6 papers
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…
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…
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…
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…
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…
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…