In recent years, there has been an exponential growth in the number of complex documents
and texts that require a deeper understanding of machine learning methods to be able to …

In recent years, significant progress has been made in developing more accurate and
efficient machine learning algorithms for segmentation of medical and natural images. In this …

The remarkable practical success of deep learning has revealed some major surprises from
a theoretical perspective. In particular, simple gradient methods easily find near-optimal …

Most methods for time series classification that attain state-of-the-art accuracy have high
computational complexity, requiring significant training time even for smaller datasets, and …

We build new test sets for the CIFAR-10 and ImageNet datasets. Both benchmarks have
been the focus of intense research for almost a decade, raising the danger of overfitting to …

In a series of recent theoretical works, it was shown that strongly over-parameterized neural
networks trained with gradient-based methods could converge exponentially fast to zero …

Attention layers---which map a sequence of inputs to a sequence of outputs---are core
building blocks of the Transformer architecture which has achieved significant …

Despite the great empirical success of deep reinforcement learning, its theoretical
foundation is less well understood. In this work, we make the first attempt to theoretically …

This survey describes probabilistic algorithms for linear algebraic computations, such as
factorizing matrices and solving linear systems. It focuses on techniques that have a proven …

The population loss of trained deep neural networks often follows precise power-law scaling
relations with either the size of the training dataset or the number of parameters in the …