Tatsunori B. Hashimoto

is this you? claim profile

0 followers
MIT ∙ Microsoft ∙ Stanford University

Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization

Overparameterized neural networks can be highly accurate on average on a...
11/20/2019 ∙ by Shiori Sagawa, et al. ∙ 0 ∙ share

read it
Learning Autocomplete Systems as a Communication Game

We study textual autocomplete—the task of predicting a full sentence fro...
11/16/2019 ∙ by Mina Lee, et al. ∙ 0 ∙ share

read it
Distributionally Robust Language Modeling

Language models are generally trained on data spanning a wide range of t...
09/04/2019 ∙ by Yonatan Oren, et al. ∙ 0 ∙ share

read it
Unifying Human and Statistical Evaluation for Natural Language Generation

How can we measure whether a natural language generation system produces...
04/04/2019 ∙ by Tatsunori B. Hashimoto, et al. ∙ 0 ∙ share

read it
A Retrieve-and-Edit Framework for Predicting Structured Outputs

For the task of generating complex outputs such as source code, editing ...
12/04/2018 ∙ by Tatsunori B. Hashimoto, et al. ∙ 0 ∙ share

read it
Fairness Without Demographics in Repeated Loss Minimization

Machine learning models (e.g., speech recognizers) are usually trained t...
06/20/2018 ∙ by Tatsunori B. Hashimoto, et al. ∙ 0 ∙ share

read it
Derivative free optimization via repeated classification

We develop an algorithm for minimizing a function using n batched functi...
04/11/2018 ∙ by Tatsunori B. Hashimoto, et al. ∙ 0 ∙ share

read it
Unsupervised Transformation Learning via Convex Relaxations

Our goal is to extract meaningful transformations from raw images, such ...
11/06/2017 ∙ by Tatsunori B. Hashimoto, et al. ∙ 0 ∙ share

read it
Generating Sentences by Editing Prototypes

We propose a new generative model of sentences that first samples a prot...
09/26/2017 ∙ by Kelvin Guu, et al. ∙ 0 ∙ share

read it
From random walks to distances on unweighted graphs

Large unweighted directed graphs are commonly used to capture relations ...
11/02/2015 ∙ by Tatsunori B. Hashimoto, et al. ∙ 0 ∙ share

read it
Word, graph and manifold embedding from Markov processes

Continuous vector representations of words and objects appear to carry s...
09/18/2015 ∙ by Tatsunori B. Hashimoto, et al. ∙ 0 ∙ share

read it
Metric recovery from directed unweighted graphs

We analyze directed, unweighted graphs obtained from x_i∈R^d by connecti...
11/20/2014 ∙ by Tatsunori B. Hashimoto, et al. ∙ 0 ∙ share

read it

Tatsunori B. Hashimoto

Featured Co-authors

Percy Liang

Tommi S. Jaakkola

John C. Duchi

Yi Sun

David Alvarez-Melis

Hongseok Namkoong

Kelvin Guu

Pang Wei Koh

Steve Yadlowsky

Shiori Sagawa

Mina Lee

Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization

Learning Autocomplete Systems as a Communication Game

Distributionally Robust Language Modeling

Unifying Human and Statistical Evaluation for Natural Language Generation

A Retrieve-and-Edit Framework for Predicting Structured Outputs

Fairness Without Demographics in Repeated Loss Minimization

Derivative free optimization via repeated classification

Unsupervised Transformation Learning via Convex Relaxations

Generating Sentences by Editing Prototypes

From random walks to distances on unweighted graphs

Word, graph and manifold embedding from Markov processes

Metric recovery from directed unweighted graphs