Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @HazanPrinceton
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @HazanPrinceton
-
The latest on non-stochastic control from our lab, a new method for control with only partial observation: https://arxiv.org/abs/2001.09254 Joint work with stellar grad students Max Simchowitz (Berkeley) and Karan Singh (Princeton)
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Elad Hazan proslijedio/la je Tweet
The 2020 Information Theory and Applications Workshop kicks off on Sunday here in San Diego! Researchers from around the country are gathering to apply theory (ie deep learning, ML) to diverse areas of science and engineering. Schedule and more info: https://ita.ucsd.edu/ws/ pic.twitter.com/zvOghbsV36
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
New results on non-stochastic control without knowing the system! https://arxiv.org/abs/1911.12178 joint work with
@ShamKakade6 and Karan Singh. You may notice the name is a tribute to one of my favorite papers of all times by Auer, Cesa-Bianchi, Freund and Schapire (a must read!)Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Tune in to my student Karan Singh's talk on non-stochastic control, selected for best paper award at NeurIPS RL workshop later today: https://optrl2019.github.io/index.html
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Video available for
@XinyiChen2 's talk.https://twitter.com/dianarycai/status/1204092408285343745 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Postdoc positions available at COS and EE Princeton, in the theoretical machine learning group, pls see application details below by
@prfsanjeevarora.https://twitter.com/prfsanjeevarora/status/1201902884163592194 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Interested in collaborating with Google AI Princeton on SOTA research? Please apply here: https://careers.google.com/jobs/results/94168920430125766-research-intern-2020/ … (specify Princeton) Ph.D. students with strong engineering/coding skills required to help advance our large-scale control library, details:http://minimizingregret.com
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Real pleasure to give a colloquium at lovely EPFL about our groups' work on non-stochastic control. Many excellent questions and control researchers in the audience.https://twitter.com/le_science4all/status/1197897507159887874 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I highly recommend this forthcoming talk by
@XinyiChen2 about foundational work on boosting and the Frank-Wolfe method!https://twitter.com/WiMLworkshop/status/1192523926649397249 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
Proud advisor moment: excellent paper by my former student Dan Garber, an innovator in projection free methods.https://twitter.com/aminkarbasi/status/1183136183376908289 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Elad Hazan proslijedio/la je Tweet
Conventional wisdom: "Not enough data? Use classic learners (Random Forests, RBF SVM, ..), not deep nets." New paper: infinitely wide nets beat these and also beat finite nets. Infinite nets train faster than finite nets here (hint: Neural Tangent Kernel)! https://arxiv.org/abs/1910.01663
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Rethinking control: excited to announce work from
@GoogleBrain Princeton and@PrincetonCS: the first efficient algorithm w. log-regret ("fast rate") for control of linear dynamical systems with changing costs, studied since the works of Kalman: https://arxiv.org/abs/1909.05062Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Test drive with my colleague Prof. Shai Shalev Schwartz, and the self-driving car he is pioneering in Mobileye. I'm a believer!pic.twitter.com/uvNKnwTnta
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Rethinking control: blog post on our latest work @ Princeton and Google AI on boosting for dynamical systems and control: (w. Naman Agarwal, Nataly Brukhim and Zhou Lu)https://minimizingregret.wordpress.com/2019/07/17/boosting-for-dynamical-systems/ …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Elad Hazan proslijedio/la je Tweet
Remember matrix completion? Deep linear nets solve it better than the old nuclear norm algorithm. Analysis requires going beyond traditional optimization view and understanding
#trajectories. Blog post by Nadav and Wei: http://www.offconvex.org/2019/07/10/trajectories-linear-nets/ … . Paper https://arxiv.org/abs/1905.13655Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Elad Hazan proslijedio/la je Tweet
Speaking tomorrow (Friday) 2pm in
@icmlconf workshop on Theor. Physics in Deep Learning. Title: "Is Optimization a sufficient language to understand deep learning?" (Also, grad Orestis speaking Thurs 4pm about our work on word2vec-like methods for representation learning.)Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
finished compiling lecture notes from my course on optimization for machine learning: (comments/suggestions welcome!)https://drive.google.com/open?id=1GIDnw7T-NT4Do3eC0B5kYJlzwOs6nzIO …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Elad Hazan proslijedio/la je Tweet
Computer science (
@PrincetonCS) is getting a new home at#PrincetonU thanks to a gift from@ericschmidt ‘76 and@wenschmidt. https://bit.ly/2Wf6a5h pic.twitter.com/DBUZAq6XVSComputer Science at Princeton University is Getting a New Home!Historic Guyot Hall will be substantially rebuilt and expanded to create a new home for Princeton’s Department of Computer Science, thanks to a gift from Eric Schmidt ’76 and his wife, Wendy Schmidt.Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Wonderful trend in our department, hope to see the same in other universitieshttps://twitter.com/prfsanjeevarora/status/1129370531051048960 …
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.