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...
We present Simplex Random Features (SimRFs), a new random feature (RF)
m...
We introduce chefs' random tables (CRTs), a new class of non-trigonometr...
Can we train a single transformer model capable of processing multiple
m...
We propose a new class of random feature methods for linearizing softmax...
Transformer networks are able to capture patterns in data coming from ma...
Approximate bi-level optimization (ABLO) consists of (outer-level)
optim...
There has recently been significant interest in training reinforcement
l...
The Transformer architecture has revolutionized deep learning on sequent...
We introduce Performers, Transformer architectures which can estimate re...
We present a new paradigm for Neural ODE algorithms, calledODEtoODE, whe...
Bilevel optimization (BLO) is a popular approach with many applications
...
Transformer models have achieved state-of-the-art results across a diver...
In this paper we propose a new approach for optimization over orthogonal...
We present a new class of stochastic, geometrically-driven optimization
...
We present a new family of zero-field Ising models over N binary
variabl...
We present a new family of zero-field Ising models over N binary
variabl...
We call an Ising model tractable when it is possible to compute its part...