Search Results for author: Garvesh Raskutti

Found 26 papers, 2 papers with code

Fast, Distribution-free Predictive Inference for Neural Networks with Coverage Guarantees

1 code implementation11 Jun 2023 Yue Gao, Garvesh Raskutti, Rebecca Willet

This paper introduces a novel, computationally-efficient algorithm for predictive inference (PI) that requires no distributional assumptions on the data and can be computed faster than existing bootstrap-type methods for neural networks.

Lazy Estimation of Variable Importance for Large Neural Networks

1 code implementation19 Jul 2022 Yue Gao, Abby Stevens, Rebecca Willet, Garvesh Raskutti

Recently, there has been a proliferation of model-agnostic methods to measure variable importance (VI) that analyze the difference in predictive power between a full model trained on all variables and a reduced model that excludes the variable(s) of interest.

Gaussian Process Inference Using Mini-batch Stochastic Gradient Descent: Convergence Guarantees and Empirical Benefits

no code implementations19 Nov 2021 Hao Chen, Lili Zheng, Raed Al Kontar, Garvesh Raskutti

Stochastic gradient descent (SGD) and its variants have established themselves as the go-to algorithms for large-scale machine learning problems with independent samples due to their generalization performance and intrinsic computational advantage.

Prediction in the presence of response-dependent missing labels

no code implementations25 Mar 2021 Hyebin Song, Garvesh Raskutti, Rebecca Willett

In a variety of settings, limitations of sensing technologies or other sampling mechanisms result in missing labels, where the likelihood of a missing label in the training set is an unknown function of the data.

Stochastic Gradient Descent in Correlated Settings: A Study on Gaussian Processes

no code implementations NeurIPS 2020 Hao Chen, Lili Zheng, Raed Al Kontar, Garvesh Raskutti

Stochastic gradient descent (SGD) and its variants have established themselves as the go-to algorithms for large-scale machine learning problems with independent samples due to their generalization performance and intrinsic computational advantage.

Gaussian Processes

A Sharp Blockwise Tensor Perturbation Bound for Orthogonal Iteration

no code implementations6 Aug 2020 Yuetian Luo, Garvesh Raskutti, Ming Yuan, Anru R. Zhang

Rate matching deterministic lower bound for tensor reconstruction, which demonstrates the optimality of HOOI, is also provided.

Clustering Denoising

Context-dependent self-exciting point processes: models, methods, and risk bounds in high dimensions

no code implementations16 Mar 2020 Lili Zheng, Garvesh Raskutti, Rebecca Willett, Benjamin Mark

High-dimensional autoregressive point processes model how current events trigger or inhibit future events, such as activity by one member of a social network can affect the future activity of his or her neighbors.

Point Processes Time Series +1

ISLET: Fast and Optimal Low-rank Tensor Regression via Importance Sketching

no code implementations9 Nov 2019 Anru Zhang, Yuetian Luo, Garvesh Raskutti, Ming Yuan

In this paper, we develop a novel procedure for low-rank tensor regression, namely \emph{\underline{I}mportance \underline{S}ketching \underline{L}ow-rank \underline{E}stimation for \underline{T}ensors} (ISLET).

Distributed Computing regression

Minimizing Negative Transfer of Knowledge in Multivariate Gaussian Processes: A Scalable and Regularized Approach

no code implementations31 Jan 2019 Raed Kontar, Garvesh Raskutti, Shiyu Zhou

The proposed method has excellent scalability when the number of outputs is large and minimizes the negative transfer of knowledge between uncorrelated outputs.

Gaussian Processes

Estimating Network Structure from Incomplete Event Data

no code implementations7 Nov 2018 Benjamin Mark, Garvesh Raskutti, Rebecca Willett

Multivariate Bernoulli autoregressive (BAR) processes model time series of events in which the likelihood of current events is determined by the times and locations of past events.

Time Series Time Series Analysis

Graph-based regularization for regression problems with alignment and highly-correlated designs

no code implementations20 Mar 2018 Yuan Li, Benjamin Mark, Garvesh Raskutti, Rebecca Willett, Hyebin Song, David Neiman

This work considers a high-dimensional regression setting in which a graph governs both correlations among the covariates and the similarity among regression coefficients -- meaning there is \emph{alignment} between the covariates and regression coefficients.

Model Selection regression

Network Estimation from Point Process Data

no code implementations13 Feb 2018 Benjamin Mark, Garvesh Raskutti, Rebecca Willett

Using our general framework, we provide a number of novel theoretical guarantees for high-dimensional self-exciting point processes that reflect the role played by the underlying network structure and long-term memory.

Point Processes

Non-parametric Sparse Additive Auto-regressive Network Models

no code implementations23 Jan 2018 Hao Henry Zhou, Garvesh Raskutti

Using a combination of $\beta$ and $\phi$-mixing properties of Markov chains and empirical process techniques for reproducing kernel Hilbert spaces (RKHSs), we provide upper bounds on mean-squared error in terms of the sparsity $s$, logarithm of the dimension $\log d$, number of time points $T$, and the smoothness of the RKHSs.

Time Series Time Series Analysis

Learning Quadratic Variance Function (QVF) DAG models via OverDispersion Scoring (ODS)

no code implementations28 Apr 2017 Gunwoong Park, Garvesh Raskutti

We prove that this class of QVF DAG models is identifiable, and introduce a new algorithm, the OverDispersion Scoring (ODS) algorithm, for learning large-scale QVF DAG models.

Causal Inference

Non-Convex Projected Gradient Descent for Generalized Low-Rank Tensor Regression

no code implementations30 Nov 2016 Han Chen, Garvesh Raskutti, Ming Yuan

The two main differences between the convex and non-convex approach are: (i) from a computational perspective whether the non-convex projection operator is computable and whether the projection has desirable contraction properties and (ii) from a statistical upper bound perspective, the non-convex approach has a superior rate for a number of examples.


Inference of High-dimensional Autoregressive Generalized Linear Models

no code implementations9 May 2016 Eric C. Hall, Garvesh Raskutti, Rebecca Willett

For instance, each element of an observation vector could correspond to a different node in a network, and the parameters of an autoregressive model would correspond to the impact of the network structure on the time series evolution.

Time Series Time Series Analysis +1

Identifiability Assumptions and Algorithm for Directed Graphical Models with Feedback

no code implementations14 Feb 2016 Gunwoong Park, Garvesh Raskutti

Our simulation study supports our theoretical results, showing that the algorithms based on our two new principles generally out-perform algorithms based on the faithfulness assumption in terms of selecting the true skeleton for DCG models.

Learning Large-Scale Poisson DAG Models based on OverDispersion Scoring

no code implementations NeurIPS 2015 Gunwoong Park, Garvesh Raskutti

In this paper, we address the question of identifiability and learning algorithms for large-scale Poisson Directed Acyclic Graphical (DAG) models.

Statistical and Algorithmic Perspectives on Randomized Sketching for Ordinary Least-Squares -- ICML

no code implementations25 May 2015 Garvesh Raskutti, Michael Mahoney

We then consider the statistical prediction efficiency (PE) and the statistical residual efficiency (RE) of the sketched LS estimator; and we use our framework to provide upper bounds for several types of random projection and random sampling algorithms.

A Statistical Perspective on Randomized Sketching for Ordinary Least-Squares

no code implementations23 Jun 2014 Garvesh Raskutti, Michael Mahoney

Prior results show that, when using sketching matrices such as random projections and leverage-score sampling algorithms, with $p < r \ll n$, the WC error is the same as solving the original problem, up to a small constant.

The Information Geometry of Mirror Descent

no code implementations29 Oct 2013 Garvesh Raskutti, Sayan Mukherjee

Using this equivalence, it follows that (1) mirror descent is the steepest descent direction along the Riemannian manifold of the exponential family; (2) mirror descent with log-likelihood loss applied to parameter estimation in exponential families asymptotically achieves the classical Cram\'er-Rao lower bound and (3) natural gradient descent for manifolds corresponding to exponential families can be implemented as a first-order method through mirror descent.

Learning directed acyclic graphs based on sparsest permutations

no code implementations1 Jul 2013 Garvesh Raskutti, Caroline Uhler

However, there is only limited work on consistency guarantees for score-based and hybrid algorithms and it has been unclear whether consistency guarantees can be proven under weaker conditions than the faithfulness assumption.

Early stopping and non-parametric regression: An optimal data-dependent stopping rule

no code implementations15 Jun 2013 Garvesh Raskutti, Martin J. Wainwright, Bin Yu

The strategy of early stopping is a regularization technique based on choosing a stopping time for an iterative algorithm.


Lower bounds on minimax rates for nonparametric regression with additive sparsity and smoothness

no code implementations NeurIPS 2009 Garvesh Raskutti, Bin Yu, Martin J. Wainwright

components from some distribution $\mP$, we determine tight lower bounds on the minimax rate for estimating the regression function with respect to squared $\LTP$ error.


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