53 citations · 181 across the 16 of their papers we have counts for
17 papers
Fast Feature Selection with Fairness Constraints
Francesco Quinzan, Rajiv Khanna, Moshik Hershcovitch +4
We study the fundamental problem of selecting optimal features for model construction. This problem is computationally challenging on large datasets, even with the use of greedy al…
Improved guarantees and a multiple-descent curve for Column Subset Selection and the Nyström method
Michał Dereziński, Rajiv Khanna, Michael W. Mahoney
The Column Subset Selection Problem (CSSP) and the Nyström method are among the leading tools for constructing small low-rank approximations of large datasets in machine learning a…
Learning Sparse Distributions using Iterative Hard Thresholding
Jacky Y. Zhang, Rajiv Khanna, Anastasios Kyrillidis +1
Iterative hard thresholding (IHT) is a projected gradient descent algorithm, known to achieve state of the art performance for a wide range of structured estimation problems, such…
Geometric Rates of Convergence for Kernel-based Sampling Algorithms
Rajiv Khanna, Liam Hodgkinson, Michael W. Mahoney
The rate of convergence of weighted kernel herding (WKH) and sequential Bayesian quadrature (SBQ), two kernel-based sampling algorithms for estimating integrals with respect to som…
Interpreting Black Box Predictions using Fisher Kernels
Rajiv Khanna, Been Kim, Joydeep Ghosh +1
Research in both machine learning and psychology suggests that salient examples can help humans to interpret learning models. To this end, we take a novel look at black box interpr…
Boosting Black Box Variational Inference
Francesco Locatello, Gideon Dresdner, Rajiv Khanna +2
Approximating a probability density in a tractable manner is a central task in Bayesian statistics. Variational Inference (VI) is a popular technique that achieves tractability by…
IHT dies hard: Provable accelerated Iterative Hard Thresholding
Rajiv Khanna, Anastasios Kyrillidis
We study --both in theory and practice-- the use of momentum motions in classic iterative hard thresholding (IHT) methods. By simply modifying plain IHT, we investigate its converg…
Boosting Variational Inference: an Optimization Perspective
Francesco Locatello, Rajiv Khanna, Joydeep Ghosh +1
Variational inference is a popular technique to approximate a possibly intractable Bayesian posterior with a more tractable one. Recently, boosting variational inference has been p…
Scalable Greedy Feature Selection via Weak Submodularity
Rajiv Khanna, Ethan Elenberg, Alexandros G. Dimakis +2
Greedy algorithms are widely used for problems in machine learning such as feature selection and set function optimization. Unfortunately, for large datasets, the running time of e…
On Approximation Guarantees for Greedy Low Rank Optimization
Rajiv Khanna, Ethan Elenberg, Alexandros G. Dimakis +1
We provide new approximation guarantees for greedy low rank matrix estimation under standard assumptions of restricted strong convexity and smoothness. Our novel analysis also unco…
A Unified Optimization View on Generalized Matching Pursuit and Frank-Wolfe
Francesco Locatello, Rajiv Khanna, Michael Tschannen +1
Two of the most fundamental prototypes of greedy optimization are the matching pursuit and Frank-Wolfe algorithms. In this paper, we take a unified view on both classes of methods,…
Restricted Strong Convexity Implies Weak Submodularity
Ethan R. Elenberg, Rajiv Khanna, Alexandros G. Dimakis +1
We connect high-dimensional subset selection and submodular maximization. Our results extend the work of Das and Kempe (2011) from the setting of linear regression to arbitrary obj…
Information Projection and Approximate Inference for Structured Sparse Variables
Rajiv Khanna, Joydeep Ghosh, Russell Poldrack +1
Approximate inference via information projection has been recently introduced as a general-purpose approach for efficient probabilistic inference given sparse variables. This manus…
Pursuits in Structured Non-Convex Matrix Factorizations
Rajiv Khanna, Michael Tschannen, Martin Jaggi
Efficiently representing real world data in a succinct and parsimonious manner is of central importance in many fields. We present a generalized greedy pursuit framework, allowing…
Towards a Better Understanding of Predict and Count Models
S. Sathiya Keerthi, Tobias Schnabel, Rajiv Khanna
In a recent paper, Levy and Goldberg pointed out an interesting connection between prediction-based word embedding models and count models based on pointwise mutual information. Un…
DPM: A State Space Model for Large-Scale Direct Marketing
Yubin Park, Rajiv Khanna, Joydeep Ghosh +1
We propose a novel statistical model to answer three challenges in direct marketing: which channel to use, which offer to make, and when to offer. There are several potential appli…
Parallel Matrix Factorization for Binary Response
Rajiv Khanna, Liang Zhang, Deepak Agarwal +1
Predicting user affinity to items is an important problem in applications like content optimization, computational advertising, and many more. While bilinear random effect models (…