Query-Focused Meeting Summarization (QFMS) aims to generate a summary of...
In this short note we consider random fully connected ReLU networks of w...
This paper proposes a framework for quantitatively evaluating interactiv...
We present NusaCrowd, a collaborative initiative to collect and unite
ex...
Dialogue systems can leverage large pre-trained language models and know...
Large-scale vision-language pre-trained (VLP) models are prone to halluc...
Not all convex functions on ℝ^n have finite minimizers; some can
only be...
We initiate a formal study of reproducibility in optimization. We define...
We investigate approximation guarantees provided by logistic regression ...
We show that the simplest actor-critic method – a linear softmax policy
...
We present and analyze a momentum-based gradient method for training lin...
This work studies the behavior of neural networks trained with the logis...
This paper theoretically investigates the following empirical phenomenon...
Amid the pandemic COVID-19, the world is facing unprecedented infodemic ...
Cross-domain named entity recognition (NER) models are able to cope with...
Multi-hop Question Generation (QG) aims to generate answer-related quest...
Recent work across many machine learning disciplines has highlighted tha...
In this paper, we show that although the minimizers of cross-entropy and...
This paper establishes rates of universal approximation for the shallow
...
Recent work has revealed that overparameterized networks trained by grad...
This paper investigates the approximation power of three types of random...
Recent work shows that gradient descent on linearly separable data is
im...
This paper establishes risk convergence and asymptotic weight matrix
ali...
The logistic loss is strictly convex and does not attain its infimum;
co...
Wikidata is the new, large-scale knowledge base of the Wikimedia Foundat...
Consider the seller's problem of finding "optimal" prices for her (divis...