• Publications
  • Influence
Mixed Membership Stochastic Blockmodels
This paper describes a latent variable model of such data called the mixed membership stochastic blockmodel, which extends blockmodels for relational data to ones which capture mixed membership latent relational structure, thus providing an object-specific low-dimensional representation. Expand
Distance Metric Learning with Application to Clustering with Side-Information
This paper presents an algorithm that, given examples of similar (and, if desired, dissimilar) pairs of points in �”n, learns a distance metric over ℝn that respects these relationships. Expand
Theoretically Principled Trade-off between Robustness and Accuracy
The prediction error for adversarial examples (robust error) is decompose as the sum of the natural (classification) error and boundary error, and a differentiable upper bound is provided using the theory of classification-calibrated loss, which is shown to be the tightest possible upper bound uniform over all probability distributions and measurable predictors. Expand
Object Bank: A High-Level Image Representation for Scene Classification & Semantic Feature Sparsification
A high-level image representation, called the Object Bank, is proposed, where an image is represented as a scale-invariant response map of a large number of pre-trained generic object detectors, blind to the testing dataset or visual task. Expand
More Effective Distributed ML via a Stale Synchronous Parallel Parameter Server
We propose a parameter server system for distributed ML, which follows a Stale Synchronous Parallel (SSP) model of computation that maximizes the time computational workers spend doing useful work onExpand
Toward Controlled Generation of Text
A new neural generative model is proposed which combines variational auto-encoders and holistic attribute discriminators for effective imposition of semantic structures inGeneric generation and manipulation of text. Expand
A Latent Variable Model for Geographic Lexical Variation
A multi-level generative model that reasons jointly about latent topics and geographical regions is presented, which recovers coherent topics and their regional variants, while identifying geographic areas of linguistic consistency. Expand
Distributed cosegmentation via submodular optimization on anisotropic diffusion
CoSand is proposed, a distributed cosegmentation approach for a highly variable large-scale image collection that takes advantage of a strong theoretic property in that the temperature under linear anisotropic diffusion is a submodular function; therefore, a greedy algorithm guarantees at least a constant factor approximation to the optimal solution for temperature maximization. Expand
Sparse Additive Generative Models of Text
This approach has two key advantages: it can enforce sparsity to prevent overfitting, and it can combine generative facets through simple addition in log space, avoiding the need for latent switching variables. Expand
Deep Kernel Learning
We introduce scalable deep kernels, which combine the structural properties of deep learning architectures with the non-parametric flexibility of kernel methods. Specifically, we transform the inputsExpand