
Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for WorstCase Generalization
Overparameterized neural networks can be highly accurate on average on a...
read it

Learning Autocomplete Systems as a Communication Game
We study textual autocomplete—the task of predicting a full sentence fro...
read it

Distributionally Robust Language Modeling
Language models are generally trained on data spanning a wide range of t...
read it

Unifying Human and Statistical Evaluation for Natural Language Generation
How can we measure whether a natural language generation system produces...
read it

A RetrieveandEdit Framework for Predicting Structured Outputs
For the task of generating complex outputs such as source code, editing ...
read it

Fairness Without Demographics in Repeated Loss Minimization
Machine learning models (e.g., speech recognizers) are usually trained t...
read it

Derivative free optimization via repeated classification
We develop an algorithm for minimizing a function using n batched functi...
read it

Unsupervised Transformation Learning via Convex Relaxations
Our goal is to extract meaningful transformations from raw images, such ...
read it

Generating Sentences by Editing Prototypes
We propose a new generative model of sentences that first samples a prot...
read it

From random walks to distances on unweighted graphs
Large unweighted directed graphs are commonly used to capture relations ...
read it

Word, graph and manifold embedding from Markov processes
Continuous vector representations of words and objects appear to carry s...
read it

Metric recovery from directed unweighted graphs
We analyze directed, unweighted graphs obtained from x_i∈R^d by connecti...
read it
Tatsunori B. Hashimoto
is this you? claim profile