arXiv Machine Learning
Aug 7
Optimal Rates for Learning with Monotone Adversaries
arXiv:2608. 06337v1 Announce Type: cross Abstract: A monotone adversary observes an i.
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.
Related stories
arXiv Machine Learning
Jun 16
Online Realizable Regression and Applications for ReLU Networks
arXiv:2602. 19172v2 Announce Type: replace Abstract: Realizable online regression can behave very differently from online classification.
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
2d ago
When Does More Correct Data Hurt? Insertion-Stability and the Limits of Dimension-Based Theory
arXiv:2608. 14020v1 Announce Type: new Abstract: Adding data known to be correct ought to be safe.
arXiv Machine Learning
Jun 17
On Randomized Algorithms in Online Strategic Classification
arXiv:2602. 06257v2 Announce Type: replace Abstract: Online strategic classification studies settings in which agents strategically modify their features to obtain favorable predictions.
arXiv Machine Learning
Jun 30
Sample Complexity of Scientific Discovery: PAC Learnability of Compositional Function Trees
arXiv:2606. 29331v1 Announce Type: new Abstract: Scientific discovery via symbolic regression is often viewed as statistically and computationally intractable because the hypothesis space of expressions grows combinatorially with depth.
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.
arXiv Machine Learning
Aug 11
Support Selection Beyond Smooth DAG Exactness: Completion Geometry,Score Margins, and Selective Certificates
arXiv:2608. 08103v1 Announce Type: new Abstract: Smooth acyclicity constraints answer whether a weighted support is a DAG, whereas structure learning asks which support change should be made.
arXiv Machine Learning
Aug 3
Fast Rates for Swap-Agnostic Learning of Proper Losses
arXiv:2607. 28856v1 Announce Type: new Abstract: Swap-agnostic learning strengthens classical agnostic learning by allowing the comparator to select a different hypothesis on each level set of the learner's predictions.
arXiv Machine Learning
Aug 6
The Sample Complexity of Distributionally Robust PAC Learning under Cressie--Read Divergences
arXiv:2608. 04686v1 Announce Type: new Abstract: We study distributionally robust PAC learning for the $0$--$1$-loss, where adversarial perturbations of the data distribution are constrained by a Cressie--Read divergence of order $k>1$ and radius $\rho\geq 0$.
Hugging Face Trending Papers
Aug 5
The Sample Complexity of Distributionally Robust PAC Learning under Cressie--Read Divergences
We study distributionally robust PAC learning for the $0$--$1$-loss, where adversarial perturbations of the data distribution are constrained by a Cressie--Read divergence of order $k>1$ and radius $ρ\geq 0$. For hypothesis classes with VC dimension $d$, we establish realizable and agnostic sample-complexity bounds tight up to constant and logarithmic factors, respectively; ordinary empirical risk minimization attains both rates up to logarithmic factors.
arXiv Machine Learning
Aug 10
Dirichlet Follow-the-Leader Closes the Gap in Simultaneous Multiclass U-Calibration
arXiv:2608. 06656v1 Announce Type: new Abstract: Can one forecaster attain the optimal regret rate for every bounded proper loss and also adapt to every smooth proper loss?