59 citations · 103 across the 22 of their papers we have counts for
10 papers · 1 filter
Online Label Shift: Optimal Dynamic Regret meets Practical Algorithms
Dheeraj Baby, Saurabh Garg, Tzu-Ching Yen +3
This paper focuses on supervised and unsupervised online label shift, where the class marginals varies but the class-conditionals remain invariant. In the unsupervi…
Two-Sample Testing on Ranked Preference Data and the Role of Modeling Assumptions
Charvi Rastogi, Sivaraman Balakrishnan, Nihar B. Shah +1
A number of applications require two-sample testing on ranked preference data. For instance, in crowdsourcing, there is a long-standing question of whether pairwise comparison data…
A Unified Approach to Robust Mean Estimation
Adarsh Prasad, Sivaraman Balakrishnan, Pradeep Ravikumar
In this paper, we develop connections between two seemingly disparate, but central, models in robust statistics: Huber's epsilon-contamination model and the heavy-tailed noise mode…
Regression with Comparisons: Escaping the Curse of Dimensionality with Ordinal Information
Yichong Xu, Sivaraman Balakrishnan, Aarti Singh +1
In supervised learning, we typically leverage a fully labeled dataset to design methods for function estimation or prediction. In many practical situations, we are able to obtain a…
How Many Samples are Needed to Estimate a Convolutional or Recurrent Neural Network?
Simon S. Du, Yining Wang, Xiyu Zhai +3
It is widely believed that the practical success of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) owes to the fact that CNNs and RNNs use a more compact…
Optimization of Smooth Functions with Noisy Observations: Local Minimax Rates
Yining Wang, Sivaraman Balakrishnan, Aarti Singh
We consider the problem of global optimization of an unknown non-convex smooth function with zeroth-order feedback. In this setup, an algorithm is allowed to adaptively query the u…