
-
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...
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 Retrieve-and-Edit 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