collaborators

6 papers

cs.LG2026

Less Data, Faster Training: repeating smaller datasets speeds up learning via sampling biases

Jingwen Liu, Ezra Edelman, Surbhi Goel +1

This work investigates the ``small-vs-large gap'', where repeating on fewer samples can lead to compute saving during training compared to using a larger dataset. This is observed…

cs.LG2026

Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift

Surbhi Goel, Jonathan Pei, James Wang

Behavior cloning provides strong imitation learning guarantees when training and test environments share the same dynamics. However, in many deployment settings the test environmen…

cs.LG2026

Testing Noise Assumptions of Learning Algorithms

Surbhi Goel, Adam R. Klivans, Konstantinos Stavropoulos +1

We pose a fundamental question in computational learning theory: can we efficiently test whether a training set satisfies the assumptions of a given noise model? This question has…

cs.LG2026

Weight Clipping for Robust Conformal Inference under Unbounded Covariate Shifts

James Wang, Surbhi Goel

Conformal prediction (CP) provides powerful, distribution-free prediction sets, but its guarantees rely on the exchangeability of training and test data, which is often violated in…

cs.LG2026

Reliable Abstention under Adversarial Injections: Tight Lower Bounds and New Upper Bounds

Ezra Edelman, Surbhi Goel

We study online learning in the adversarial injection model introduced by [Goel et al. 2017], where a stream of labeled examples is predominantly drawn i.i.d.\ from an unknown dist…

cs.DS2024

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…