• Publications
  • Influence
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
This work empirically demonstrates that its algorithms significantly reduce gender bias in embeddings while preserving the its useful properties such as the ability to cluster related concepts and to solve analogy tasks. Expand
Zero-Shot Learning via Semantic Similarity Embedding
In this paper we consider a version of the zero-shot learning problem where seen class source and target domain data are provided. The goal during test-time is to accurately predict the class labelExpand
Zero-Shot Learning via Joint Latent Similarity Embedding
A joint discriminative learning framework based on dictionary learning is developed to jointly learn the parameters of the model for both domains, which ultimately leads to a class-independent classifier that shows 4.90% improvement over the state-of-the-art in accuracy averaged across four benchmark datasets. Expand
Boolean Compressed Sensing and Noisy Group Testing
The group testing problem is formulated as a channel coding/decoding problem and a single-letter characterization for the total number of tests used to identify the defective set is derived. Expand
Video anomaly detection based on local statistical aggregates
A key insight of the paper is that if anomalies are local optimal decision rules are local even when the nominal behavior exhibits global spatial and temporal statistical dependencies, this insight helps collapse the large ambient data dimension for detecting local anomalies. Expand
Non-adaptive probabilistic group testing with noisy measurements: Near-optimal bounds with efficient algorithms
This work is the first to explicitly estimate such a constant that characterizes the gap between the upper and lower bounds for these problems, and gives information-theoretic lower bounds on the query complexity of these problems. Expand
Efficient Training of Very Deep Neural Networks for Supervised Hashing
This paper proposes a novel and efficient training algorithm inspired by alternating direction method of multipliers (ADMM) that overcomes some of the limitations of existing methods for supervised learning of hash codes. Expand
Information Theoretic Bounds for Compressed Sensing
This paper derives information theoretic performance bounds to sensing and reconstruction of sparse phenomena from noisy projections by developing novel extensions to Fano's inequality to handle continuous domains and arbitrary distortions and shows that with constant SNR the number of measurements scales linearly with the rate-distortion function of the sparse phenomena. Expand
Foreground-Adaptive Background Subtraction
This paper introduces a nonparametric background model based on small spatial neighborhood to improve discrimination sensitivity and applies a Markov model to change labels to improve spatial coherence of the detections. Expand
Adaptive Neural Networks for Efficient Inference
It is shown that computational time can be dramatically reduced by exploiting the fact that many examples can be correctly classified using relatively efficient networks and that complex, computationally costly networks are only necessary for a small fraction of examples. Expand