Share This Author
Theoretically Principled Trade-off between Robustness and Accuracy
- Hongyang R. Zhang, Yaodong Yu, Jiantao Jiao, E. Xing, L. Ghaoui, Michael I. Jordan
- Computer ScienceICML
- 24 January 2019
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.
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.
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.
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 on…
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.
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.
DAGs with NO TEARS: Continuous Optimization for Structure Learning
This paper forms the structure learning problem as a purely continuous optimization problem over real matrices that avoids this combinatorial constraint entirely and achieves a novel characterization of acyclicity that is not only smooth but also exact.
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.
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 inputs…
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.