arXiv Machine Learning
Oct 19
Nearly Linear Private Learning of Littlestone Classes
arXiv:2610. 23160v1 Announce Type: new Abstract: Differentially private learning aims to learn from data while protecting individual training examples.
New Lower Bounds for Private PAC Learning
The paper investigates realizable PAC learning under approximate differential privacy and develops a framework for establishing lower bounds on sample complexity. It demonstrates that classes sharing the same VC and Littlestone dimensions can have different private sample complexities, introducing the Independent Class Packing (ICP) parameter to capture this distinction. Using ICP, the authors derive tight lower bounds for several hypothesis classes, including axis-aligned rectangles, unions of intervals, linear subspaces, and improved bounds for halfspaces and convex polygons, and show that ICP characterizes private PAC sample complexity for product classes up to logarithmic factors.
Related stories
arXiv Machine Learning
Sep 22
Adversarially Robust PAC Learning with Optimal VC Rates
arXiv:2609.24260v1 Announce Type: cross Abstract: We study the problem of \emph{adversarially robust} PAC learning. In this framework, the learner observes independent samples from an unknown distrib...
Hugging Face Trending Papers
Sep 21
Adversarially Robust PAC Learning with Optimal VC Rates
We study the problem of \emph{adversarially robust} PAC learning. In this framework, the learner observes independent samples from an unknown distribution over $\mathcal{X} \times \{0,1\}$, as in clas...
arXiv Machine Learning
Oct 27
Near-Optimal List Replicability from Littlestone Dimension
arXiv:2610.32853v1 Announce Type: new Abstract: We study the list replicability number in the realizable PAC learning framework and prove that every concept class $H$ over a countable domain with Lit...
arXiv Machine Learning
Sep 25
Bandit Multiclass PAC Learning: Corrected Lower Bounds, Exact Families, and a Confidence Direct-Sum Phenomenon
The paper revisits realizable multiclass PAC learning with bandit feedback, correcting a previously claimed lower bound on sample complexity. It introduces a new anchored dimension, “aBDS,” and establishes a constant‑free three‑part lower bound, while also providing tighter upper bounds that eliminate dependence on the total label count. The authors demonstrate that the optimal sample complexity can vary dramatically even among classes with identical dimensional profiles, revealing a confidence direct‑sum phenomenon and a rank‑saturation phase transition.
arXiv AI
Aug 7
An Optimal Agnostic PAC Algorithm
arXiv:2608. 06363v1 Announce Type: cross Abstract: Let $H\subseteq\{-1,+1\}^X$ be a class of finite VC dimension $d\ge1$.
arXiv Machine Learning
Aug 27
Two Dimensions Govern Agnostic Multiclass Transductive Learning
arXiv:2608. 25326v1 Announce Type: new Abstract: In transductive classification, an adversary fixes a labeled population, one label is hidden uniformly, and the learner sees all remaining labels.
arXiv Machine Learning
Jul 10
On the Gradient Complexity of Private Optimization with Private Oracles
arXiv:2511. 13999v2 Announce Type: replace Abstract: We study the running time, in terms of first order oracle queries, of differentially private empirical/population risk minimization of Lipschitz convex losses.
arXiv Machine Learning
Oct 21
Quadratic Sample Complexity for Strictly Replicable Realizable Learning with Unknown Marginals
arXiv:2610. 26944v1 Announce Type: cross Abstract: Under the quantifier $\exists A\,\forall D$, where the realizable distribution and its marginal are unknown, we determine the finite-class sample-complexity exponent for strict replicability: two independent samples and one shared seed must produce identical functions.
arXiv Statistics ML
Oct 26
Strictly Replicable Realizable Learning: Unknown Marginals, Finite-Class Interpolation, and the Cost of Shared Randomness
arXiv:2610. 26944v2 Announce Type: replace Abstract: Strict replicability requires two independent training samples, processed with the same random seed, to produce exactly the same hypothesis.
arXiv Machine Learning
Aug 12
Optimistic Rates for Multiclass PAC Learning
arXiv:2608. 10869v1 Announce Type: new Abstract: Worst-case multiclass bounds do not become smaller when the best classifier is already nearly correct: what is missing is an optimistic rate, a guarantee whose fluctuation scales with the oracle risk itself.
arXiv Machine Learning
Jul 9
The Optimal Sample Complexity of Learning Autoregressive Chain-of-Thought
arXiv:2607. 07423v1 Announce Type: new Abstract: We prove that, in the realizable PAC setting, the sample complexity of exact-trace learning for full autoregressive Chain-of-Thought traces is upper bounded by the standard multiclass rate of the local next-token class, where this rate is governed by the Daniely--Shalev-Shwartz dimension.