Search Results for author: Tom Gunter

Found 11 papers, 1 papers with code

Large Language Model-guided Document Selection

no code implementations7 Jun 2024 Xiang Kong, Tom Gunter, Ruoming Pang

Filtering allows us to quality-match a model trained on the full corpus across diverse benchmarks with at most 70% of the FLOPs, 2.

In-Context Learning Language Modelling +1

Revisiting MoE and Dense Speed-Accuracy Comparisons for LLM Training

1 code implementation23 May 2024 Xianzhi Du, Tom Gunter, Xiang Kong, Mark Lee, ZiRui Wang, Aonan Zhang, Nan Du, Ruoming Pang

In this work, we revisit the settings by adopting step time as a more accurate measure of model complexity, and by determining the total compute budget under the Chinchilla compute-optimal settings.


Mobile V-MoEs: Scaling Down Vision Transformers via Sparse Mixture-of-Experts

no code implementations8 Sep 2023 Erik Daxberger, Floris Weers, BoWen Zhang, Tom Gunter, Ruoming Pang, Marcin Eichner, Michael Emmersberger, Yinfei Yang, Alexander Toshev, Xianzhi Du

We empirically show that our sparse Mobile Vision MoEs (V-MoEs) can achieve a better trade-off between performance and efficiency than the corresponding dense ViTs.

Masked Autoencoding Does Not Help Natural Language Supervision at Scale

no code implementations CVPR 2023 Floris Weers, Vaishaal Shankar, Angelos Katharopoulos, Yinfei Yang, Tom Gunter

Self supervision and natural language supervision have emerged as two exciting ways to train general purpose image encoders which excel at a variety of downstream tasks.

Unknowable Manipulators: Social Network Curator Algorithms

no code implementations17 Jan 2017 Samuel Albanie, Hillary Shakespeare, Tom Gunter

For a social networking service to acquire and retain users, it must find ways to keep them engaged.

Decision Making

Blitzkriging: Kronecker-structured Stochastic Gaussian Processes

no code implementations27 Oct 2015 Thomas Nickson, Tom Gunter, Chris Lloyd, Michael A. Osborne, Stephen Roberts

We present Blitzkriging, a new approach to fast inference for Gaussian processes, applicable to regression, optimisation and classification.

Gaussian Processes General Classification +3

Sampling for Inference in Probabilistic Models with Fast Bayesian Quadrature

no code implementations NeurIPS 2014 Tom Gunter, Michael A. Osborne, Roman Garnett, Philipp Hennig, Stephen J. Roberts

We propose a novel sampling framework for inference in probabilistic models: an active learning approach that converges more quickly (in wall-clock time) than Markov chain Monte Carlo (MCMC) benchmarks.

Active Learning Numerical Integration

Variational Inference for Gaussian Process Modulated Poisson Processes

no code implementations2 Nov 2014 Chris Lloyd, Tom Gunter, Michael A. Osborne, Stephen J. Roberts

We present the first fully variational Bayesian inference scheme for continuous Gaussian-process-modulated Poisson processes.

Astronomy Bayesian Inference +2

Efficient Bayesian Nonparametric Modelling of Structured Point Processes

no code implementations25 Jul 2014 Tom Gunter, Chris Lloyd, Michael A. Osborne, Stephen J. Roberts

This paper presents a Bayesian generative model for dependent Cox point processes, alongside an efficient inference scheme which scales as if the point processes were modelled independently.

Point Processes

Cannot find the paper you are looking for? You can Submit a new open access paper.