We study several variants of a combinatorial game which is based on Cant...
We consider Sharpness-Aware Minimization (SAM), a gradient-based optimiz...
Humans can reason compositionally when presented with new tasks. Previou...
Learning curves plot the expected error of a learning algorithm as a fun...
We propose a novel prompting strategy, least-to-most prompting, that ena...
The amount of training-data is one of the key factors which determines t...
Hypothesis Selection is a fundamental distribution learning problem wher...
How quickly can a given class of concepts be learned from examples? It i...
We study deep neural networks (DNNs) trained on natural image data with
...
The classical PAC sample complexity bounds are stated for any Empirical ...
We study the prediction of the accuracy of a neural network given only i...
We consider the variance of a function of n independent random variables...
State-of-the-art machine learning methods exhibit limited compositional
...
We consider the classical problem of learning rates for classes with fin...
The generalization bounds for stable algorithms is a classical question ...
Recent progress in the field of reinforcement learning has been accelera...
In semi-supervised classification, one is given access both to labeled a...
The estimation of an f-divergence between two probability distributions ...
Despite the tremendous progress in the estimation of generative models, ...
Consider the following problem: given two arbitrary densities q_1,q_2 an...
We introduce two mathematical frameworks for foolability in the context ...
Recent advances in generative modeling have led to an increased interest...
Deep neural networks are often trained in the over-parametrized regime (...
Generative adversarial networks (GAN) are a powerful subclass of generat...
We propose the Wasserstein Auto-Encoder (WAE)---a new algorithm for buil...
Generative adversarial networks (GAN) approximate a target data distribu...
Generic text embeddings are successfully used in a variety of tasks. How...
We study unsupervised generative modeling in terms of the optimal transp...
Generative Adversarial Networks (GAN) (Goodfellow et al., 2014) are an
e...