Search Results for author: Ian Waudby-Smith

Found 5 papers, 4 papers with code

Anytime-valid off-policy inference for contextual bandits

1 code implementation19 Oct 2022 Ian Waudby-Smith, Lili Wu, Aaditya Ramdas, Nikos Karampatziakis, Paul Mineiro

Importantly, our methods can be employed while the original experiment is still running (that is, not necessarily post-hoc), when the logging policy may be itself changing (due to learning), and even if the context distributions are a highly dependent time-series (such as if they are drifting over time).

Multi-Armed Bandits Off-policy evaluation +1

A nonparametric extension of randomized response for private confidence sets

no code implementations17 Feb 2022 Ian Waudby-Smith, Zhiwei Steven Wu, Aaditya Ramdas

This work derives methods for performing nonparametric, nonasymptotic statistical inference for population means under the constraint of local differential privacy (LDP).

Time-uniform central limit theory, asymptotic confidence sequences, and anytime-valid causal inference

2 code implementations11 Mar 2021 Ian Waudby-Smith, David Arbour, Ritwik Sinha, Edward H. Kennedy, Aaditya Ramdas

While the CLT approximates the distribution of a sample average by that of a Gaussian at a fixed sample size, we use strong invariance principles (stemming from the seminal 1970s work of Komlos, Major, and Tusnady) to uniformly approximate the entire sample average process by an implicit Gaussian process.

Causal Inference

Estimating means of bounded random variables by betting

3 code implementations19 Oct 2020 Ian Waudby-Smith, Aaditya Ramdas

This paper derives confidence intervals (CI) and time-uniform confidence sequences (CS) for the classical problem of estimating an unknown mean from bounded observations.

Confidence sequences for sampling without replacement

3 code implementations NeurIPS 2020 Ian Waudby-Smith, Aaditya Ramdas

We then present Hoeffding- and empirical-Bernstein-type time-uniform CSs and fixed-time confidence intervals for sampling WoR, which improve on previous bounds in the literature and explicitly quantify the benefit of WoR sampling.

Cannot find the paper you are looking for? You can Submit a new open access paper.