Vladimir Feinberg — accepted AI-conference papers

2026

FutureFill: Fast Generation from Convolutional Sequence Models

Naman Agarwal, Xinyi Chen, Evan Dogariu, Devan Shah, Hubert Strauss, Vladimir Feinberg +3

ICLR 2026poster

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 prediction algorithm based on convolutional operators. FutureFill reduces generation time from quadratic to quasilinear i…

Cited by 0 Source ↗Scholar ↗

2023

Sketchy: Memory-efficient Adaptive Regularization with Frequent Directions

Vladimir Feinberg, Xinyi Chen, Y. Jennifer Sun, Rohan Anil, Elad Hazan

NeurIPS 2023poster

Adaptive regularization methods that exploit more than the diagonal entries exhibit state of the art performance for many tasks, but can be prohibitive in terms of memory and running time. We find the spectra of the Kronecker-factored gradient covariance matrix in deep learning (DL) training tasks a…

Cited by 14 Source ↗PDF ↗Scholar ↗