• Publications
  • Influence
Discriminative Embeddings of Latent Variable Models for Structured Data
TLDR
In applications involving millions of data points, it is shown that structure2vec runs 2 times faster, produces models which are 10, 000 times smaller, while at the same time achieving the state-of-the-art predictive performance.
DualDICE: Behavior-Agnostic Estimation of Discounted Stationary Distribution Corrections
TLDR
This work proposes an algorithm, DualDICE, that is agnostic to knowledge of the behavior policy (or policies) used to generate the dataset and improves accuracy compared to existing techniques.
Syntax-Directed Variational Autoencoder for Structured Data
TLDR
This work proposes a novel syntax-directed variational autoencoder (SD-VAE) by introducing stochastic lazy attributes, which demonstrates the effectiveness in incorporating syntactic and semantic constraints in discrete generative models, which is significantly better than current state-of-the-art approaches.
Scalable Kernel Methods via Doubly Stochastic Gradients
TLDR
An approach that scales up kernel methods using a novel concept called "doubly stochastic functional gradients" based on the fact that many kernel methods can be expressed as convex optimization problems, which can readily scale kernel methods up to the regimes which are dominated by neural nets.
AlgaeDICE: Policy Gradient from Arbitrary Experience
TLDR
A new formulation of max-return optimization that allows the problem to be re-expressed by an expectation over an arbitrary behavior-agnostic and off-policy data distribution and shows that, if auxiliary dual variables of the objective are optimized, then the gradient of the off-Policy objective is exactly the on-policy policy gradient, without any use of importance weighting.
Stochastic Generative Hashing
TLDR
This paper proposes a novel generative approach to learn hash functions through Minimum Description Length principle such that the learned hash codes maximally compress the dataset and can also be used to regenerate the inputs.
Iterative Machine Teaching
TLDR
This paper studies a new paradigm where the learner uses an iterative algorithm and a teacher can feed examples sequentially and intelligently based on the current performance of the learNER.
Retrosynthesis Prediction with Conditional Graph Logic Network
TLDR
The Conditional Graph Logic Network is proposed, a conditional graphical model built upon graph neural networks that learns when rules from reaction templates should be applied, implicitly considering whether the resulting reaction would be both chemically feasible and strategic.
Learning towards Minimum Hyperspherical Energy
TLDR
The redundancy regularization problem is reduced to generic energy minimization, and a minimum hyperspherical energy (MHE) objective is proposed as generic regularization for neural networks.
GenDICE: Generalized Offline Estimation of Stationary Values
TLDR
This work proves the consistency of the method under general conditions, provides a detailed error analysis, and demonstrates strong empirical performance on benchmark tasks, including off-line PageRank and off-policy policy evaluation.
...
...