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
📢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
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!
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 🙌🏼😎
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! ♥️
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]
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😞
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!
Very delighted to share this pre-print: joint work with @mhammediz on risk-monotoncinity (a property often taken for granted) with very interesting findings!
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.
@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! :)
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!
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
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