Learning Distributions from Multiple Data Providers

• URL: http://arxiv.org/abs/2607.24732v1
• Date: Mon, 27 Jul 2026 17:57:16 GMT
• Title: Learning Distributions from Multiple Data Providers
• Abstract summary: We study a stylized model of distribution learning from restricted conditional samples.<n>Learnability is governed by the co-occurrence graph associated with $mathscrS$.<n>The optimal sample complexity of PAC learning ranges from nearly linear to quadratic.
• Score: 13.95037228126825
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Motivated by learning from heterogeneous and overlapping data providers, we study a stylized model of distribution learning from restricted conditional samples. The goal is to learn an unknown distribution $p$ on a finite domain $[n]$. The learner is given a fixed family of queryable sets $\mathscr{S} \subseteq 2^{[n]}$, and each query to $S \in \mathscr{S}$ returns an independent sample from the conditional distribution $p(\cdot \mid S)$. Learnability is governed by the co-occurrence graph associated with $\mathscr{S}$: two domain elements are adjacent if they appear together in some queryable set. Pointwise consistency is achievable when this graph is connected on the target support. PAC learning requires more: it is possible when the co-occurrence graph is complete. The optimal sample complexity of PAC learning ranges from nearly linear to quadratic. Every query family with complete co-occurrence graph admits sample complexity $\widetilde O(n^2/ε^2)$, and this bound is tight in the worst case. On the other hand, if $[n]$ is queryable then ordinary sampling improves the bound to $Θ(n/ε^2)$, and this cannot be improved further even if every set is queryable. More generally, we identify hierarchical comparabilityas a sufficient structural condition on $\mathscr S$ under which the optimal complexity is nearly linear, $\widetilde Θ(n/ε^2)$, with pairwise query families as a canonical example. Finally, the full range of polynomial rates between linear and quadratic is attainable: for every $α\in (1,2)$, there exists a query family with optimal PAC rate $\widetilde Θ(n^α/ε^2)$.

Related papers

• Sample Complexity of Multicalibration for Multilevel Properties [52.27687531970317]
  We study multicalibration for a sequence of $k$ properties in which each property is identifiable once the preceding properties are fixed.<n>Even with only polylogarithmically many binary groups, achieving multicalibration error $varepsilon$ requires $widetilde(varepsilon-(k+2))$ samples.
  arXiv  Detail & Related papers  (2026-08-04T23:38:54Z)
• Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model [67.75889920324124]
  We study the sample complexity of learning an $$-optimal policy in the Shortest Path (SSP) problem.<n>We show that there exists a worst-case SSP instance with $S$ states, $A$ actions, minimum cost $c_min$, and maximum expected cost of the optimal policy over all states $B_star$.<n>Surprisingly, this implies that whenever $c_min = 0$ an SSP problem may not be learnable.
  arXiv  Detail & Related papers  (2026-04-17T14:47:52Z)
• High-accuracy sampling for diffusion models and log-concave distributions [70.90863485771405]
  We present algorithms for diffusion model sampling which obtain $$-error in $mathrmpolylog (1/)$ steps.<n>Our approach also yields the first $mathrmpolylog (1/)$ complexity sampler for general log-concave distributions.
  arXiv  Detail & Related papers  (2026-02-01T17:05:31Z)
• Robust Learning of Multi-index Models via Iterative Subspace Approximation [36.138661719725626]
  We study the task of learning Multi-Index Models (MIMs) with label noise under the Gaussian distribution.<n>We focus on well-behaved MIMs with finite ranges that satisfy certain regularity properties.<n>We show that in the presence of random classification noise, the complexity of our algorithm scales agnosticly with $1/epsilon$.
  arXiv  Detail & Related papers  (2025-02-13T17:37:42Z)
• One-Shot Learning for k-SAT [2.6293381978389787]
  We show that one-shot learning for $k$-SAT is infeasible well below the satisfiability threshold.<n>We simplify the analysis of the learning algorithm and obtain significantly stronger bounds on $d$ in terms of $beta$.
  arXiv  Detail & Related papers  (2025-02-10T23:56:08Z)
• Statistical-Computational Trade-offs for Density Estimation [60.81548752871115]
  We show that for a broad class of data structures their bounds cannot be significantly improved. This is a novel emphstatistical-computational trade-off for density estimation.
  arXiv  Detail & Related papers  (2024-10-30T15:03:33Z)
• Learning and Covering Sums of Independent Random Variables with Unbounded Support [4.458210211781738]
  We study the problem of covering and learning sums $X = X_1 + cdots + X_n$ of independent integer-valued random variables $X_i$ with unbounded, or even infinite, support. We show that the maximum value of the collective support of $X_i$'s necessarily appears in the sample complexity of learning $X$.
  arXiv  Detail & Related papers  (2022-10-24T15:03:55Z)
• TURF: A Two-factor, Universal, Robust, Fast Distribution Learning Algorithm [64.13217062232874]
  One of its most powerful and successful modalities approximates every distribution to an $ell$ distance essentially at most a constant times larger than its closest $t$-piece degree-$d_$. We provide a method that estimates this number near-optimally, hence helps approach the best possible approximation.
  arXiv  Detail & Related papers  (2022-02-15T03:49:28Z)
• Statistically Near-Optimal Hypothesis Selection [33.83129262033921]
  We derive an optimal $2$-approximation learning strategy for the Hypothesis Selection problem. This is the first algorithm that simultaneously achieves the best approximation factor and sample complexity.
  arXiv  Detail & Related papers  (2021-08-17T21:11:20Z)
• On the Parameterized Complexity of Polytree Learning [4.060731229044571]
  A fundamental task in data science is to learn a Bayesian network from observed data. We show that textscPolytree Learning can be solved in $3n cdot |I|mathcalO(1)$ time.
  arXiv  Detail & Related papers  (2021-05-20T11:29:12Z)
• Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity [59.34067736545355]
  Given an MDP with $S$ states, $A$ actions, the discount factor $gamma in (0,1)$, and an approximation threshold $epsilon > 0$, we provide a model-free algorithm to learn an $epsilon$-optimal policy. For small enough $epsilon$, we show an improved algorithm with sample complexity.
  arXiv  Detail & Related papers  (2020-06-06T13:34:41Z)
• Agnostic Q-learning with Function Approximation in Deterministic Systems: Tight Bounds on Approximation Error and Sample Complexity [94.37110094442136]
  We study the problem of agnostic $Q$-learning with function approximation in deterministic systems. We show that if $delta = Oleft(rho/sqrtdim_Eright)$, then one can find the optimal policy using $Oleft(dim_Eright)$.
  arXiv  Detail & Related papers  (2020-02-17T18:41:49Z)

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.