94 citations · 361 across the 20 of their papers we have counts for
22 papers
Thermalization of horizon through asymptotic symmetry in three-dimensional massive gravity
M. R. Setare, A. Jalali, Bibhas Ranjan Majhi
Recently, black hole symmetries have been studied widely and it has been speculated that this procedure will lead to the deeper understanding of the black hole physics. Spontaneous…
Not All Features Are Equal: Discovering Essential Features for Preserving Prediction Privacy
Fatemehsadat Mireshghallah, Mohammadkazem Taram, Ali Jalali +3
When receiving machine learning services from the cloud, the provider does not need to receive all features; in fact, only a subset of the features are necessary for the target pre…
Holographically description of Kerr-Bolt Black hole in terms of the warped conformal field theory
M. R. Setare, A. Jalali
Recently it has been speculated that a set of diffeomorphisms exist which act non-trivially on the horizon of some black holes such as Kerr and Kerr-Newman black hole. %\cite{Haco:…
Kerr-Bolt Black Hole Entropy and Soft Hair
M. R. Setare, A. Jalali
Recently it has been speculated that a set of infinitesimal diffeomorphisms exist which act non-trivially on the horizon of some b…
Dilaton Black Hole Entropy from Entropy Function Formalism
Komeil Babaei Velni, Ali Jalali, Bahareh Khoshdelan
It has been shown that the entropy function formalism is an efficient way to calculate the entropy of black holes in string theory. We check this formalism for the extremal charged…
Higher derivative corrections to DBI action at order
Komeil Babaei Velni, Ali Jalali
We use the compatibility of D-brane action with linear off-shell T-duality and linear on-shell S-duality as guiding principles to find all world volume couplings of one massless cl…
On Chern-Simons Couplings at order
Komeil Babaei Velni, Ali Jalali
Using the explicit string scattering calculation and the linear T-dual ward identity, we evaluate the string theory disc amplitude of one Ramond-Ramond field and two Ne…
Higher derivative corrections to WZ action: One RR, one NSNS and one NS couplings
Ali Jalali, Mohammad R. Garousi
In the first part of this paper, we calculate the disk-level S-matrix elements of one RR, one NSNS and one NS vertex operators, and show that they are consistent with the amplitude…
On D-brane action at order
Ali Jalali, Mohammad R. Garousi
We use compatibility of D-brane action with linear T-duality, S-duality and with S-matrix elements as guiding principles to find all world volume couplings of one massless closed a…
Scalable Audience Reach Estimation in Real-time Online Advertising
Ali Jalali, Santanu Kolay, Peter Foldes +1
Online advertising has been introduced as one of the most efficient methods of advertising throughout the recent years. Yet, advertisers are concerned about the efficiency of their…
Real Time Bid Optimization with Smooth Budget Delivery in Online Advertising
Kuang-Chih Lee, Ali Jalali, Ali Dasdan
Today, billions of display ad impressions are purchased on a daily basis through a public auction hosted by real time bidding (RTB) exchanges. A decision has to be made for adverti…
A New Greedy Algorithm for Multiple Sparse Regression
Ali Jalali, Sujay Sanghavi
This paper proposes a new algorithm for multiple sparse regression in high dimensions, where the task is to estimate the support and values of several (typically related) sparse ve…
A Lipschitz Exploration-Exploitation Scheme for Bayesian Optimization
Ali Jalali, Javad Azimi, Xiaoli Fern +1
The problem of optimizing unknown costly-to-evaluate functions has been studied for a long time in the context of Bayesian Optimization. Algorithms in this field aim to find the op…
Clustering using Max-norm Constrained Optimization
Ali Jalali, Nathan Srebro
We suggest using the max-norm as a convex surrogate constraint for clustering. We show how this yields a better exact cluster recovery guarantee than previously suggested nuclear-n…
Hybrid Batch Bayesian Optimization
Javad Azimi, Ali Jalali, Xiaoli Fern
Bayesian Optimization aims at optimizing an unknown non-convex/concave function that is costly to evaluate. We are interested in application scenarios where concurrent function eva…
High-dimensional Sparse Inverse Covariance Estimation using Greedy Methods
Christopher C. Johnson, Ali Jalali, Pradeep Ravikumar
In this paper we consider the task of estimating the non-zero pattern of the sparse inverse covariance matrix of a zero-mean Gaussian random vector from a set of iid samples. Note…
Dynamic Batch Bayesian Optimization
Javad Azimi, Ali Jalali, Xiaoli Fern
Bayesian optimization (BO) algorithms try to optimize an unknown function that is expensive to evaluate using minimum number of evaluations/experiments. Most of the proposed algori…
On Learning Discrete Graphical Models Using Greedy Methods
Ali Jalali, Chris Johnson, Pradeep Ravikumar
In this paper, we address the problem of learning the structure of a pairwise graphical model from samples in a high-dimensional setting. Our first main result studies the sparsist…
A Dirty Model for Multiple Sparse Regression
Ali Jalali, Pradeep Ravikumar, Sujay Sanghavi
Sparse linear regression -- finding an unknown vector from linear measurements -- is now known to be possible with fewer samples than variables, via methods like the LASSO. We cons…
Learning the Dependence Graph of Time Series with Latent Factors
Ali Jalali, Sujay Sanghavi
This paper considers the problem of learning, from samples, the dependency structure of a system of linear stochastic differential equations, when some of the variables are latent.…
Clustering Partially Observed Graphs via Convex Optimization
Yudong Chen, Ali Jalali, Sujay Sanghavi +1
This paper considers the problem of clustering a partially observed unweighted graph---i.e., one where for some node pairs we know there is an edge between them, for some others we…
Low-rank Matrix Recovery from Errors and Erasures
Yudong Chen, Ali Jalali, Sujay Sanghavi +1
This paper considers the recovery of a low-rank matrix from an observed version that simultaneously contains both (a) erasures: most entries are not observed, and (b) errors: value…