ICML Conference

@icmlconf

A premier international conference for researchers on machine learning. July 10-15, 2018 in Stockholm, Sweden

icml.cc
Geregistreerd in oktober 2011
5 foto's en video's Foto's en video's

Tweets

Je hebt @icmlconf geblokkeerd

Weet je zeker dat je deze Tweets wilt bekijken? @icmlconf wordt niet gedeblokkeerd door Tweets te bekijken.

  1. heeft geretweet
    11 uur geleden

    The camera ready version of our paper "On the Implicit Bias of Dropout" is online:

    4 retweets 18 vind-ik-leuks
    Ongedaan maken
  2. heeft geretweet
    9 uur geleden

    We are thrilled to have 11 papers accepted to this year. , we'll see you in a couple of weeks!

    2 retweets 1 vind-ik-leuk
    Ongedaan maken
  3. heeft geretweet
    28 jun.

    Adversarial Posterior Distillation (APD): Using SGLD+GANs to produce posterior samples for BNNs. Has the flexibility of MCMC + constant memory cost at test time. And it scales easily to hundreds of thousands of network parameters! Accepted to !

    14 retweets 58 vind-ik-leuks
    Ongedaan maken
  4. heeft geretweet
    27 jun.

    I'm thrilled to share two workshop papers that I'll be presenting at ! Both interrogate common notions of algorithmic fairness, especially in the criminal justice system, and challenge the community to embrace more interdisciplinary and critical discourse.

    1 antwoord 10 retweets 28 vind-ik-leuks
    Deze collectie tonen
    Deze collectie tonen
    Ongedaan maken
  5. heeft geretweet
    26 jun.

    Attending in Stockholm? Don't forget to register for Intel's Devjam:

    1 retweet 1 vind-ik-leuk
    Ongedaan maken
  6. heeft geretweet
    25 jun.

    Our new paper is out! We show how population-based diversity search can bootstrap for hard exploration problem PDF: Blog: Code:

    1 antwoord 49 retweets 134 vind-ik-leuks
    Deze collectie tonen
    Deze collectie tonen
    Ongedaan maken
  7. heeft geretweet
    25 jun.

    Who do you think should be interviewed by during ALL suggestions are welcome!

    2 antwoorden 4 retweets 3 vind-ik-leuks
    Ongedaan maken
  8. heeft geretweet
    22 jun.

    Very proud to announce ’s own Dr. Ari Melnick as Scientific Committee Chair of the 1st meeting dedicated to , hosted in tandem w/ . Stay tuned for updates.

    15 retweets 15 vind-ik-leuks
    Ongedaan maken
  9. heeft geretweet
    22 jun.

    Camera ready version of our paper "Adaptive Three Operator Splitting" is now online: Presents an optimization method for non-smooth objectives that does not require to tune any hyperparameter. 3 reasons to dig into it:

    2 antwoorden 17 retweets 44 vind-ik-leuks
    Deze collectie tonen
    Deze collectie tonen
    Ongedaan maken
  10. heeft geretweet
    21 jun.

    Excited to see 's new paper on semi-supervised learning () has been accepted as a long oral at

    1 antwoord 6 retweets 45 vind-ik-leuks
    Ongedaan maken
  11. heeft geretweet
    21 jun.

    Happy to announce that we ( and I) will be presenting our paper "Defining Locality for Surrogates in Post-hoc Interpretablity" at the WHI workshop at ! Paper available at: Can't wait!

    1 antwoord 3 retweets 11 vind-ik-leuks
    Ongedaan maken
  12. heeft geretweet
    19 jun.

    Just released our paper "Gated Path Planning Networks" as well as a implementation for replicating our experiments: - with Emilio Parisotto, , Eric Xing, See you in Stockholm!

    69 retweets 264 vind-ik-leuks
    Ongedaan maken
  13. heeft geretweet
    19 jun.

    Check out our new paper on algorithms and applications for unsupervised representation learning of policies in multiagent systems: w/ Accepted as a long talk at !

    13 retweets 49 vind-ik-leuks
    Ongedaan maken
  14. heeft geretweet
    15 jun.

    Our work on BinGAN will be presented at the 'Theoretical Foundations and Applications of Deep Generative Models' workshop at (). Thanks u organizers!! Stay tuned for the paper.

    6 retweets 24 vind-ik-leuks
    Ongedaan maken
  15. heeft geretweet
    15 jun.

    Our work on MolGAN will be presented at the deep generative models workshop at (). Thanks to the anonymous reviewers for their valuable feedback! We will post an updated version of the paper soon.

    Happy to share our new work on MolGAN: An implicit generative model for small molecular graphs. GANs + RL for generating graphs with desired properties: - Some benefits over VAEs, but can still suffer from mode collapse. Joint work with
    28 retweets 108 vind-ik-leuks
    Ongedaan maken
  16. heeft geretweet
    15 jun.

    New paper with on how we as a community might look at improving the amount of fair ML in practice. Will be presenting ML-Debates. Looking forward to Jared's new paper haiku

    2 retweets 4 vind-ik-leuks
    Ongedaan maken
  17. heeft geretweet
    13 jun.

    Delighted to share our work on antibody binding site prediction (with & ): Accepted for oral presentation at Workshop on Computational Biology! Sets state-of-the-art using cross-modal attention.

    2 retweets 12 vind-ik-leuks
    Ongedaan maken
  18. heeft geretweet
    13 jun.

    Exciting work with , Chaoqi Wang, , Jiaman Li and . Check it on ICML 2018

    Neural Kernel Networks: a differentiable framework for compositional kernel learning. Like the Automatic Statistician, but trainable with gradient-based optimization rather than discrete search. By et al.
    1 antwoord 4 retweets 17 vind-ik-leuks
    Ongedaan maken
  19. heeft geretweet
    13 jun.

    The camera-ready version of Neural Kernel Network (NKN): If you've ever worried about how to choose the kernel function for Gaussian Processes. This is the paper for you. Let data take the call! will present it !!

    51 retweets 178 vind-ik-leuks
    Ongedaan maken
  20. heeft geretweet
    12 jun.

    Happy to announce that our paper "Efficient Model-Based Deep Reinforcement Learning with Variational State Tabulation" will be presented as a long talk at ! Camera-ready version: & code:

    2 antwoorden 3 retweets 17 vind-ik-leuks
    Ongedaan maken

@icmlconf heeft nog niet getweet.

Het laden lijkt wat langer te duren.

Twitter is mogelijk overbelast of ondervindt een tijdelijke onderbreking. Probeer het opnieuw of bekijk de Twitter-status voor meer informatie.

    Je bent misschien ook geïnteresseerd in

    ·