexity of PAC learning halfspaces in the presence of Massart (bounded) noise. We show that there an exponential gap between the information-theoretically optimal error and the best error that can be achieved by a SQ algorithm.
  arXiv  Detail & Related papers  (2020-12-17T16:43:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.