Author pages are created from data sourced from our academic publisher partnerships and public sources.

- Publications
- Influence

Variational Dropout and the Local Reparameterization Trick

- A. Blum, N. Haghtalab, A. Procaccia
- Computer Science, Mathematics
- NIPS
- 2015

We explore an as yet unexploited opportunity for drastically improving the efficiency of stochastic gradient variational Bayes (SGVB) with global model parameters. Regular SGVB estimators rely on… Expand

Ignorance is Almost Bliss: Near-Optimal Stochastic Matching With Few Queries

- A. Blum, N. Haghtalab, A. Procaccia, A. Sharma
- Computer Science
- EC '15
- 15 July 2014

The stochastic matching problem deals with finding a maximum matching in a graph whose edges are unknown but can be accessed via queries. This is a special case of stochastic k-set packing, where the… Expand

Commitment Without Regrets: Online Learning in Stackelberg Security Games

- Maria-Florina Balcan, A. Blum, N. Haghtalab, A. Procaccia
- Computer Science
- EC '15
- 15 June 2015

In a Stackelberg Security Game, a defender commits to a randomized deployment of security resources, and an attacker best-responds by attacking a target that maximizes his utility. While algorithms… Expand

Efficient Learning of Linear Separators under Bounded Noise

- P. Awasthi, Maria-Florina Balcan, N. Haghtalab, Ruth Urner
- Computer Science, Mathematics
- COLT
- 11 March 2015

We study the learnability of linear separators in $\Re^d$ in the presence of bounded (a.k.a Massart) noise. This is a realistic generalization of the random classification noise model, where the… Expand

Learning Optimal Commitment to Overcome Insecurity

- A. Blum, N. Haghtalab, A. Procaccia
- Computer Science
- NIPS
- 8 December 2014

Game-theoretic algorithms for physical security have made an impressive real-world impact. These algorithms compute an optimal strategy for the defender to commit to in a Stackelberg game, where the… Expand

k-Center Clustering Under Perturbation Resilience

- Maria-Florina Balcan, N. Haghtalab, C. White
- Computer Science, Mathematics
- ICALP
- 14 May 2015

The $k$-center problem is a canonical and long-studied facility location and clustering problem with many applications in both its symmetric and asymmetric forms. Both versions of the problem have… Expand

Collaborative PAC Learning

- A. Blum, N. Haghtalab, A. Procaccia, Mingda Qiao
- Computer Science
- NIPS
- 1 December 2017

We introduce a collaborative PAC learning model, in which k players attempt to learn the same underlying concept. We ask how much more information is required to learn an accurate classifier for all… Expand

Symmetric and Asymmetric $k$-center Clustering under Stability

- Maria-Florina Balcan, Nika Haghtalab, Colin White
- Mathematics, Computer Science
- ArXiv
- 14 May 2015

The k-center problem is a canonical and long-studied facility location and clustering problem with many applications in both its symmetric and asymmetric forms. Both versions of the problem have… Expand

- 7
- 3

Insecticidal efficacy of castor and hazelnut oils in stored cowpea against Callosobruchus maculatus (F.) (Coleoptera: Bruchidae).

- Nika Haghtalab, Nouraldin Shayesteh, Shahram Aramideh
- Biology
- 1 February 2009

Learning and 1-bit Compressed Sensing under Asymmetric Noise

- P. Awasthi, Maria-Florina Balcan, N. Haghtalab, Hongyang Zhang
- Computer Science
- COLT
- 6 June 2016

We study the approximate recovery problem under noise: Given corrupted 1-bit measurements of the form sign(w∗ · xi), recover a vector w with a small 0/1 loss w.r.t. w∗ ∈ R. In learning theory, this… Expand