2017 Workshop on
Statistical Physics of Disordered Systems
and Its Applications (SPDSA2017)
--- Statistical-Mechanical Informatics and Statistical Machine Learning Theory in Big Data Sciences ---
Schedule: 8-9 February, 2017
Venue: Meeting Room Horai in Akiu Resort Hotel Sakan
(Access)
Yumoto Akiu, Taihaku-Ku, Sendai 982-0241, Japan
Scientific Program:
Organized session only: We do not accept submissions from non-invited speakers.
8 February, 2017
13:20-13:30 Opening
Kazuyuki Tanaka (Graduate School of Information Sciences, Tohoku University, Japan)
13:30-15:00 Session 1
Federico Ricci-Tersenghi (Dipartmento di Fisica, Universitá di Roma, "La Sapienza", Italy)
Title: Phase Transitions in Semidefinite Relaxations (a fast & robust algorithm for community detection)
Muneki Yasuda (Graduate School of Science and Engineering, Yamagata University, Japan)
Title: Relationship between pre-training and maximum likelihood estimation
in deep Boltzmann machines
15:00-15:15 Break
15:15-16:45 Session 2
Pan Zhang (Institute of Theoretical Physics, Chinese Academy of Sciences, China)
Title: Spectral detection of global structures in the noisy data
Utako Yamamoto (Graduate School of Informatics, Kyoto University, Japan)
Title: Shape estimation of elastic object with neural network
9 February 2017
10:15-12:30 Session 3
Sam Schoenholz (Google Brain, Google, USA)
Title: Understanding deep neural networks using statistical field theory
Akihisa Ichiki (Institutes of Innovation for Future Society, Nagoya University, Japan)
Title: Physics of nonequilibrium steady state and its application to numerical technique
Shun Kataoka (Graduate School of Information Sciences, Tohoku University, Japan)
Title: Community detection algorithm utilizing attribute data
12:30-12:40 Closing
Organized by
Masayuki Ohzeki (Graduate School of Information Sciences, Tohoku University, Japan)
Kazuyuki Tanaka (Graduate School of Information Sciences, Tohoku University, Japan)
Supported by
JST-CREST``Foundations of Innovative Algorithms for Big Data''
JSPS KAKENHI Grants-in-Aid for Scientific Research (B) ``Design Theory of Probabilistic Computational Modeling in Community Detection by Non-Additive Volume and Entropy'' (No.25280089)
Co-Supported by
Graduate School of Information Sciences (GSIS), Tohoku University, Japan
Related Webpages
SPDSA2013 (20-21 March, 2013, Sendai, Japan)
SPDSA2014 (10 March, 2014, Kyoto, Japan)
SPDSA2015 (19 February, 2015, Kyoto, Japan)
SPDSA2016 (27-28 January, 2016, Sendai, Japan)
Contact to SPDSA2017 office