10 papers · 1 filter
Efficient Robust Learning at the Information-Theoretic Limit
Adam R. Klivans, Konstantinos Stavropoulos, Sergei Tikhonov +1
In an important recent work, Blanc (2026) gave an algorithm for robustly learning Boolean concept classes with respect to a fixed distribution that outputs a (randomized) classifie…
Iterative Chow Filtering for Learning with Distribution Shift
Gautam Chandrasekaran, Georgios Gkrinias, Adam R. Klivans +2
Recent work due to Goel et al. gave the first efficient algorithms for learning with distribution shift in the challenging PQ framework. In this setting, a learner receives labeled…
Equivalence of Coarse and Fine-Grained Models for Learning with Distribution Shift
Adam R. Klivans, Shyamal Patel, Konstantinos Stavropoulos +1
Recent work on provably efficient algorithms for learning with distribution shift has focused on two models: PQ learning (Goldwasser et al. (2020)) and TDS learning (Klivans et al.…
A Fully Polynomial-Time Algorithm for Robustly Learning Halfspaces over the Hypercube
Gautam Chandrasekaran, Adam R. Klivans, Konstantinos Stavropoulos +1
We give the first fully polynomial-time algorithm for learning halfspaces with respect to the uniform distribution on the hypercube in the presence of contamination, where an adver…
Learning Neural Networks with Distribution Shift: Efficiently Certifiable Guarantees
Gautam Chandrasekaran, Adam R. Klivans, Lin Lin Lee +1
We give the first provably efficient algorithms for learning neural networks with distribution shift. We work in the Testable Learning with Distribution Shift framework (TDS learni…
Learning Constant-Depth Circuits in Malicious Noise Models
Adam R. Klivans, Konstantinos Stavropoulos, Arsen Vasilyan
The seminal work of Linial, Mansour, and Nisan gave a quasipolynomial-time algorithm for learning constant-depth circuits () with respect to the uniform distribution…
Efficient Discrepancy Testing for Learning with Distribution Shift
Gautam Chandrasekaran, Adam R. Klivans, Vasilis Kontonis +2
A fundamental notion of distance between train and test distributions from the field of domain adaptation is discrepancy distance. While in general hard to compute, here we provide…
Tolerant Algorithms for Learning with Arbitrary Covariate Shift
Surbhi Goel, Abhishek Shetty, Konstantinos Stavropoulos +1
We study the problem of learning under arbitrary distribution shift, where the learner is trained on a labeled set from one distribution but evaluated on a different, potentially a…
Learning Intersections of Halfspaces with Distribution Shift: Improved Algorithms and SQ Lower Bounds
Adam R. Klivans, Konstantinos Stavropoulos, Arsen Vasilyan
Recent work of Klivans, Stavropoulos, and Vasilyan initiated the study of testable learning with distribution shift (TDS learning), where a learner is given labeled samples from tr…
Testable Learning with Distribution Shift
Adam R. Klivans, Konstantinos Stavropoulos, Arsen Vasilyan
We revisit the fundamental problem of learning with distribution shift, in which a learner is given labeled samples from training distribution , unlabeled samples from test dist…