Sort by:

• Highly Influential Citations
• Citations
• Acceleration
• Velocity
• Recency

Learn More

Semantic Parsing on Freebase from Question-Answer Pairs

• Jonathan Berant, Andrew Chou, Roy Frostig, Percy Liang
• EMNLP
• 2013

In this paper, we train a semantic parser that scales up to Freebase. Instead of relying on annotated logical forms, which is especially expensive to obtain at large scale, we learn from… (More)

Un-regularizing: approximate proximal point and faster stochastic algorithms for empirical risk minimization

• Roy Frostig, Rong Ge, Sham M. Kakade, Aaron Sidford
• ICML
• 2015

We develop a family of accelerated stochastic algorithms that minimize sums of convex functions. Our algorithms improve upon the fastest running time for empirical risk minimization (ERM), and in… (More)

Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivity

• Amit Daniely, Roy Frostig, Yoram Singer
• NIPS
• 2016

We develop a general duality between neural networks and compositional kernel Hilbert spaces. We introduce the notion of a computation skeleton, an acyclic graph that succinctly describes both a… (More)

Competing with the Empirical Risk Minimizer in a Single Pass

• Roy Frostig, Rong Ge, Sham M. Kakade, Aaron Sidford
• COLT
• 2015

In many estimation problems, e.g. linear and logistic regression, we wish to minimize an unknown objective given only unbiased samples of the objective function. Furthermore, we aim to achieve this… (More)

Principal Component Projection Without Principal Component Analysis

• Roy Frostig, Cameron Musco, Christopher Musco, Aaron Sidford
• ICML
• 2016

We show how to efficiently project a vector onto the top principal components of a matrix, without explicitly computing these components. Specifically, we introduce an iterative algorithm that… (More)

Simple MAP Inference via Low-Rank Relaxations

• Roy Frostig, Sida I. Wang, Percy Liang, Christopher D. Manning
• NIPS
• 2014

We focus on the problem of maximum a posteriori (MAP) inference in Markov random fields with binary variables and pairwise interactions. For this common subclass of inference tasks, we consider… (More)

Parente2: a fast and accurate method for detecting identity by descent.

• Jesse M. Rodriguez, Sivan Bercovici, Lin Ke Huang, Roy Frostig, Serafim Batzoglou
• Genome research
• 2015

Identity-by-descent (IBD) inference is the problem of establishing a genetic connection between two individuals through a genomic segment that is inherited by both individuals from a recent common… (More)

Random Features for Compositional Kernels

• Amit Daniely, Roy Frostig, Vineet Gupta, Yoram Singer
• ArXiv
• 2017

We describe and analyze a simple random feature scheme (RFS) from prescribed compositional kernels. The compositional kernels we use are inspired by the structure of convolutional neural networks and… (More)

Relaxations for inference in restricted Boltzmann machines

• Sida I. Wang, Roy Frostig, Percy Liang, Christopher D. Manning
• ArXiv
• 2013

We propose a randomized relax-and-round inference algorithm that samples near-MAP configurations of a binary pairwise Markov random field. We experiment on MAP inference tasks in several restricted… (More)

Compiling machine learning programs via high-level tracing

• Roy Frostig, Matthew J. Johnson
• 2018

We describe JAX, a domain-specific tracing JIT compiler for generating high-performance accelerator code from pure Python and Numpy machine learning programs. JAX uses the XLA compiler infrastructure… (More)

• ‹
• 1
• 2
• ›