Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @michaelrzhang
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @michaelrzhang
-
Prikvačeni tweet
Excited to share the NeurIPS camera-ready version of the Lookahead Optimizer: https://arxiv.org/abs/1907.08610 . Lookahead wraps around and often improves the performance of other optimizers. Very grateful to work on this with James Lucas, Geoffrey Hinton, and Jimmy Ba.pic.twitter.com/TFvfL7F8nh
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
We show our rules compare favorably to rules learned by order-invariant neural networks under different noise models. paper: https://arxiv.org/abs/2001.10092 code:https://github.com/spitis/objective_social_choice …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
This is interesting especially when the voting rule has access to auxiliary information e.g. some proxy for voter experience. Our model is applicable for cooperative policy making and peer review--lots more exciting directions to pursue!
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Our AAMAS 2020 paper “Objective Social Choice: Using Auxiliary Information to Improve Voting Outcomes” (
@SilviuPitis and me) is online! We analyze voting rules under a setup where voters get noisy estimates of some underlying ground truth.Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Michael Zhang proslijedio/la je Tweet
Kobe was a legend on the court and just getting started in what would have been just as meaningful a second act. To lose Gianna is even more heartbreaking to us as parents. Michelle and I send love and prayers to Vanessa and the entire Bryant family on an unthinkable day.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The researcher themed trading cards are really neat too.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Enjoyed this short piece by
@hugo_larochelle: https://www.thestar.com/opinion/contributors/2019/05/10/what-hockey-can-teach-us-about-ai-education.html … via@torontostar It's hard to capture how much hockey is a part of growing up in CanadaPrikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Lots of exciting research on distributional RL lately, and this work shows that dopamine in mouse brain cells is better modeled with a distribution (rather than a point estimate as in classic TD)!https://twitter.com/DeepMind/status/1217510885733928960 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Writing down notes, both digital and physical, between sessions has been very useful for remembering cool ideas, experiences, and people.
#NeurIPS2019Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Michael Zhang proslijedio/la je Tweet
(3) Lookahead Optimizer: k steps forward, 1 step back. Thursday evening, East Hall B+C (#200) We propose a new optimization algorithm that wraps around existing optimizers, reducing variance and improving convergence. Work with
@michaelrzhang, Geoff Hinton, and Jimmy Ba.pic.twitter.com/DcbR0qL4sF
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The algorithm has minimal computational overhead and stores one additional copy of the parameters. It can be incorporated into existing pipelines with a couple of lines of code. Our implementation is available at:https://github.com/michaelrzhang/lookahead …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Lookahead selects a search direction based on k steps of the inner optimizer. We demonstrate that this reduces variance, which improves convergence and makes Lookahead more robust to hyperparameter choices. This is desirable on novel datasets without well-calibrated baselines.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Michael Zhang proslijedio/la je Tweet
There’s a simple way to fight familiarity bias. When you read a good paper with an author you don’t know, especially if they’re junior, take a minute to look them up, get to know their work, cite them, and keep them in mind for events you organize. In short, remember the name!
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Looking forward to giving a talk this week at Toronto Machine Learning Summit (
@TMLS_TO) about the Lookahead Optimizer! Details:https://torontomachinelearning.comHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Inspiring talk from Colleen Lewis (
@CSTeachingTips) about promoting department inclusivity@UofTCompSci today. Believing in students and small changes sustained over time make a huge difference.@harveymudd is doing very well.Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Very cool perspective of viewing an infinite depth network as computing the equilibrium point of a single layer.https://twitter.com/zicokolter/status/1169603463304634368 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
This is on the original set of MAML tasks, and results will most likely be different if tasks required more adaptation.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Neat paper! Shows that inner loop adaptation is not necessary at meta-test time for MAML. Removing the final layer and computing cosine similarities (similar to prototypical nets) is sufficient.https://twitter.com/maithra_raghu/status/1176181071727095808 …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
+1, Waves was quite an emotional journey at TIFF.https://twitter.com/griffschiller/status/1170049434199179270 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
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.