Timezone: »
Cheng Zhang: Active Mini-Batch Sampling using Repulsive Point Processes
Cheng Zhang
Fri Jun 14 04:40 PM -- 05:20 PM (PDT) @
We explore active mini-batch selection using repulsive point processes for stochastic gradient descent (SGD). Our approach simultaneously introduces active bias and leads to stochastic gradients with lower variance. We show theoretically and empirically that our approach improves over standard SGD both in terms of convergence speed as well as final model performance.
Author Information
Cheng Zhang (Microsoft Research, Cambridge)
More from the Same Authors
-
2021 : Optimal transport for causal discovery »
Ruibo Tu · Kun Zhang · Hedvig Kjellström · Cheng Zhang -
2021 : VICAUSE: Simultaneous missing value imputation and causal discovery »
Pablo Morales-Alvarez · Angus Lamb · Simon Woodhead · Simon Pyton Jones · Miltiadis Allamanis · Cheng Zhang -
2023 Poster: CO-BED: Information-Theoretic Contextual Optimization via Bayesian Experimental Design »
Desi Ivanova · Joel Jennings · Tom Rainforth · Cheng Zhang · Adam Foster -
2023 Workshop: Challenges in Deployable Generative AI »
Swami Sankaranarayanan · Thomas Hartvigsen · Camille Bilodeau · Ryutaro Tanno · Cheng Zhang · Florian Tramer · Phillip Isola -
2020 : Invited talk 4: Divergence Measures in Variational Inference and How to Choose Them »
Cheng Zhang -
2019 Poster: EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE »
Chao Ma · Sebastian Tschiatschek · Konstantina Palla · Jose Miguel Hernandez-Lobato · Sebastian Nowozin · Cheng Zhang -
2019 Oral: EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE »
Chao Ma · Sebastian Tschiatschek · Konstantina Palla · Jose Miguel Hernandez-Lobato · Sebastian Nowozin · Cheng Zhang