We propose a new class of linear Transformers called
FourierLearner-Tran...
We present two new classes of algorithms for efficient field integration...
The problem of efficient approximation of a linear operator induced by t...
Composition theorems are general and powerful tools that facilitate priv...
The problem of learning threshold functions is a fundamental one in mach...
CountSketch and Feature Hashing (the "hashing trick") are popular random...
We introduce chefs' random tables (CRTs), a new class of non-trigonometr...
CountSketch is a popular dimensionality reduction technique that maps ve...
We introduce ES-ENAS, a simple neural architecture search (NAS) algorith...
Common datasets have the form of elements with keys (e.g.,
transactions ...
We introduce Performers, Transformer architectures which can estimate re...
Transformer models have achieved state-of-the-art results across a diver...
We present a new class of stochastic, geometrically-driven optimization
...
We present a new algorithm for finding compact neural networks encoding
...
We provide an online convex optimization algorithm with regret that
inte...
Wasserstein distances are increasingly used in a wide variety of applica...
We introduce LAMP: the Linear Additive Markov Process. Transitions in LA...
We present a generic compact computational framework relying on structur...