Search Results for author: Kristjan Greenewald

Found 34 papers, 12 papers with code

Asymmetry in Low-Rank Adapters of Foundation Models

1 code implementation26 Feb 2024 Jiacheng Zhu, Kristjan Greenewald, Kimia Nadjahi, Haitz Sáez de Ocáriz Borde, Rickard Brüel Gabrielsson, Leshem Choshen, Marzyeh Ghassemi, Mikhail Yurochkin, Justin Solomon

Specifically, when updating the parameter matrices of a neural network by adding a product $BA$, we observe that the $B$ and $A$ matrices have distinct functions: $A$ extracts features from the input, while $B$ uses these features to create the desired output.

PresAIse, A Prescriptive AI Solution for Enterprises

no code implementations3 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.

Causal Inference Decision Making

High-Dimensional Smoothed Entropy Estimation via Dimensionality Reduction

no code implementations8 May 2023 Kristjan Greenewald, Brian Kingsbury, Yuancheng Yu

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

Dimensionality Reduction Vocal Bursts Intensity Prediction

Outlier-Robust Group Inference via Gradient Space Clustering

1 code implementation13 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.

Clustering

k-Sliced Mutual Information: A Quantitative Study of Scalability with Dimension

no code implementations17 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.

Log-Euclidean Signatures for Intrinsic Distances Between Unaligned Datasets

1 code implementation3 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.

Learning Proximal Operators to Discover Multiple Optima

1 code implementation28 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.

object-detection Object Detection

$k$-Mixup Regularization for Deep Learning via Optimal Transport

no code implementations29 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.

Adversarial Robustness

k-Mixup Regularization for Deep Learning via Optimal Transport

1 code implementation5 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.

Adversarial Robustness Hyperparameter Optimization

Improving Approximate Optimal Transport Distances using Quantization

no code implementations25 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.

Quantization

Entropic Causal Inference: Identifiability and Finite Sample Results

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.

Causal Identification Causal Inference

$k$-Variance: A Clustered Notion of Variance

no code implementations13 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.

Active Structure Learning of Causal DAGs via Directed Clique Trees

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.

Selection bias

Active Structure Learning of Causal DAGs via Directed Clique Tree

4 code implementations1 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.

Selection bias

The Computational Limits of Deep Learning

1 code implementation10 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.

Game of Go Image Classification +1

Personalized HeartSteps: A Reinforcement Learning Algorithm for Optimizing Physical Activity

no code implementations8 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.

reinforcement-learning Reinforcement Learning (RL)

BreGMN: scaled-Bregman Generative Modeling Networks

no code implementations1 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.

Bayesian Nonparametric Federated Learning of Neural Networks

1 code implementation28 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.

Federated Learning General Classification +1

Probabilistic Federated Neural Matching

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.

Federated Learning General Classification +1

Estimating Information Flow in Deep Neural Networks

no code implementations12 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.

Clustering

Similarity Function Tracking using Pairwise Comparisons

no code implementations7 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.

Clustering Metric Learning +1

Dynamic Metric Learning from Pairwise Comparisons

no code implementations10 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.

Clustering Metric Learning +1

Robust SAR STAP via Kronecker Decomposition

no code implementations5 May 2016 Kristjan Greenewald, Edmund Zelnio, Alfred Hero

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

Nonstationary Distance Metric Learning

no code implementations11 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.

Clustering Metric Learning +1

Kronecker Sum Decompositions of Space-Time Data

no code implementations27 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.