-
My first ICLR was a blast! Notes for
@iclr2019 available here: https://david-abel.github.io/notes/iclr_2019.pdf …#ICLR2019 pic.twitter.com/BH0W80w8B4
-
What makes for a Lottery Ticket (
#ICLR2019) in neural networks? We provide answers in our new paper, Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask! Read about it on our blog. With@lanjanice,@savvyrl,@jasonyohttps://eng.uber.com/deconstructing-lottery-tickets/ … -
Check out our paper on "Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous Outputs" (now accepted at
#iclr2019) with my amazing advisor Prof. Yulia Tsvetkov: https://openreview.net/forum?id=rJlDnoA5Y7 … -
Top trends I saw at
#ICLR2019 include the rise of unsupervised representation learning, RNN losing its luster, GANs still dominating, RL moving towards meta-learning, the return of old school ideas. Great conference for not only ideas but also motivation https://huyenchip.com/2019/05/12/top-8-trends-from-iclr-2019.html … -
My work with
@jaschasd and@goodfellow_ian on Adversarial reprogramming of neural networks (https://arxiv.org/abs/1806.11146 ) is now accepted at#ICLR2019 -
"Learning Representations Using Causal Invariance" Leon Bottou. Invited Talk
#ICLR2019 https://videoken.com/embed/8UxS4ls6g1g?tocitem=2 … It describes: "Invariant Risk Minimization"
https://arxiv.org/pdf/1907.02893.pdf … -
I will be at
#ICLR2019 to present our work: Augmented Cyclic Adversarial Learning for Low Resource Domain Adaptation https://openreview.net/forum?id=B1G9doA9F7 … w/@yingbozhou_ai@CaimingXiong@RichardSocherPrikaži ovu nit -
Our paper "How powerful are graph neural networks?" was accepted as ICLR oral! Joint work with Keyulu Xu, Jure Leskovec and Stefanie Jegelka. Check out our paper here: https://openreview.net/forum?id=ryGs6iA5Km …
#iclr2019 -
#ICLR2019 is almost here- check out our 2nd Learning from Limited Labeled Data (LLD) workshop https://lld-workshop.github.io/ on Monday 5/6. We are grateful to have a really exciting lineup including@chelseabfinn Luna Dong@AnimaAnandkumar@ermonste! -
#ICLR2019 done. opinions: 1. RL and GANs are obscenely over-represented 2. Empirical/querying based interpretation and understanding is hip now which is nice 3. The citation game is really biased, lots of papers from sub-disciplines that should've been cited and weren't -
Excited to organize a workshop on structure & priors in RL at
#iclr2019 on Monday with a great set of talks and posters! http://spirl.info/2019/program If you are a junior researcher, please consider submitting a challenge question to our speakers! http://spirl.info/2019/call/#call-for-challenge-questions …Prikaži ovu nit -
Excited to preview our list of invited speakers for
#iclr2019 in New Orleans: Léon Bottou, Cynthia Dwork, Ian Goodfellow, Noah Goodman, Mirella Lapata, Pierre-Yves Oudeyer, Emily Shuckburgh, and, Zeynep Tufekci Tickets go on sale tomorrow @ 4pm PST at http://iclr.ccPrikaži ovu nit -
New paper by lead author from my group
@iftenney in collaboration with JSALT workshop members just accepted to ICLR!#iclr2019 https://openreview.net/forum?id=SJzSgnRcKX¬eId=Syes7Emgl4 … -
Posters from
#ICLR2019, all nicely accessible in one place. https://postersession.ai pic.twitter.com/wzaJ7hUzIm
-
Here's the talk I gave on 'Deterministic variational inference for robust Bayesian neural networks' in ICLR2019
#ICLR2019 https://youtu.be/XpeSImGoT9A paper link: https://openreview.net/pdf?id=B1l08oAct7 … Tensorflow by MSR: https://github.com/Microsoft/deterministic-variational-inference … Tensor2Tensor by Google:https://github.com/tensorflow/tensor2tensor/commit/master …Prikaži ovu nit -
Deep Generative Models for Graphs: Methods & Applications. Slides from my talk at
#ICLR2019 workshop on Representation Learning on Graphs and Manifolds. http://i.stanford.edu/~jure/pub/talks2/graph_gen-iclr-may19-long.pdf …pic.twitter.com/QgjmwOJ8ms
-
Happy to announce that a paper "Distributional Concavity Regularization For GANs" is accepted for poster presentation in
#ICLR2019 from Preferred Networks. Congrats to Shoichiro Yamaguchi and Masanori Koyama!!! https://openreview.net/forum?id=SklEEnC5tQ¬eId=SklEEnC5tQ … -
Graph Wavelet Neural Network
#ICLR2019 Compared to graph Fourier transform (1) Graph wavelets are local & sparse (2) Graph wavelet transform is computationally efficient (3) Convolution is localized in vertex domain. Paper https://openreview.net/forum?id=H1ewdiR5tQ … PyTorch https://github.com/benedekrozemberczki/GraphWaveletNeuralNetwork … pic.twitter.com/SiEdD6UOj0
-
My Relativistic GANs paper was accepted to
#ICLR2019!Prikaži ovu nit -
Excited to announce that our paper, "A Statistical Approach to Assessing Neural Network Robustness" has been accepted to publication at
#ICLR2019!
Joint work with @tom_rainforth,@yeewhye, and M. Pawan Kumar. https://arxiv.org/abs/1811.07209 pic.twitter.com/tPseHcqveV
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.