Russell Tsuchida

2026 - ARC DECRA fellow
2025 - Lecturer at Monash University. Data Science and AI Group
2020-2024 - Research scientist in machine learning at CSIRO's Data61.

[Frank Nielsen @FrnkNlsn]

New preprint:

"Generalising maximum mean discrepancy: kernelised functional Bregman divergences"

https://t.co/uJ6wkLCEDd

[Russell Tsuchida @RussellTsuchida]

Squared families can be viewed as simplified versions of previous models, such as squared probabilistic circuits (@loreloc_ ), or squared neural families. We fix the "hidden feature" for extra tractable theory, while still allowing for rich representations.

[Russell Tsuchida @RussellTsuchida]

Squared families are in some precise sense "rare" families which always have tractable (often closed-form):

1. Normalising constant
2. Fisher info
3. Statistical divergence

all linked through a tractable convex Bregman generator and integral. Applied to MLE for params/density.

[Stat.ML Papers @StatMLPapers]

Squared families: Searching beyond regular probability models https://t.co/M3awAKgbOm

[Yannic Kilcher 🇸🇨 @ykilcher]

Come chat with us about "Squared Neural Families: A New Class of Tractable Density Models" tonight on Discord.
6pm UTC, https://t.co/5EPnAc4f9L

[Dino Sejdinovic @sejDino]

Squared Neural Families: A New Class of Tractable Density Models [spotlight], with @RussellTsuchida, @ChengSoonOng, a simple neural network density model with closed form normalising constants, generalising exponential family.
https://t.co/jBvkZDEJGi
https://t.co/i0ctvAwOWF 4/4

[Russell Tsuchida @RussellTsuchida]

We find latent variables under an exponential family model using SGD. We call inner products of these latents Deep Equilibrium Kernels (DEKers). DEKers are built from and generalise NNGP components. DEKers may admit fixed points and are kernel versions of deep equilibrium models.

[Russell Tsuchida @RussellTsuchida]

Pleased to share our freshly accepted paper at TMLR!

If you are interested in neural network kernels (NNGP, NTK), implicit neural networks, SGD, or exponential families, you might enjoy this paper.

https://t.co/ecBwxItZpb

[Accepted papers at TMLR @TmlrPub]

Stochastic gradient updates yield deep equilibrium kernels

Russell Tsuchida, Cheng Soon Ong.

Action editor: Nadav Cohen.

https://t.co/AgaMAZuPAP

#deep #kernels #features

[Russell Tsuchida @RussellTsuchida]

@le_anh_phuong @aistats_conf @ChengSoonOng Hi Phuong. I didn't realise you had started a PhD. Congratulations to you too!!

[Russell Tsuchida @RussellTsuchida]

Nice to be recognised as a Top Reviewer (top 10%) by @aistats_conf!

Also looking forward to attending in April, where I will be presenting https://t.co/3so8rOs01v, which views exponential family PCA in light of deep equilibrium models. Joint work with @ChengSoonOng.

[Gabriel Peyré @gabrielpeyre]

The Legendre transform can be approximated in O(n*log(n)) using a Gaussian convolution. https://t.co/0yoS0KApj3 https://t.co/fx1nIRQui7

[Frank Nielsen @FrnkNlsn]

Some tricks of the trade in #MachineLearning
Kindly add in comments missing tricks please. Thanks. @thegautamkamath
https://t.co/yyjU0uNzug

[Russell Tsuchida @RussellTsuchida]

Camera ready paper available here:
https://t.co/Qg2ZPNlqYs

[Russell Tsuchida @RussellTsuchida]

Happy to announce that work emerging from a successful collaboration between myself, @sukyeeyong, Ali Armin, Lars Peterrson and @ChengSoonOng has been accepted into @iclr_conf!

[Russell Tsuchida @RussellTsuchida]

Suk Yee, Lars, Cheng Soon and myself are part of @CSIROMLAI.

[Mengyan Zhang @MengyanZg]

Excited to present our work Gaussian Process Bandits with Aggregated Feedback (accepted by #AAAI2022) at #NeurIPS2021 #WiML2021 poster session #1 (https://t.co/o0cFa5LlyS) at 3:45-4:45pm AEST .
Pre-print https://t.co/ruE2GTIcYy
Joint work with @RussellTsuchida @ChengSoonOng

[Russell Tsuchida @RussellTsuchida]

@aaronsnoswell I see you found the answer yourself :) Cool stuff! The question was tagged as recreational so I'm curious; do you have an application in mind or is just for fun?

[Russell Tsuchida @RussellTsuchida]

Does anyone want to guess what this is?? 🤔🤔😷

[Russell Tsuchida @RussellTsuchida]

Back in February, @Tea_Pearce, Chris van der Heide, Fred Roosta, @marcus_marcusg and I did some work on the kernels of infinitely wide deep neural networks with GELU and ELU activations. We also studied the fixed points of these kernels. Check it out here:
https://t.co/fJoJP43aYn

[Russell Tsuchida @RussellTsuchida]

@marcus_marcusg Is this about https://t.co/KqF9Maru9x ?

Does "attendance" have to be synced? Do we even need time zones?