4 papers
FutureFill: Fast Generation from Convolutional Sequence Models
Naman Agarwal, Xinyi Chen, Evan Dogariu +6
We address the challenge of efficient auto-regressive generation in sequence prediction models by introducing FutureFill, a general-purpose fast generation method for any sequence…
Benchmarking Neural Network Training Algorithms
George E. Dahl, Frank Schneider, Zachary Nado +22
Training algorithms, broadly construed, are an essential part of every deep learning pipeline. Training algorithm improvements that speed up training across a wide variety of workl…
Stacking as Accelerated Gradient Descent
Naman Agarwal, Pranjal Awasthi, Satyen Kale +1
Stacking, a heuristic technique for training deep residual networks by progressively increasing the number of layers and initializing new layers by copying parameters from older la…
Provable Length Generalization in Sequence Prediction via Spectral Filtering
Annie Marsden, Evan Dogariu, Naman Agarwal +3
We consider the problem of length generalization in sequence prediction. We define a new metric of performance in this setting -- the Asymmetric-Regret -- which measures regret aga…