Navid Shervani-Tabar@Nshervt
I had a great time learning from @sirbayes on various topics, including prediction under #DistributionShift and online decision making, during his visit to @NotreDame.
001321
Posts with #DistributionShift
#DistributionShift
Public posts on X that use #DistributionShift.
Related hashtags
Jielin Qiu@_Jason_Q🎊Extremely honored to share that our paper on multimodal model robustness has been accepted as the 1st paper for the Journal of Data-centric Machine Learning Research @DMLRJournal With @yizhu59 @sxjscience @flwenz @mli65 #Multimodal #Robustness #DistributionShiftJournal of Data-centric Machine Learning Research @DMLRJournal'Benchmarking Robustness of Multimodal Image-Text Models under Distribution Shift' by Jielin Qiu, Yi Zhu, Xingjian Shi, Florian Wenzel, Zhiqiang Tang, Ding Zhao, Bo Li, Mu Li Action Editor: Hongyang Zhang #Multimodal #Robustness #DistributionShift23162.3K
'Benchmarking Robustness of Multimodal Image-Text Models under Distribution Shift' by Jielin Qiu, Yi Zhu, Xingjian Shi, Florian Wenzel, Zhiqiang Tang, Ding Zhao, Bo Li, Mu Li Action Editor: Hongyang Zhang #Multimodal #Robustness #DistributionShift02826.1K
Danilo Bzdok@danilobzdokOur paper on #distributionshift in human neuroscience now accepted at @PLOSBiology. Congrats to @oualid_benkarim for leading this quantitative analysis! #untracked #diversity #outofdistribution @enigmabrains @ABCD_ReproNim @BertrandThirion @phyzangDanilo Bzdok @danilobzdokNew preprint, led by @oualid_benkarim, examining out-of-distribution prediction in #ABIDE + #HBN: Analytical tools are needed to get a handle on #untracked #diversity in multi-site cohorts0511- Danilo Bzdok@danilobzdokNew preprint, led by @oualid_benkarim, examining out-of-distribution prediction in #ABIDE + #HBN: Analytical tools are needed to get a handle on #untracked #diversity in multi-site cohorts
01733 
Jonas M. Kübler@jonas_kubler🧐 Do we need special-purpose libraries for powerful two-sample testing⁉️ No! All you need is an existing (Auto)ML framework and our Python package @VStimper @krikamol @bschoelkopf (and Simon Buchholz)11348- Jonas M. Kübler@jonas_kubler@jonas_kublerSince we use data splitting, we can do anything we want on the training data, without the risk of accidental p-value hacking. This allows us to deploy well-engineered ML toolboxes into our two-sample testing pipeline and apply advancements in #autoML to two-sample testing.103
- Jonas M. Kübler@jonas_kubler@jonas_kublerWe use #AutoGluon (@innixma @smolix ) which out of the box leads to great empirical results and can outperform recent MMD-based tests (@AntoninSchrab, @AlexFengLiu1). In particular, we run the #distributionShift benchmark of @steverab @zacharylipton @guenneman.
237 
Kishan@kpb_in_acadYet another #NeurIPS22 post in your timeline! 📣📣 My first in-person conference! 💡💡 Need your #ReinforcementLearning algorithms to be ROBUST??? a.k.a #distributionshift Attend our poster in Hall J: Tue 29 Nov 4 p.m. CST105- Show more posts
