works on

From the 1 of 1.5k papers with an AI index.

output
20052023
most citedBatch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

24.4k citations

Showing stat.MLShow all

74 papers · 1 filter

stat.ML2021

Variational Bayesian Optimistic Sampling

Brendan O'Donoghue, Tor Lattimore

We consider online sequential decision problems where an agent must balance exploration and exploitation. We derive a set of Bayesian `optimistic' policies which, in the stochastic…

stat.ML20217 cited

Powerpropagation: A sparsity inducing weight reparameterisation

Jonathan Schwarz, Siddhant M. Jayakumar, Razvan Pascanu +2

The training of sparse neural networks is becoming an increasingly important tool for reducing the computational footprint of models at training and evaluation, as well enabling th…

stat.ML20211 cited

Differentiable Annealed Importance Sampling and the Perils of Gradient Noise

Guodong Zhang, Kyle Hsu, Jianing Li +2

Annealed importance sampling (AIS) and related algorithms are highly effective tools for marginal likelihood estimation, but are not fully differentiable due to the use of Metropol…

stat.ML2021

Discretization Drift in Two-Player Games

Mihaela Rosca, Yan Wu, Benoit Dherin +1

Gradient-based methods for two-player games produce rich dynamics that can solve challenging problems, yet can be difficult to stabilize and understand. Part of this complexity ori…

stat.ML20216 cited

Variational Refinement for Importance Sampling Using the Forward Kullback-Leibler Divergence

Ghassen Jerfel, Serena Wang, Clara Fannjiang +3

Variational Inference (VI) is a popular alternative to asymptotically exact sampling in Bayesian inference. Its main workhorse is optimization over a reverse Kullback-Leibler diver…

stat.ML20213 cited

Breaking The Dimension Dependence in Sparse Distribution Estimation under Communication Constraints

Wei-Ning Chen, Peter Kairouz, Ayfer Özgür

We consider the problem of estimating a -dimensional -sparse discrete distribution from its samples observed under a -bit communication constraint. The best-known previous…