Hugh Salimbeni

PhD student in machine learning at Imperial. Currently thinking about Gaussian processes and their hierarchical extensions

[Hugh Salimbeni @HSalimbeni]

@holstsingers https://t.co/OjKxwxW3sx

[Hugh Salimbeni @HSalimbeni]

@xenophar Natural gradient descent gives a significant boost in the Gaussian observation case (minibatch training). I recommend the gpytorch/gpflow demos

[Hugh Salimbeni @HSalimbeni]

Congratulations!

[AISTATS Conference @aistats_conf]

Andreas Damianou (@adamianou) and Neil Lawrence (@lawrennd) are the recipients of the #AISTATS2023 Test of Time Award for their work on Deep Gaussian Processes!

[Hugh Salimbeni @HSalimbeni]

@thomaspinder94 @stefanos_ele @markvanderwilk @jameshensman In jax it should be simpler with built-in forward mode, though what you already have is the most useful

[Hugh Salimbeni @HSalimbeni]

Nice paper! And an important contribution to interpretable ML. Thoughts, @ChristophMolnar?

[James Hensman @jameshensman]

Our new ICML paper shows how to build more interpretable Gaussian-Process Generalized Additive Models (GP-GAMs).

With @xiaoyulu2022 and @Boukouva1Alexis.

Here’s our GP-GAM on the SUSY dataset.

[Hugh Salimbeni @HSalimbeni]

@louistiao It is visually quite similar to the great circle method. A difference is that the samples are not constant density in time, and the periodicity is decoupled from how the time dimension is traversed @scien_ti_st @PhilippHennig5

[Hugh Salimbeni @HSalimbeni]

@louistiao Nice work! Here's yet another way of getting animated sample via a spatio-temporal GP

[Hugh Salimbeni @HSalimbeni]

@louistiao

[Jascha Sohl-Dickstein @jaschasd]

Neural Network Gaussian Processes (NNGPs) correspond to wide Bayesian neural networks! In https://t.co/P9RJeS7RHc we show that the posterior distribution over functions computed by a Bayesian neural network converges to the posterior of the NNGP as layer width grows large.

[Tim G. J. Rudner @timrudner]

Excited to share our #ICML2020 paper on

*Inter-domain Deep Gaussian Processes*

which I will be presenting at #ICML today:

⏲️Time: July 16, 7am & 6pm AOE
💻Room: https://t.co/STgVtG4sAt

📄Paper: https://t.co/u6ubgoLXC7
���️Website: https://t.co/3durqt37o6

w/ @yaringal @sejDino

[Hugh Salimbeni @HSalimbeni]

@stefanos_ele @PhilippHennig5 @lawrennd @fhuszar @maosbot @carlhenrikek @jameshensman The best thing is that the basis for these jokes is infinite (except for the degenerate jokes)

[Arno Solin @arnosolin]

I will be giving an #ICML2020 tutorial on Machine Learning with Signal Processing. The links between the two are many and old; 4x30min is just for scratching the surface. I'm grateful for the opportunity @icmlconf and for all the help I've received.
https://t.co/BXfDKbFZc9

[Martin Jørgensen @JorgensenMart]

At #ICML2020: SDEs with Variational Wishart Diffusions.

We introduce a Bayesian framework with Wishart processes, which learns richer noise models in SDEs, both state-dependent and correlations between outputs. Joint work with @mpd37 and @HSalimbeni

https://t.co/GQ7smM4rzg

[J. Emmanuel Johnson @jejjohnson]

@mpd37 @andrewgwils @HSalimbeni GPyTorch recently released an example of the Doubly Stochastic DeepGP using PyTorch that was implemented in the above paper.

https://t.co/9qP8ogP3EN

[Hugh Salimbeni @HSalimbeni]

@EmtiyazKhan Congratulations! Greatly looking forward to it

[Hugh Salimbeni @HSalimbeni]

Video of the presentation can be found here: https://t.co/snkbUED6o2

[Hugh Salimbeni @HSalimbeni]

Delighted to share a new paper, Deep Gaussian Processes with Importance-Weighted Variational Inference https://t.co/znluVTtU04 appearing at @icmlconf. With @vdutor @jameshensman @mpd37. Code: https://t.co/N8nFxgarnp

[Hugh Salimbeni @HSalimbeni]

Poster and slides: https://t.co/B4pVttgF6q. Talk is on Wednesday at noon in room 101.

[Hugh Salimbeni @HSalimbeni]

@BurtDavidR presenting at ICML. Work with Carl Rasmussen and @markvanderwilk. Huge congratulations!

[Mark van der Wilk @markvanderwilk]

Thanks to @icmlconf for the best paper award for our work on "Rates of Convergence for Sparse Variational Gaussian Process Regression"! First author @davidrburt will be giving the invited talk on Thursday 3PM Hall A. We'll be at poster #237 that evening! https://t.co/gM0b6hRts8

[Markus Heinonen @HeinonenMarkus]

We have a cool new manuscript "ODE2VAE: Deep generative second order ODEs with Bayesian neural networks" https://t.co/kEKEaGGtvM with @CgtyYldz @HLahdesmaki where we embed neural ODE's in VAEs with position-velocity decompositions @AaltoCS @FCAI_fi