• Publications
  • Influence
Deep Sets
TLDR
We study the problem of designing models for machine learning tasks defined on sets. Expand
Federated Optimization in Heterogeneous Networks
TLDR
We propose FedProx, a federated optimization algorithm that addresses the challenges of heterogeneity in federated networks. Expand
Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
TLDR
We propose a new algorithm MINERVA, which addresses the much more difficult and practical task of answering questions where the relation is known, but only one entity. Expand
Gaussian LDA for Topic Models with Word Embeddings
TLDR
We replace LDA’s parameterization of “topics” as categorical distributions over opaque word types with multivariate Gaussian distributions on the embedding space. Expand
Compressed Video Action Recognition
TLDR
We propose to train a deep network directly on the compressed video. Expand
Adaptive Methods for Nonconvex Optimization
TLDR
Adaptive gradient methods that rely on scaling gradients down by the square root of exponential moving averages of squared gradients, such RMSProp, Adam, Adadelta have found wide application in optimizing the nonconvex problems that arise in deep learning. Expand
Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text
TLDR
We propose a novel model, GRAFT-Net, for extracting answers from a question-specific subgraph containing text and KB entities and relations, which outperforms state-of-the-art methods in the combined setting. Expand
Adaptive Federated Optimization
TLDR
We propose federated versions of adaptive optimizers, including Adagrad, Adam, and Yogi, and analyze their convergence in the presence of heterogeneous data for general nonconvex settings. Expand
On the Convergence of Federated Optimization in Heterogeneous Networks
TLDR
We propose and introduce \fedprox, which is similar in spirit to \fedavg, but more amenable to theoretical analysis. Expand
Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering
TLDR
This paper introduces a new framework for open-domain question answering in which the retriever and the reader iteratively interact with each other. Expand
...
1
2
3
4
5
...