Search Results for author: Raaz Dwivedi

Found 21 papers, 12 papers with code

Debiased Distribution Compression

1 code implementation18 Apr 2024 Lingxiao Li, Raaz Dwivedi, Lester Mackey

Modern compression methods can summarize a target distribution $\mathbb{P}$ more succinctly than i. i. d.

FairPair: A Robust Evaluation of Biases in Language Models through Paired Perturbations

no code implementations9 Apr 2024 Jane Dwivedi-Yu, Raaz Dwivedi, Timo Schick

We present an evaluation of several commonly used generative models and a qualitative analysis that indicates a preference for discussing family and hobbies with regard to women.

counterfactual

Doubly Robust Inference in Causal Latent Factor Models

no code implementations18 Feb 2024 Alberto Abadie, Anish Agarwal, Raaz Dwivedi, Abhin Shah

This article introduces a new estimator of average treatment effects under unobserved confounding in modern data-rich environments featuring large numbers of units and outcomes.

Imputation Matrix Completion

Did we personalize? Assessing personalization by an online reinforcement learning algorithm using resampling

1 code implementation11 Apr 2023 Susobhan Ghosh, Raphael Kim, Prasidh Chhabria, Raaz Dwivedi, Predrag Klasnja, Peng Liao, Kelly Zhang, Susan Murphy

We use a working definition of personalization and introduce a resampling-based methodology for investigating whether the personalization exhibited by the RL algorithm is an artifact of the RL algorithm stochasticity.

Decision Making Reinforcement Learning (RL)

Compress Then Test: Powerful Kernel Testing in Near-linear Time

1 code implementation14 Jan 2023 Carles Domingo-Enrich, Raaz Dwivedi, Lester Mackey

To address these shortcomings, we introduce Compress Then Test (CTT), a new framework for high-powered kernel testing based on sample compression.

Two-sample testing

Doubly robust nearest neighbors in factor models

no code implementations25 Nov 2022 Raaz Dwivedi, Katherine Tian, Sabina Tomkins, Predrag Klasnja, Susan Murphy, Devavrat Shah

We consider a matrix completion problem with missing data, where the $(i, t)$-th entry, when observed, is given by its mean $f(u_i, v_t)$ plus mean-zero noise for an unknown function $f$ and latent factors $u_i$ and $v_t$.

counterfactual Counterfactual Inference +1

On counterfactual inference with unobserved confounding

no code implementations14 Nov 2022 Abhin Shah, Raaz Dwivedi, Devavrat Shah, Gregory W. Wornell

Given an observational study with $n$ independent but heterogeneous units, our goal is to learn the counterfactual distribution for each unit using only one $p$-dimensional sample per unit containing covariates, interventions, and outcomes.

counterfactual Counterfactual Inference +1

Counterfactual inference for sequential experiments

no code implementations14 Feb 2022 Raaz Dwivedi, Katherine Tian, Sabina Tomkins, Predrag Klasnja, Susan Murphy, Devavrat Shah

Our goal is to provide inference guarantees for the counterfactual mean at the smallest possible scale -- mean outcome under different treatments for each unit and each time -- with minimal assumptions on the adaptive treatment policy.

counterfactual Counterfactual Inference +3

Distribution Compression in Near-linear Time

1 code implementation ICLR 2022 Abhishek Shetty, Raaz Dwivedi, Lester Mackey

Near-optimal thinning procedures achieve this goal by sampling $n$ points from a Markov chain and identifying $\sqrt{n}$ points with $\widetilde{\mathcal{O}}(1/\sqrt{n})$ discrepancy to $\mathbb{P}$.

Generalized Kernel Thinning

2 code implementations ICLR 2022 Raaz Dwivedi, Lester Mackey

Fourth, we establish that KT applied to a sum of the target and power kernels (a procedure we call KT+) simultaneously inherits the improved MMD guarantees of power KT and the tighter individual function guarantees of target KT.

Kernel Thinning

1 code implementation12 May 2021 Raaz Dwivedi, Lester Mackey

The maximum discrepancy in integration error is $\mathcal{O}_d(n^{-1/2}\sqrt{\log n})$ in probability for compactly supported $\mathbb{P}$ and $\mathcal{O}_d(n^{-\frac{1}{2}} (\log n)^{(d+1)/2}\sqrt{\log\log n})$ for sub-exponential $\mathbb{P}$ on $\mathbb{R}^d$.

Stable discovery of interpretable subgroups via calibration in causal studies

1 code implementation23 Aug 2020 Raaz Dwivedi, Yan Shuo Tan, Briton Park, Mian Wei, Kevin Horgan, David Madigan, Bin Yu

Building on Yu and Kumbier's PCS framework and for randomized experiments, we introduce a novel methodology for Stable Discovery of Interpretable Subgroups via Calibration (StaDISC), with large heterogeneous treatment effects.

Revisiting minimum description length complexity in overparameterized models

1 code implementation17 Jun 2020 Raaz Dwivedi, Chandan Singh, Bin Yu, Martin J. Wainwright

We provide an extensive theoretical characterization of MDL-COMP for linear models and kernel methods and show that it is not just a function of parameter count, but rather a function of the singular values of the design or the kernel matrix and the signal-to-noise ratio.

Learning Theory

Instability, Computational Efficiency and Statistical Accuracy

no code implementations22 May 2020 Nhat Ho, Koulik Khamaru, Raaz Dwivedi, Martin J. Wainwright, Michael. I. Jordan, Bin Yu

Many statistical estimators are defined as the fixed point of a data-dependent operator, with estimators based on minimizing a cost function being an important special case.

Computational Efficiency

Curating a COVID-19 data repository and forecasting county-level death counts in the United States

1 code implementation16 May 2020 Nick Altieri, Rebecca L. Barter, James Duncan, Raaz Dwivedi, Karl Kumbier, Xiao Li, Robert Netzorg, Briton Park, Chandan Singh, Yan Shuo Tan, Tiffany Tang, Yu Wang, Chao Zhang, Bin Yu

We use this data to develop predictions and corresponding prediction intervals for the short-term trajectory of COVID-19 cumulative death counts at the county-level in the United States up to two weeks ahead.

COVID-19 Tracking Decision Making +2

Fast mixing of Metropolized Hamiltonian Monte Carlo: Benefits of multi-step gradients

1 code implementation29 May 2019 Yuansi Chen, Raaz Dwivedi, Martin J. Wainwright, Bin Yu

This bound gives a precise quantification of the faster convergence of Metropolized HMC relative to simpler MCMC algorithms such as the Metropolized random walk, or Metropolized Langevin algorithm.

Sharp Analysis of Expectation-Maximization for Weakly Identifiable Models

no code implementations1 Feb 2019 Raaz Dwivedi, Nhat Ho, Koulik Khamaru, Martin J. Wainwright, Michael. I. Jordan, Bin Yu

We study a class of weakly identifiable location-scale mixture models for which the maximum likelihood estimates based on $n$ i. i. d.

Theoretical guarantees for EM under misspecified Gaussian mixture models

no code implementations NeurIPS 2018 Raaz Dwivedi, Nhật Hồ, Koulik Khamaru, Martin J. Wainwright, Michael. I. Jordan

We provide two classes of theoretical guarantees: first, we characterize the bias introduced due to the misspecification; and second, we prove that population EM converges at a geometric rate to the model projection under a suitable initialization condition.

Singularity, Misspecification, and the Convergence Rate of EM

no code implementations1 Oct 2018 Raaz Dwivedi, Nhat Ho, Koulik Khamaru, Michael. I. Jordan, Martin J. Wainwright, Bin Yu

A line of recent work has analyzed the behavior of the Expectation-Maximization (EM) algorithm in the well-specified setting, in which the population likelihood is locally strongly concave around its maximizing argument.

Log-concave sampling: Metropolis-Hastings algorithms are fast

1 code implementation8 Jan 2018 Raaz Dwivedi, Yuansi Chen, Martin J. Wainwright, Bin Yu

Relative to known guarantees for the unadjusted Langevin algorithm (ULA), our bounds show that the use of an accept-reject step in MALA leads to an exponentially improved dependence on the error-tolerance.

Fast MCMC sampling algorithms on polytopes

2 code implementations23 Oct 2017 Yuansi Chen, Raaz Dwivedi, Martin J. Wainwright, Bin Yu

We propose and analyze two new MCMC sampling algorithms, the Vaidya walk and the John walk, for generating samples from the uniform distribution over a polytope.

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