Hisham Husain

[Hisham Husain @syimplectic]

Interested in understanding the role regularization plays for (distributional) robustness?

Check out my paper “Distributional Robustness with IPMs and links to Regularization and GANs” (accepted to NeurIPS2020) with general IPM results. https://t.co/RQVHVdnV5W #NeurIPS2020

[Zak Mhammedi @mhammediz]

📢Pre-print Alert📢
There is a new algorithm for projection-free (Online) Convex Optimization. No need for expensive Euclidean projections whenever the iterates step outside the feasible set. It achieves the optimal regret bound unlike Frank-Wolfe https://t.co/FiOcyEqjAM

[Luisa Zintgraf @luisa_zintgraf]

In Meta-RL, the *agent* is responsible for collecting the data that we meta-train on. If it doesn't do this well, meta-training can fail! 😱

We address this meta-exploration problem in our #ICML2021 paper. Come by our poster this Friday 5-7AM BST!

[Luisa Zintgraf @luisa_zintgraf]

ICML recording done 🎉 Always fun to build a little recording area 🎥😬🪴

Finally getting better at recording - The entire thing only took me 2 days this time, not 2 weeks 🙌🏼😎

[@[email protected] on Mastodon @ChengSoonOng]

Congratulations to @MengyanZg on your first accepted paper! To be presented soon at #ICML2021 , see https://t.co/8h84Q1lTDH.

[Jacob Brogan @Jacob_Brogan]

Half of the heroes in the MCU seem to have PhDs that they're not using. The whole franchise is a story about the academic employment crisis.

[Luisa Zintgraf @luisa_zintgraf]

Looking forward to present our poster on “Deep Interactive Bayesian RL via Meta-Learning” at #AAMAS in 1 hour! Take a sneak peek below 🤖🐣🤓

Joint work with @smdvln @MLciosek @shimon8282 @katjahofmann. Thinking back to the times of my internship at @MSFTResearch Cambridge! ♥️

[François-Xavier Briol @fx_briol]

Very excited by our recent paper on "Robust Generalised Bayesian Inference for Intractable Likelihoods" with @TakuoMatsubara, @LauchLab and Chris Oates; you can find it here: https://t.co/VfZHKMtaP6. [1/10]

[Xiaoyu Li @xyli94]

Depressing to see my work on AdaGrad constantly missing in the discussion of prior work. I was the first one to prove convergence and adaptivity in stochastic convex and non-convex https://t.co/9SxIU7V5GD
I bet if I were a big shot people would not forget my work so easily😞

[Neil Lawrence @lawrennd]

PMLR Volume 130

Proceedings of AISTATS 2021

Is now available

https://t.co/HnRGNEP4J0

[Sam Power @sp_monte_carlo]

my goodness that's a clean proof

(from https://t.co/2PHO5OjZiy, links to pdf)

[Dawid Kielak @DawidKielak]

This is \Huge: Giles Gardam just announced a counterexample to the Kaplansky unit conjecture! The group ring ℤ₂G of the Promislow group has non-trivial units. Congratulations Giles!

[Hisham Husain @syimplectic]

Very delighted to share this pre-print: joint work with @mhammediz on risk-monotoncinity (a property often taken for granted) with very interesting findings!

[Zak Mhammedi @mhammediz]

Do you expect the risk of your algorithm to monotonically decrease when trained on more data? Surprisingly, this is not always the case even for ERM. With @syimplectic, we derived general risk-monotonic algorithms https://t.co/V5UGNmz63w, resolving parts of a COLT19 open problem.

[Vitaly 🇺🇦 Feldman @vitalyFM]

4 days left. Just in time for the quality ML theory papers that lost the #NeurIPS2020 lottery.

[Hisham Husain @syimplectic]

@jacobmenick @LauchLab @Miles_Brundage It seems this paper devises a novel method based on the primal and dual formulation of Optimal Transport. The paper mentioned in the tweet does not propose a new method but establishes a formal link between f-GANs and Autoencoders through a primal-dual relationship! :)

[Prof. Feynman @ProfFeynman]

If you're the smartest person in the room, then you're in the wrong room. 🧠

[Frank Nielsen @FrnkNlsn]

Highly recommended: draw your figures with the excellent free Ipe sofware https://t.co/fx7d46Iix9 and export into pdf for inclusion in latex files. Can be used for slides too... RT!

[AISTATS 2020 @Aistats2020]

The virtual website where to watch papers and keynotes videos is now available to all participants!
Subscriptions are still open at https://t.co/Uzynd4uYTP. #AISTATS2020

[Jeremias Knoblauch @LauchLab]

1/3
Why is it so hard to design Continual Learning algorithms that do not forget catastrophically?

We give the answer: Such algorithms would solve an NP-hard problem with perfect memory (https://t.co/emFHuF3EP0)

ICML paper with @syimplectic @tommy_da_cat