You need to log in to edit.

You can create a new account if you don't have one.

Or, discuss a change on Slack.

You can create a new account if you don't have one.

Or, discuss a change on Slack.

no code implementations • 3 Feb 2024 • Wei Sun, Scott McFaddin, Linh Ha Tran, Shivaram Subramanian, Kristjan Greenewald, Yeshi Tenzin, Zack Xue, Youssef Drissi, Markus Ettl

The first challenge is caused by the limitations of observational data for accurate causal inference which is typically a prerequisite for good decision-making.

no code implementations • 11 Oct 2023 • Apoorva Nitsure, Youssef Mroueh, Mattia Rigotti, Kristjan Greenewald, Brian Belgodere, Mikhail Yurochkin, Jiri Navratil, Igor Melnyk, Jerret Ross

Using this framework, we formally develop a risk-aware approach for foundation model selection given guardrails quantified by specified metrics.

1 code implementation • NeurIPS 2023 • JiaQi Zhang, Chandler Squires, Kristjan Greenewald, Akash Srivastava, Karthikeyan Shanmugam, Caroline Uhler

Causal disentanglement aims to uncover a representation of data using latent variables that are interrelated through a causal model.

no code implementations • 8 May 2023 • Kristjan Greenewald, Brian Kingsbury, Yuancheng Yu

We study the problem of overcoming exponential sample complexity in differential entropy estimation under Gaussian convolutions.

1 code implementation • 13 Oct 2022 • Yuchen Zeng, Kristjan Greenewald, Kangwook Lee, Justin Solomon, Mikhail Yurochkin

Traditional machine learning models focus on achieving good performance on the overall training distribution, but they often underperform on minority groups.

no code implementations • 17 Jun 2022 • Ziv Goldfeld, Kristjan Greenewald, Theshani Nuradha, Galen Reeves

However, a quantitative characterization of how SMI itself and estimation rates thereof depend on the ambient dimension, which is crucial to the understanding of scalability, remain obscure.

1 code implementation • 3 Feb 2022 • Tal Shnitzer, Mikhail Yurochkin, Kristjan Greenewald, Justin Solomon

We use manifold learning to compare the intrinsic geometric structures of different datasets by comparing their diffusion operators, symmetric positive-definite (SPD) matrices that relate to approximations of the continuous Laplace-Beltrami operator from discrete samples.

1 code implementation • 28 Jan 2022 • Lingxiao Li, Noam Aigerman, Vladimir G. Kim, Jiajin Li, Kristjan Greenewald, Mikhail Yurochkin, Justin Solomon

We present an end-to-end method to learn the proximal operator of a family of training problems so that multiple local minima can be quickly obtained from initial guesses by iterating the learned operator, emulating the proximal-point algorithm that has fast convergence.

no code implementations • 29 Sep 2021 • Kristjan Greenewald, Anming Gu, Mikhail Yurochkin, Justin Solomon, Edward Chien

To better leverage the structure of the data, we extend mixup to $k$-mixup by perturbing $k$-batches of training points in the direction of other $k$-batches using displacement interpolation, i. e. interpolation under the Wasserstein metric.

1 code implementation • NeurIPS 2021 • Ching-Yao Chuang, Youssef Mroueh, Kristjan Greenewald, Antonio Torralba, Stefanie Jegelka

Understanding the generalization of deep neural networks is one of the most important tasks in deep learning.

1 code implementation • 5 Jun 2021 • Kristjan Greenewald, Anming Gu, Mikhail Yurochkin, Justin Solomon, Edward Chien

Our empirical results show that training with $k$-mixup further improves generalization and robustness across several network architectures and benchmark datasets of differing modalities.

no code implementations • 25 Feb 2021 • Gaspard Beugnot, Aude Genevay, Kristjan Greenewald, Justin Solomon

Optimal transport (OT) is a popular tool in machine learning to compare probability measures geometrically, but it comes with substantial computational burden.

no code implementations • NeurIPS 2020 • Spencer Compton, Murat Kocaoglu, Kristjan Greenewald, Dmitriy Katz

This unobserved randomness is measured by the entropy of the exogenous variable in the underlying structural causal model, which governs the causal relation between the observed variables.

no code implementations • 13 Dec 2020 • Justin Solomon, Kristjan Greenewald, Haikady N. Nagaraja

We introduce $k$-variance, a generalization of variance built on the machinery of random bipartite matchings.

1 code implementation • NeurIPS 2020 • Chandler Squires, Sara Magliacane, Kristjan Greenewald, Dmitriy Katz, Murat Kocaoglu, Karthikeyan Shanmugam

Most existing works focus on \textit{worst-case} or \textit{average-case} lower bounds for the number of interventions required to orient a DAG.

no code implementations • 3 Nov 2020 • Kristjan Greenewald, Dmitriy Katz-Rogozhnikov, Karthik Shanmugam

The estimation of causal treatment effects from observational data is a fundamental problem in causal inference.

4 code implementations • 1 Nov 2020 • Chandler Squires, Sara Magliacane, Kristjan Greenewald, Dmitriy Katz, Murat Kocaoglu, Karthikeyan Shanmugam

Most existing works focus on worst-case or average-case lower bounds for the number of interventions required to orient a DAG.

1 code implementation • 10 Jul 2020 • Neil C. Thompson, Kristjan Greenewald, Keeheon Lee, Gabriel F. Manso

Deep learning's recent history has been one of achievement: from triumphing over humans in the game of Go to world-leading performance in image classification, voice recognition, translation, and other tasks.

no code implementations • NeurIPS 2019 • Kristjan Greenewald, Dmitriy Katz, Karthikeyan Shanmugam, Sara Magliacane, Murat Kocaoglu, Enric Boix Adsera, Guy Bresler

We consider the problem of experimental design for learning causal graphs that have a tree structure.

1 code implementation • NeurIPS 2019 • Mikhail Yurochkin, Mayank Agarwal, Soumya Ghosh, Kristjan Greenewald, Trong Nghia Hoang

We consider the problem of aggregating models learned from sequestered, possibly heterogeneous datasets.

no code implementations • 8 Sep 2019 • Peng Liao, Kristjan Greenewald, Predrag Klasnja, Susan Murphy

In this paper, we develop a Reinforcement Learning (RL) algorithm that continuously learns and improves the treatment policy embedded in the JITAI as the data is being collected from the user.

no code implementations • 1 Jun 2019 • Akash Srivastava, Kristjan Greenewald, Farzaneh Mirzazadeh

Well-definedness of f-divergences, however, requires the distributions of the data and model to overlap completely in every time step of training.

1 code implementation • 28 May 2019 • Mikhail Yurochkin, Mayank Agarwal, Soumya Ghosh, Kristjan Greenewald, Trong Nghia Hoang, Yasaman Khazaeni

In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited.

no code implementations • ICLR 2019 • Ziv Goldfeld, Ewout van den Berg, Kristjan Greenewald, Brian Kingsbury, Igor Melnyk, Nam Nguyen, Yury Polyanskiy

We then develop a rigorous estimator for I(X;T) in noisy DNNs and observe compression in various models.

no code implementations • ICLR 2019 • Mikhail Yurochkin, Mayank Agarwal, Soumya Ghosh, Kristjan Greenewald, Nghia Hoang, Yasaman Khazaeni

In federated learning problems, data is scattered across different servers and exchanging or pooling it is often impractical or prohibited.

no code implementations • 12 Oct 2018 • Ziv Goldfeld, Ewout van den Berg, Kristjan Greenewald, Igor Melnyk, Nam Nguyen, Brian Kingsbury, Yury Polyanskiy

We then develop a rigorous estimator for $I(X;T)$ in noisy DNNs and observe compression in various models.

no code implementations • 7 Jan 2017 • Kristjan Greenewald, Stephen Kelley, Brandon Oselio, Alfred O. Hero III

We propose Online Convex Ensemble StrongLy Adaptive Dynamic Learning (OCELAD), a general adaptive, online approach for learning and tracking optimal metrics as they change over time that is highly robust to a variety of nonstationary behaviors in the changing metric.

no code implementations • 10 Oct 2016 • Kristjan Greenewald, Stephen Kelley, Alfred Hero III

Recent work in distance metric learning has focused on learning transformations of data that best align with specified pairwise similarity and dissimilarity constraints, often supplied by a human observer.

no code implementations • 5 May 2016 • Kristjan Greenewald, Edmund Zelnio, Alfred Hero

This paper proposes a spatio-temporal decomposition for the detection of moving targets in multiantenna SAR.

no code implementations • 11 Mar 2016 • Kristjan Greenewald, Stephen Kelley, Alfred Hero

Recent work in distance metric learning has focused on learning transformations of data that best align with provided sets of pairwise similarity and dissimilarity constraints.

no code implementations • 14 Jan 2014 • Kristjan Greenewald, Alfred Hero

Our approach is to estimate the covariance using parameter reduction and sparse models.

no code implementations • 27 Jul 2013 • Kristjan Greenewald, Theodoros Tsiligkaridis, Alfred O. Hero III

To allow a smooth tradeoff between the reduction in the number of parameters (to reduce estimation variance) and the accuracy of the covariance approximation (affecting estimation bias), we introduce a diagonally loaded modification of the sum of kronecker products representation [1].

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

Contact us on:
hello@paperswithcode.com
.
Papers With Code is a free resource with all data licensed under CC-BY-SA.