革新知能統合研究センター

EPFL CIS and RIKEN AIP will hold a joint workshop, titled “EPFL-CIS & RIKEN-AIP Joint Online Workshop on Machine Learning” on September 7 – 8 as follows;

Date:
Sep. 7 Switzerland 9:50 -14:00 / Japan 16:50 – 21:00
Sep. 8 Switzerland 10:00 -14:00 / Japan 17:00 – 21:00

Program:

DAY 1: Sep. 7
(Abstract)
Time: Switzerland / Japan
9:50 / 16:50 Opening Remarks
Masashi Sugiyama (RIKEN-AIP)
Volkan Cevher (EPFL-CIS)

10:00 / 17:00 Jingfeng Zhang (RIKEN-AIP)
Title: Adversarial robustness: from basic science to applications
10:30 / 17:30 Guillermo Ortiz-Jimenez (EPFL-CIS)
Title: Catastrophic overfitting is a bug but also a feature
11:00 / 18:00 Vo Nguyen Le Duy (RIKEN-AIP)
Title: Exact Statistical Inference for the Wasserstein Distance by Selective Inference
11:30 / 18:30 Hugo Cui (EPFL-CIS)
Title: Error rates for kernel methods under source and capacity conditions
12:00 / 19:00 Yu Zhe (RIKEN-AIP)
Title: Domain Generalization via Adversarially Learned Novel Domains
12:30 / 19:30 Berfin Simsek (EPFL-CIS)
Title: Neural Network Loss Landscapes: Symmetry-Induced Saddles and the Global Minima Manifold
13:00 / 20:00 Yaxiong Liu (RIKEN-AIP)
Title: Expert advice problem with noisy low rank loss
13:30 / 20:30 Hadrien Hendrikx (EPFL-CIS)
Title: Beyond spectral gap: the role of the topology in decentralized learning

DAY 2: Sep 8
(Abstract)
Time: Switzerland / Japan
10:00 / 17:00 Etienne Boursier (EPFL-CIS)
Title: Gradient flow dynamics of shallow ReLU networks for square loss and orthogonal inputs
10:30 / 17:30 Chao Li (RIKEN-AIP)
Title: Structure Search for Tensor Network Learning
11:00 / 18:00 Luca Viano (EPFL-CIS)
Title: Proximal Point Imitation Learning
11:30 / 18:30 Matthias Weissenbacher (RIKEN-AIP)
Title: Reinforcement Learning via Symmetries of Dynamics
12:00 / 19:00 Sebastian Neumayer (EPFL-CIS)
Title: Lipschitz Function Approximation using DeepSpline Neural Networks
12:30 / 19:30 Koichi Tojo (RIKEN-AIP)
Title: A method to construct exponential family by representation theory
13:00 / 20:00 Raphael Reinauer (EPFL-CIS)
Title: The Topological BERT: Transforming Attention into Topology for Natural Language Processing
13:30 / 20:30 Tomasz M. Rutkowski (RIKEN-AIP)
Title: Machine Learning Approaches for EEG-derived Early-onset Dementia Neuro-biomarker Development

14:00 / 21:00

Closing Remarks
Masashi Sugiyama (RIKEN-AIP)
Volkan Cevher (EPFL-CIS)

*************
EPFL is located in Switzerland and is one of the most vibrant and cosmopolitan science and technology institutions. EPFL has both a Swiss and international vocation and focuses on three missions: teaching, research and innovation.

The Center for Intelligent Systems (CIS) at EPFL, a joint initiative of the schools ENAC, IC, SB, STI, and SV seeks to advance research and practice in the strategic field of intelligent systems.

RIKEN is Japan’s largest comprehensive research institution renowned for high-quality research in a diverse range of scientific disciplines.

RIKEN Center for Advanced Intelligence Project (AIP) houses more than 30 research teams ranging from fundamentals of machine learning and optimization, applications in medicine, materials, and disaster, to the analysis of ethics and social impact of artificial intelligence.

*************
All participants are required to agree with the AIP Seminar Series Code of Conduct.
Please see the URL below.

TermsOfParticipation

RIKEN AIP will expect adherence to this code throughout the event. We expect cooperation from all participants to help ensure a safe environment for everybody.
*************