• Publications
  • Influence
Automatic Understanding of Image and Video Advertisements
tl;dr
We propose the novel problem of ad-understanding, and develop two datasets to enable progress on it. Expand
  • 53
  • 13
  • Open Access
Partial Redundancy in HPC Systems with Non-Uniform Node Reliabilities
tl;dr
We study the usefulness of partial redundancy in HPC message passing systems where individual node failure distributions are not identical. Expand
  • 11
  • 2
  • Open Access
Diversifying with Few Regrets, But too Few to Mention
tl;dr
In this work we propose a novel scheme called ReDi, which aims to generate representative data that balance the tradeoff between regret minimization and diversity maximization. Expand
  • 5
  • Open Access
Interpreting the Rhetoric of Visual Advertisements.
tl;dr
We make available a dataset of 64,832 image ads and 3,477 video ads, annotated with ten types of information: the topic and sentiment of the ad; whether it is funny, exciting, or effective; what action it prompts the viewer to do, and what arguments it provides for why this action should be taken; symbolic associations that the ad relies on; the metaphorical object transformations on which especially creative ads rely; and the climax. Expand
  • 1
CoLoR: Co-Located Rescuers for Fault Tolerance in HPC Systems
tl;dr
We propose CoLoR, a fault tolerance scheme that i)requires only the failing process to recover, ii)overlaps reexecution with restart, and iii)avoids the cumulative effect of successive failures. Expand
  • 1
A systematic fault-tolerant computational model for both crash failures and silent data corruption
tl;dr
This paper proposes a novel fault-tolerant computational model that applies to both compute- and data-intensive workloads, and deals with diverse types of faults. Expand
Sample size reduction in groundwater surveys via sparse data assimilation
tl;dr
In this paper, we focus on sparse signal recovery methods for data assimilation in groundwater models. Expand
  • 1
  • Open Access
Graph Sensitive Indices for Comparing Clusterings
tl;dr
This report discusses two new indices for comparing clusterings of a set of points. Expand
  • 1
  • Open Access
Optimal Placement of In-memory Checkpoints Under Heterogeneous Failure Likelihoods
tl;dr
We provide theoretical results on the optimal way to place in-memory checkpoints such that the probability of occurrence of a catastrophic failure, i.e. failure of a node as well as the node containing its checkpoint, is minimized. Expand
Enhancing Reliability-Aware Speedup Modelling via Replication
tl;dr
Reliability-aware speedup models study the expected speedup of a parallel application as a function of the number of processors, on a platform susceptible to processor failures. Expand