38 citations · 70 across the 19 of their papers we have counts for
20 papers
Sequential One-Sided Hypothesis Testing of Markov Chains
Greg Fields, Tara Javidi, Shubhanshu Shekhar
We study the problem of sequentially testing whether a given stochastic process is generated by a known Markov chain. Formally, given access to a stream of random variables, we wan…
On the near-optimality of betting confidence sets for bounded means
Shubhanshu Shekhar, Aaditya Ramdas
Constructing nonasymptotic confidence intervals (CIs) for the mean of a univariate distribution from independent and identically distributed (i.i.d.) observations is a fundamental…
Deep anytime-valid hypothesis testing
Teodora Pandeva, Patrick Forré, Aaditya Ramdas +1
We propose a general framework for constructing powerful, sequential hypothesis tests for a large class of nonparametric testing problems. The null hypothesis for these problems is…
Reducing sequential change detection to sequential estimation
Shubhanshu Shekhar, Aaditya Ramdas
We consider the problem of sequential change detection, where the goal is to design a scheme for detecting any changes in a parameter or functional of the data stream distribut…
Risk-limiting Financial Audits via Weighted Sampling without Replacement
Shubhanshu Shekhar, Ziyu Xu, Zachary C. Lipton +2
We introduce the notion of a risk-limiting financial auditing (RLFA): given transactions, the goal is to estimate the total misstated monetary fraction~() to a given accur…
Sequential change detection via backward confidence sequences
Shubhanshu Shekhar, Aaditya Ramdas
We present a simple reduction from sequential estimation to sequential changepoint detection (SCD). In short, suppose we are interested in detecting changepoints in some parameter…
A Permutation-Free Kernel Independence Test
Shubhanshu Shekhar, Ilmun Kim, Aaditya Ramdas
In nonparametric independence testing, we observe i.i.d.\ data , where lie in any general spaces, and we wish to test…
A Permutation-free Kernel Two-Sample Test
Shubhanshu Shekhar, Ilmun Kim, Aaditya Ramdas
The kernel Maximum Mean Discrepancy~(MMD) is a popular multivariate distance metric between distributions that has found utility in two-sample testing. The usual kernel-MMD test st…
Instance-Dependent Regret Analysis of Kernelized Bandits
Shubhanshu Shekhar, Tara Javidi
We study the kernelized bandit problem, that involves designing an adaptive strategy for querying a noisy zeroth-order-oracle to efficiently learn about the optimizer of an unknown…
Nonparametric Two-Sample Testing by Betting
Shubhanshu Shekhar, Aaditya Ramdas
We study the problem of designing consistent sequential two-sample tests in a nonparametric setting. Guided by the principle of testing by betting, we reframe this task into that o…
Uncertainty-aware Safe Exploratory Planning using Gaussian Process and Neural Control Contraction Metric
Dawei Sun, Mohammad Javad Khojasteh, Shubhanshu Shekhar +1
In this paper, we consider the problem of using a robot to explore an environment with an unknown, state-dependent disturbance function while avoiding some forbidden areas. The goa…
Adaptive Sampling for Minimax Fair Classification
Shubhanshu Shekhar, Greg Fields, Mohammad Ghavamzadeh +1
Machine learning models trained on uncurated datasets can often end up adversely affecting inputs belonging to underrepresented groups. To address this issue, we consider the probl…
Multi-Scale Zero-Order Optimization of Smooth Functions in an RKHS
Shubhanshu Shekhar, Tara Javidi
We aim to optimize a black-box function under the assumption that is Hölder smooth and has bounded norm in the RKHS associated with a given k…
Active Model Estimation in Markov Decision Processes
Jean Tarbouriech, Shubhanshu Shekhar, Matteo Pirotta +2
We study the problem of efficient exploration in order to learn an accurate model of an environment, modeled as a Markov decision process (MDP). Efficient exploration in this probl…
Adaptive Sampling for Estimating Multiple Probability Distributions
Shubhanshu Shekhar, Tara Javidi, Mohammad Ghavamzadeh
We consider the problem of allocating samples to a finite set of discrete distributions in order to learn them uniformly well in terms of four common distance measures: ,…
Active Learning for Binary Classification with Abstention
Shubhanshu Shekhar, Mohammad Ghavamzadeh, Tara Javidi
We construct and analyze active learning algorithms for the problem of binary classification with abstention. We consider three abstention settings: \emph{fixed-cost} and two varia…
Binary Classification with Bounded Abstention Rate
Shubhanshu Shekhar, Mohammad Ghavamzadeh, Tara Javidi
We consider the problem of binary classification with abstention in the relatively less studied \emph{bounded-rate} setting. We begin by obtaining a characterization of the Bayes o…
Multiscale Gaussian Process Level Set Estimation
Shubhanshu Shekhar, Tara Javidi
In this paper, the problem of estimating the level set of a black-box function from noisy and expensive evaluation queries is considered. A new algorithm for this problem in the Ba…
Gaussian Process bandits with adaptive discretization
Shubhanshu Shekhar, Tara Javidi
In this paper, the problem of maximizing a black-box function is studied in the Bayesian framework with a Gaussian Process (GP) prior. In particular,…
Species tree estimation using ASTRAL: how many genes are enough?
Shubhanshu Shekhar, Sebastien Roch, Siavash Mirarab
Species tree reconstruction from genomic data is increasingly performed using methods that account for sources of gene tree discordance such as incomplete lineage sorting. One popu…