[robotics-worldwide] [meetings] ICML 2017 Workshop on Principled Approaches to Deep Learning

Andrzej Pronobis a.pronobis at gmail.com
Wed May 31 12:22:31 PDT 2017


ICML 2017 Workshop on Principled Approaches to Deep Learning
August 10th, 2017
Sydney, Australia

Important dates:
- submission deadline: June 17, 2017
- acceptance notification: July 23, 2017

- full papers (max 8 pages excluding references)
- position papers (max 4 pages excluding references)
- Google Best Paper Awards (600$)

The recent advancements in deep learning have revolutionized the field of
machine learning, enabling unparalleled performance and many new real-world
applications. Yet, the developments that led to this success have often
been driven by empirical studies, and little is known about the theory
behind some of the most successful approaches. While theoretically
well-founded deep learning architectures had been proposed in the past,
they came at a price of increased complexity and reduced tractability.
Recently, we have witnessed considerable interest in principled deep
learning. This led to a better theoretical understanding of existing
architectures as well as development of more mature deep models with solid
theoretical foundations. In this workshop, we intend to review the state of
those developments and provide a platform for the exchange of ideas between
the theoreticians and the practitioners of the growing deep learning
community. Through a series of invited talks by the experts in the field,
contributed presentations, and an interactive panel discussion, the
workshop will cover recent theoretical developments, provide an overview of
promising and mature architectures, highlight their challenges and unique
benefits, and present the most exciting recent results.

Topics of interest include, but are not limited to:
- Deep architectures with solid theoretical foundations
- Theoretical understanding of deep networks
- Theoretical approaches to representation learning
- Algorithmic and optimization challenges, alternatives to backpropagation
- Probabilistic, generative deep models
- Symmetry, transformations, and equivariance
- Practical implementations of principled deep learning approaches
- Domain-specific challenges of principled deep learning approaches
- Applications to real-world problems

We invite submissions of full papers (max 8 pages excluding references) as
well as work-in-progress, position, and challenging problems papers (max 4
pages excluding references). Papers must be formatted using the ICML style
and submitted online (link to the submission system is available at
https://urldefense.proofpoint.com/v2/url?u=http-3A__padl.ws&d=DwIBaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=28NecX-5hhQf0MidW2oqD_uegqn97Yg7DJz1ojbx-cw&s=JC5ihCanPPN6dlTYCtp9DCrbqbZ-KHsv3jbCS65az70&e= ). Accepted papers will be selected for an oral or a poster
presentation. While original contributions are preferred, we also invite
submissions of high-quality work that has recently been published in other

Best submissions will be awarded the Google Best Paper Award for the best
paper and the Google Best Student Paper Award for the best student paper.
Both awards come with a prize of 600$ sponsored by Google.

Invited Speakers
- Sanjeev Arora (Princeton University)
- Pedro Domingos (University of Washington)
- Surya Ganguli (Stanford University)
- Tomaso Poggio (Massachusetts Institute of Technology)
- Ruslan Salakhutdinov (Carnegie Mellon University)
- Nathan Srebro (Toyota Technological Institute at Chicago, University of

- Andrzej Pronobis, University of Washington, KTH
- Robert Gens, Google Research
- Sham Kakade, University of Washington
- Pedro Domingos, University of Washington

For more information, please refer to: https://urldefense.proofpoint.com/v2/url?u=http-3A__padl.ws&d=DwIBaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=28NecX-5hhQf0MidW2oqD_uegqn97Yg7DJz1ojbx-cw&s=JC5ihCanPPN6dlTYCtp9DCrbqbZ-KHsv3jbCS65az70&e= 

More information about the robotics-worldwide mailing list